WorldWideScience

Sample records for learning neural basis

  1. Exploring the spatio-temporal neural basis of face learning

    Science.gov (United States)

    Yang, Ying; Xu, Yang; Jew, Carol A.; Pyles, John A.; Kass, Robert E.; Tarr, Michael J.

    2017-01-01

    Humans are experts at face individuation. Although previous work has identified a network of face-sensitive regions and some of the temporal signatures of face processing, as yet, we do not have a clear understanding of how such face-sensitive regions support learning at different time points. To study the joint spatio-temporal neural basis of face learning, we trained subjects to categorize two groups of novel faces and recorded their neural responses using magnetoencephalography (MEG) throughout learning. A regression analysis of neural responses in face-sensitive regions against behavioral learning curves revealed significant correlations with learning in the majority of the face-sensitive regions in the face network, mostly between 150–250 ms, but also after 300 ms. However, the effect was smaller in nonventral regions (within the superior temporal areas and prefrontal cortex) than that in the ventral regions (within the inferior occipital gyri (IOG), midfusiform gyri (mFUS) and anterior temporal lobes). A multivariate discriminant analysis also revealed that IOG and mFUS, which showed strong correlation effects with learning, exhibited significant discriminability between the two face categories at different time points both between 150–250 ms and after 300 ms. In contrast, the nonventral face-sensitive regions, where correlation effects with learning were smaller, did exhibit some significant discriminability, but mainly after 300 ms. In sum, our findings indicate that early and recurring temporal components arising from ventral face-sensitive regions are critically involved in learning new faces. PMID:28570739

  2. Tensor Basis Neural Network v. 1.0 (beta)

    Energy Technology Data Exchange (ETDEWEB)

    2017-03-28

    This software package can be used to build, train, and test a neural network machine learning model. The neural network architecture is specifically designed to embed tensor invariance properties by enforcing that the model predictions sit on an invariant tensor basis. This neural network architecture can be used in developing constitutive models for applications such as turbulence modeling, materials science, and electromagnetism.

  3. Machine learning of radial basis function neural network based on Kalman filter: Introduction

    Directory of Open Access Journals (Sweden)

    Vuković Najdan L.

    2014-01-01

    Full Text Available This paper analyzes machine learning of radial basis function neural network based on Kalman filtering. Three algorithms are derived: linearized Kalman filter, linearized information filter and unscented Kalman filter. We emphasize basic properties of these estimation algorithms, demonstrate how their advantages can be used for optimization of network parameters, derive mathematical models and show how they can be applied to model problems in engineering practice.

  4. The neural circuit basis of learning

    Science.gov (United States)

    Patrick, Kaifosh William John

    The astounding capacity for learning ranks among the nervous system's most impressive features. This thesis comprises studies employing varied approaches to improve understanding, at the level of neural circuits, of the brain's capacity for learning. The first part of the thesis contains investigations of hippocampal circuitry -- both theoretical work and experimental work in the mouse Mus musculus -- as a model system for declarative memory. To begin, Chapter 2 presents a theory of hippocampal memory storage and retrieval that reflects nonlinear dendritic processing within hippocampal pyramidal neurons. As a prelude to the experimental work that comprises the remainder of this part, Chapter 3 describes an open source software platform that we have developed for analysis of data acquired with in vivo Ca2+ imaging, the main experimental technique used throughout the remainder of this part of the thesis. As a first application of this technique, Chapter 4 characterizes the content of signaling at synapses between GABAergic neurons of the medial septum and interneurons in stratum oriens of hippocampal area CA1. Chapter 5 then combines these techniques with optogenetic, pharmacogenetic, and pharmacological manipulations to uncover inhibitory circuit mechanisms underlying fear learning. The second part of this thesis focuses on the cerebellum-like electrosensory lobe in the weakly electric mormyrid fish Gnathonemus petersii, as a model system for non-declarative memory. In Chapter 6, we study how short-duration EOD motor commands are recoded into a complex temporal basis in the granule cell layer, which can be used to cancel Purkinje-like cell firing to the longer duration and temporally varying EOD-driven sensory responses. In Chapter 7, we consider not only the temporal aspects of the granule cell code, but also the encoding of body position provided from proprioceptive and efference copy sources. Together these studies clarify how the cerebellum-like circuitry of the

  5. Radial basis function neural networks with sequential learning MRAN and its applications

    CERN Document Server

    Sundararajan, N; Wei Lu Ying

    1999-01-01

    This book presents in detail the newly developed sequential learning algorithm for radial basis function neural networks, which realizes a minimal network. This algorithm, created by the authors, is referred to as Minimal Resource Allocation Networks (MRAN). The book describes the application of MRAN in different areas, including pattern recognition, time series prediction, system identification, control, communication and signal processing. Benchmark problems from these areas have been studied, and MRAN is compared with other algorithms. In order to make the book self-contained, a review of t

  6. Learning from neural control.

    Science.gov (United States)

    Wang, Cong; Hill, David J

    2006-01-01

    One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, first, a deterministic learning mechanism is presented, by which an appropriately designed adaptive neural controller is capable of learning closed-loop system dynamics during tracking control to a periodic reference orbit. Among various neural network (NN) architectures, the localized radial basis function (RBF) network is employed. A property of persistence of excitation (PE) for RBF networks is established, and a partial PE condition of closed-loop signals, i.e., the PE condition of a regression subvector constructed out of the RBFs along a periodic state trajectory, is proven to be satisfied. Accurate NN approximation for closed-loop system dynamics is achieved in a local region along the periodic state trajectory, and a learning ability is implemented during a closed-loop feedback control process. Second, based on the deterministic learning mechanism, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve closed-loop stability and improved control performance. The significance of this paper is that the presented deterministic learning mechanism and the neural learning control scheme provide elementary components toward the development of a biologically-plausible learning and control methodology. Simulation studies are included to demonstrate the effectiveness of the approach.

  7. Neural networks and statistical learning

    CERN Document Server

    Du, Ke-Lin

    2014-01-01

    Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

  8. Neural Basis of Reinforcement Learning and Decision Making

    Science.gov (United States)

    Lee, Daeyeol; Seo, Hyojung; Jung, Min Whan

    2012-01-01

    Reinforcement learning is an adaptive process in which an animal utilizes its previous experience to improve the outcomes of future choices. Computational theories of reinforcement learning play a central role in the newly emerging areas of neuroeconomics and decision neuroscience. In this framework, actions are chosen according to their value functions, which describe how much future reward is expected from each action. Value functions can be adjusted not only through reward and penalty, but also by the animal’s knowledge of its current environment. Studies have revealed that a large proportion of the brain is involved in representing and updating value functions and using them to choose an action. However, how the nature of a behavioral task affects the neural mechanisms of reinforcement learning remains incompletely understood. Future studies should uncover the principles by which different computational elements of reinforcement learning are dynamically coordinated across the entire brain. PMID:22462543

  9. Neural plasticity of development and learning.

    Science.gov (United States)

    Galván, Adriana

    2010-06-01

    Development and learning are powerful agents of change across the lifespan that induce robust structural and functional plasticity in neural systems. An unresolved question in developmental cognitive neuroscience is whether development and learning share the same neural mechanisms associated with experience-related neural plasticity. In this article, I outline the conceptual and practical challenges of this question, review insights gleaned from adult studies, and describe recent strides toward examining this topic across development using neuroimaging methods. I suggest that development and learning are not two completely separate constructs and instead, that they exist on a continuum. While progressive and regressive changes are central to both, the behavioral consequences associated with these changes are closely tied to the existing neural architecture of maturity of the system. Eventually, a deeper, more mechanistic understanding of neural plasticity will shed light on behavioral changes across development and, more broadly, about the underlying neural basis of cognition. (c) 2010 Wiley-Liss, Inc.

  10. The neural basis of implicit learning and memory: a review of neuropsychological and neuroimaging research.

    Science.gov (United States)

    Reber, Paul J

    2013-08-01

    Memory systems research has typically described the different types of long-term memory in the brain as either declarative versus non-declarative or implicit versus explicit. These descriptions reflect the difference between declarative, conscious, and explicit memory that is dependent on the medial temporal lobe (MTL) memory system, and all other expressions of learning and memory. The other type of memory is generally defined by an absence: either the lack of dependence on the MTL memory system (nondeclarative) or the lack of conscious awareness of the information acquired (implicit). However, definition by absence is inherently underspecified and leaves open questions of how this type of memory operates, its neural basis, and how it differs from explicit, declarative memory. Drawing on a variety of studies of implicit learning that have attempted to identify the neural correlates of implicit learning using functional neuroimaging and neuropsychology, a theory of implicit memory is presented that describes it as a form of general plasticity within processing networks that adaptively improve function via experience. Under this model, implicit memory will not appear as a single, coherent, alternative memory system but will instead be manifested as a principle of improvement from experience based on widespread mechanisms of cortical plasticity. The implications of this characterization for understanding the role of implicit learning in complex cognitive processes and the effects of interactions between types of memory will be discussed for examples within and outside the psychology laboratory. Copyright © 2013 Elsevier Ltd. All rights reserved.

  11. Behavioural and neural basis of anomalous motor learning in children with autism.

    Science.gov (United States)

    Marko, Mollie K; Crocetti, Deana; Hulst, Thomas; Donchin, Opher; Shadmehr, Reza; Mostofsky, Stewart H

    2015-03-01

    Autism spectrum disorder is a developmental disorder characterized by deficits in social and communication skills and repetitive and stereotyped interests and behaviours. Although not part of the diagnostic criteria, individuals with autism experience a host of motor impairments, potentially due to abnormalities in how they learn motor control throughout development. Here, we used behavioural techniques to quantify motor learning in autism spectrum disorder, and structural brain imaging to investigate the neural basis of that learning in the cerebellum. Twenty children with autism spectrum disorder and 20 typically developing control subjects, aged 8-12, made reaching movements while holding the handle of a robotic manipulandum. In random trials the reach was perturbed, resulting in errors that were sensed through vision and proprioception. The brain learned from these errors and altered the motor commands on the subsequent reach. We measured learning from error as a function of the sensory modality of that error, and found that children with autism spectrum disorder outperformed typically developing children when learning from errors that were sensed through proprioception, but underperformed typically developing children when learning from errors that were sensed through vision. Previous work had shown that this learning depends on the integrity of a region in the anterior cerebellum. Here we found that the anterior cerebellum, extending into lobule VI, and parts of lobule VIII were smaller than normal in children with autism spectrum disorder, with a volume that was predicted by the pattern of learning from visual and proprioceptive errors. We suggest that the abnormal patterns of motor learning in children with autism spectrum disorder, showing an increased sensitivity to proprioceptive error and a decreased sensitivity to visual error, may be associated with abnormalities in the cerebellum. © The Author (2015). Published by Oxford University Press on behalf

  12. Learning in Artificial Neural Systems

    Science.gov (United States)

    Matheus, Christopher J.; Hohensee, William E.

    1987-01-01

    This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

  13. A prediction method for the wax deposition rate based on a radial basis function neural network

    Directory of Open Access Journals (Sweden)

    Ying Xie

    2017-06-01

    Full Text Available The radial basis function neural network is a popular supervised learning tool based on machinery learning technology. Its high precision having been proven, the radial basis function neural network has been applied in many areas. The accumulation of deposited materials in the pipeline may lead to the need for increased pumping power, a decreased flow rate or even to the total blockage of the line, with losses of production and capital investment, so research on predicting the wax deposition rate is significant for the safe and economical operation of an oil pipeline. This paper adopts the radial basis function neural network to predict the wax deposition rate by considering four main influencing factors, the pipe wall temperature gradient, pipe wall wax crystal solubility coefficient, pipe wall shear stress and crude oil viscosity, by the gray correlational analysis method. MATLAB software is employed to establish the RBF neural network. Compared with the previous literature, favorable consistency exists between the predicted outcomes and the experimental results, with a relative error of 1.5%. It can be concluded that the prediction method of wax deposition rate based on the RBF neural network is feasible.

  14. The neural basis of task switching changes with skill acquisition

    Directory of Open Access Journals (Sweden)

    Koji eJimura

    2014-05-01

    Full Text Available Learning novel skills involves reorganization and optimization of cognitive processing involving a broad network of brain regions. Previous work has shown asymmetric costs of switching to a well-trained task versus a poorly-trained task, but the neural basis of these differential switch costs is unclear. The current study examined the neural signature of task switching in the context of acquisition of new skill. Human participants alternated randomly between a novel visual task (mirror-reversed word reading and a highly practiced one (plain word reading, allowing the isolation of task switching and skill set maintenance. Two scan sessions were separated by two weeks, with behavioral training on the mirror reading task in between the two sessions. Broad cortical regions, including bilateral prefrontal, parietal, and extrastriate cortices, showed decreased activity associated with learning of the mirror reading skill. In contrast, learning to switch to the novel skill was associated with decreased activity in a focal subcortical region in the dorsal striatum. Switching to the highly practiced task was associated with a non-overlapping set of regions, suggesting substantial differences in the neural substrates of switching as a function of task skill. Searchlight multivariate pattern analysis also revealed that learning was associated with decreased pattern information for mirror versus plain reading tasks in fronto-parietal regions. Inferior frontal junction and posterior parietal cortex showed a joint effect of univariate activation and pattern information. These results suggest distinct learning mechanisms task performance and executive control as a function of learning.

  15. Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

    Czech Academy of Sciences Publication Activity Database

    Neruda, Roman; Vidnerová, Petra

    2009-01-01

    Roč. 1, č. 2 (2009), s. 49-57 ISSN 2005-4262 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural network * RBF networks * regularization * learning Subject RIV: IN - Informatics, Computer Science http://www.sersc.org/journals/IJGDC/vol2_no1/5.pdf

  16. Learning-induced neural plasticity of speech processing before birth.

    Science.gov (United States)

    Partanen, Eino; Kujala, Teija; Näätänen, Risto; Liitola, Auli; Sambeth, Anke; Huotilainen, Minna

    2013-09-10

    Learning, the foundation of adaptive and intelligent behavior, is based on plastic changes in neural assemblies, reflected by the modulation of electric brain responses. In infancy, auditory learning implicates the formation and strengthening of neural long-term memory traces, improving discrimination skills, in particular those forming the prerequisites for speech perception and understanding. Although previous behavioral observations show that newborns react differentially to unfamiliar sounds vs. familiar sound material that they were exposed to as fetuses, the neural basis of fetal learning has not thus far been investigated. Here we demonstrate direct neural correlates of human fetal learning of speech-like auditory stimuli. We presented variants of words to fetuses; unlike infants with no exposure to these stimuli, the exposed fetuses showed enhanced brain activity (mismatch responses) in response to pitch changes for the trained variants after birth. Furthermore, a significant correlation existed between the amount of prenatal exposure and brain activity, with greater activity being associated with a higher amount of prenatal speech exposure. Moreover, the learning effect was generalized to other types of similar speech sounds not included in the training material. Consequently, our results indicate neural commitment specifically tuned to the speech features heard before birth and their memory representations.

  17. Logarithmic learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2014-12-01

    Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

  18. Neuronal spike sorting based on radial basis function neural networks

    Directory of Open Access Journals (Sweden)

    Taghavi Kani M

    2011-02-01

    Full Text Available "nBackground: Studying the behavior of a society of neurons, extracting the communication mechanisms of brain with other tissues, finding treatment for some nervous system diseases and designing neuroprosthetic devices, require an algorithm to sort neuralspikes automatically. However, sorting neural spikes is a challenging task because of the low signal to noise ratio (SNR of the spikes. The main purpose of this study was to design an automatic algorithm for classifying neuronal spikes that are emitted from a specific region of the nervous system."n "nMethods: The spike sorting process usually consists of three stages: detection, feature extraction and sorting. We initially used signal statistics to detect neural spikes. Then, we chose a limited number of typical spikes as features and finally used them to train a radial basis function (RBF neural network to sort the spikes. In most spike sorting devices, these signals are not linearly discriminative. In order to solve this problem, the aforesaid RBF neural network was used."n "nResults: After the learning process, our proposed algorithm classified any arbitrary spike. The obtained results showed that even though the proposed Radial Basis Spike Sorter (RBSS reached to the same error as the previous methods, however, the computational costs were much lower compared to other algorithms. Moreover, the competitive points of the proposed algorithm were its good speed and low computational complexity."n "nConclusion: Regarding the results of this study, the proposed algorithm seems to serve the purpose of procedures that require real-time processing and spike sorting.

  19. Neural Basis of Intrinsic Motivation: Evidence from Event-Related Potentials.

    Science.gov (United States)

    Jin, Jia; Yu, Liping; Ma, Qingguo

    2015-01-01

    Human intrinsic motivation is of great importance in human behavior. However, although researchers have focused on this topic for decades, its neural basis was still unclear. The current study employed event-related potentials to investigate the neural disparity between an interesting stop-watch (SW) task and a boring watch-stop task (WS) to understand the neural mechanisms of intrinsic motivation. Our data showed that, in the cue priming stage, the cue of the SW task elicited smaller N2 amplitude than that of the WS task. Furthermore, in the outcome feedback stage, the outcome of the SW task induced smaller FRN amplitude and larger P300 amplitude than that of the WS task. These results suggested that human intrinsic motivation did exist and that it can be detected at the neural level. Furthermore, intrinsic motivation could be quantitatively indexed by the amplitude of ERP components, such as N2, FRN, and P300, in the cue priming stage or feedback stage. Quantitative measurements would also be convenient for intrinsic motivation to be added as a candidate social factor in the construction of a machine learning model.

  20. Thermodynamic efficiency of learning a rule in neural networks

    Science.gov (United States)

    Goldt, Sebastian; Seifert, Udo

    2017-11-01

    Biological systems have to build models from their sensory input data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a binary classification rule for these inputs from examples provided by a teacher. We analyse the ability of the network to apply the rule to new inputs, that is to generalise from past experience. Using stochastic thermodynamics, we show that the thermodynamic costs of the learning process provide an upper bound on the amount of information that the network is able to learn from its teacher for both batch and online learning. This allows us to introduce a thermodynamic efficiency of learning. We analytically compute the dynamics and the efficiency of a noisy neural network performing online learning in the thermodynamic limit. In particular, we analyse three popular learning algorithms, namely Hebbian, Perceptron and AdaTron learning. Our work extends the methods of stochastic thermodynamics to a new type of learning problem and might form a suitable basis for investigating the thermodynamics of decision-making.

  1. Bio-Inspired Neural Model for Learning Dynamic Models

    Science.gov (United States)

    Duong, Tuan; Duong, Vu; Suri, Ronald

    2009-01-01

    A neural-network mathematical model that, relative to prior such models, places greater emphasis on some of the temporal aspects of real neural physical processes, has been proposed as a basis for massively parallel, distributed algorithms that learn dynamic models of possibly complex external processes by means of learning rules that are local in space and time. The algorithms could be made to perform such functions as recognition and prediction of words in speech and of objects depicted in video images. The approach embodied in this model is said to be "hardware-friendly" in the following sense: The algorithms would be amenable to execution by special-purpose computers implemented as very-large-scale integrated (VLSI) circuits that would operate at relatively high speeds and low power demands.

  2. Neural basis of disgust perception in racial prejudice.

    Science.gov (United States)

    Liu, Yunzhe; Lin, Wanjun; Xu, Pengfei; Zhang, Dandan; Luo, Yuejia

    2015-12-01

    Worldwide racial prejudice is originated from in-group/out-group discrimination. This prejudice can bias face perception at the very beginning of social interaction. However, little is known about the neurocognitive mechanism underlying the influence of racial prejudice on facial emotion perception. Here, we examined the neural basis of disgust perception in racial prejudice using a passive viewing task and functional magnetic resonance imaging. We found that compared with the disgusted faces of in-groups, the disgusted faces of out-groups result in increased amygdala and insular engagement, positive coupling of the insula with amygdala-based emotional system, and negative coupling of the insula with anterior cingulate cortex (ACC)-based regulatory system. Furthermore, machine-learning algorithms revealed that the level of implicit racial prejudice could be predicted by functional couplings of the insula with both the amygdala and the ACC, which suggests that the insula is largely involved in racially biased disgust perception through two distinct neural circuits. In addition, individual difference in disgust sensitivity was found to be predictive of implicit racial prejudice. Taken together, our results suggest a crucial role of insula-centered circuits for disgust perception in racial prejudice. © 2015 Wiley Periodicals, Inc.

  3. Genetic learning in rule-based and neural systems

    Science.gov (United States)

    Smith, Robert E.

    1993-01-01

    The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.

  4. Detection of an inhibitory cortical gradient underlying peak shift in learning: a neural basis for a false memory.

    Science.gov (United States)

    Miasnikov, Alexandre A; Weinberger, Norman M

    2012-11-01

    Experience often does not produce veridical memory. Understanding false attribution of events constitutes an important problem in memory research. "Peak shift" is a well-characterized, controllable phenomenon in which human and animal subjects that receive reinforcement associated with one sensory stimulus later respond maximally to another stimulus in post-training stimulus generalization tests. Peak shift ordinarily develops in discrimination learning (reinforced CS+, unreinforced CS-) and has long been attributed to the interaction of an excitatory gradient centered on the CS+ and an inhibitory gradient centered on the CS-; the shift is away from the CS-. In contrast, we have obtained peak shifts during single tone frequency training, using stimulation of the cholinergic nucleus basalis (NB) to implant behavioral memory into the rat. As we also recorded cortical activity, we took the opportunity to investigate the possible existence of a neural frequency gradient that could account for behavioral peak shift. Behavioral frequency generalization gradients (FGGs, interruption of ongoing respiration) were determined twice before training while evoked potentials were recorded from the primary auditory cortex (A1), to obtain a baseline gradient of "habituatory" neural decrement. A post-training behavioral FGG obtained 24h after three daily sessions of a single tone paired with NB stimulation (200 trials/day) revealed a peak shift. The peak of the FGG was at a frequency lower than the CS while the cortical inhibitory gradient was at a frequency higher than the CS frequency. Further analysis indicated that the frequency location and magnitude of the gradient could account for the behavioral peak shift. These results provide a neural basis for a systematic case of memory misattribution and may provide an animal model for the study of the neural bases of a type of "false memory". Published by Elsevier Inc.

  5. QSAR modelling using combined simple competitive learning networks and RBF neural networks.

    Science.gov (United States)

    Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

    2018-04-01

    The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

  6. Satisfiability of logic programming based on radial basis function neural networks

    International Nuclear Information System (INIS)

    Hamadneh, Nawaf; Sathasivam, Saratha; Tilahun, Surafel Luleseged; Choon, Ong Hong

    2014-01-01

    In this paper, we propose a new technique to test the Satisfiability of propositional logic programming and quantified Boolean formula problem in radial basis function neural networks. For this purpose, we built radial basis function neural networks to represent the proportional logic which has exactly three variables in each clause. We used the Prey-predator algorithm to calculate the output weights of the neural networks, while the K-means clustering algorithm is used to determine the hidden parameters (the centers and the widths). Mean of the sum squared error function is used to measure the activity of the two algorithms. We applied the developed technique with the recurrent radial basis function neural networks to represent the quantified Boolean formulas. The new technique can be applied to solve many applications such as electronic circuits and NP-complete problems

  7. Satisfiability of logic programming based on radial basis function neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hamadneh, Nawaf; Sathasivam, Saratha; Tilahun, Surafel Luleseged; Choon, Ong Hong [School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Malaysia)

    2014-07-10

    In this paper, we propose a new technique to test the Satisfiability of propositional logic programming and quantified Boolean formula problem in radial basis function neural networks. For this purpose, we built radial basis function neural networks to represent the proportional logic which has exactly three variables in each clause. We used the Prey-predator algorithm to calculate the output weights of the neural networks, while the K-means clustering algorithm is used to determine the hidden parameters (the centers and the widths). Mean of the sum squared error function is used to measure the activity of the two algorithms. We applied the developed technique with the recurrent radial basis function neural networks to represent the quantified Boolean formulas. The new technique can be applied to solve many applications such as electronic circuits and NP-complete problems.

  8. Application of radial basis neural network for state estimation of ...

    African Journals Online (AJOL)

    An original application of radial basis function (RBF) neural network for power system state estimation is proposed in this paper. The property of massive parallelism of neural networks is employed for this. The application of RBF neural network for state estimation is investigated by testing its applicability on a IEEE 14 bus ...

  9. Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

    Directory of Open Access Journals (Sweden)

    Chernoded Andrey

    2017-01-01

    Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

  10. Identifying Emotions on the Basis of Neural Activation.

    Science.gov (United States)

    Kassam, Karim S; Markey, Amanda R; Cherkassky, Vladimir L; Loewenstein, George; Just, Marcel Adam

    2013-01-01

    We attempt to determine the discriminability and organization of neural activation corresponding to the experience of specific emotions. Method actors were asked to self-induce nine emotional states (anger, disgust, envy, fear, happiness, lust, pride, sadness, and shame) while in an fMRI scanner. Using a Gaussian Naïve Bayes pooled variance classifier, we demonstrate the ability to identify specific emotions experienced by an individual at well over chance accuracy on the basis of: 1) neural activation of the same individual in other trials, 2) neural activation of other individuals who experienced similar trials, and 3) neural activation of the same individual to a qualitatively different type of emotion induction. Factor analysis identified valence, arousal, sociality, and lust as dimensions underlying the activation patterns. These results suggest a structure for neural representations of emotion and inform theories of emotional processing.

  11. Entropy Learning in Neural Network

    Directory of Open Access Journals (Sweden)

    Geok See Ng

    2017-12-01

    Full Text Available In this paper, entropy term is used in the learning phase of a neural network.  As learning progresses, more hidden nodes get into saturation.  The early creation of such hidden nodes may impair generalisation.  Hence entropy approach is proposed to dampen the early creation of such nodes.  The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes.  At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network.

  12. Identifying Emotions on the Basis of Neural Activation.

    Directory of Open Access Journals (Sweden)

    Karim S Kassam

    Full Text Available We attempt to determine the discriminability and organization of neural activation corresponding to the experience of specific emotions. Method actors were asked to self-induce nine emotional states (anger, disgust, envy, fear, happiness, lust, pride, sadness, and shame while in an fMRI scanner. Using a Gaussian Naïve Bayes pooled variance classifier, we demonstrate the ability to identify specific emotions experienced by an individual at well over chance accuracy on the basis of: 1 neural activation of the same individual in other trials, 2 neural activation of other individuals who experienced similar trials, and 3 neural activation of the same individual to a qualitatively different type of emotion induction. Factor analysis identified valence, arousal, sociality, and lust as dimensions underlying the activation patterns. These results suggest a structure for neural representations of emotion and inform theories of emotional processing.

  13. Radial basis function neural network in fault detection of automotive ...

    African Journals Online (AJOL)

    Radial basis function neural network in fault detection of automotive engines. ... Five faults have been simulated on the MVEM, including three sensor faults, one component fault and one actuator fault. The three sensor faults ... Keywords: Automotive engine, independent RBFNN model, RBF neural network, fault detection

  14. Supervised Learning with Complex-valued Neural Networks

    CERN Document Server

    Suresh, Sundaram; Savitha, Ramasamy

    2013-01-01

    Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks.  Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computati...

  15. Asymmetric Variate Generation via a Parameterless Dual Neural Learning Algorithm

    Directory of Open Access Journals (Sweden)

    Simone Fiori

    2008-01-01

    Full Text Available In a previous work (S. Fiori, 2006, we proposed a random number generator based on a tunable non-linear neural system, whose learning rule is designed on the basis of a cardinal equation from statistics and whose implementation is based on look-up tables (LUTs. The aim of the present manuscript is to improve the above-mentioned random number generation method by changing the learning principle, while retaining the efficient LUT-based implementation. The new method proposed here proves easier to implement and relaxes some previous limitations.

  16. Using Deep Learning Neural Networks To Find Best Performing Audience Segments

    Directory of Open Access Journals (Sweden)

    Anup Badhe

    2015-08-01

    Full Text Available Finding the appropriate mobile audience for mobile advertising is always challenging since there are many data points that need to be considered and assimilated before a target segment can be created and used in ad serving by any ad server. Deep learning neural networks have been used in machine learning to use multiple processing layers to interpret large datasets with multiple dimensions to come up with a high-level characterization of the data. During a request for an advertisement and subsequently serving of the advertisement on the mobile device there are many trackers that are fired collecting a lot of data points. If the user likes the advertisement and clicks on it another set of trackers give additional information resulting from the click. This information is aggregated by the ad server and shown in its reporting console. The same information can form the basis of machine learning by feeding this information to a deep learning neural network to come up with audiences that can be targeted based on the product that is advertised.

  17. Differences between Neural Activity in Prefrontal Cortex and Striatum during Learning of Novel Abstract Categories

    OpenAIRE

    Antzoulatos, Evan G.; Miller, Earl K.

    2011-01-01

    Learning to classify diverse experiences into meaningful groups, like categories, is fundamental to normal cognition. To understand its neural basis, we simultaneously recorded from multiple electrodes in the lateral prefrontal cortex and dorsal striatum, two interconnected brain structures critical for learning. Each day, monkeys learned to associate novel, abstract dot-based categories with a right vs. left saccade. Early on, when they could acquire specific stimulus-response associations, ...

  18. Supervised learning of probability distributions by neural networks

    Science.gov (United States)

    Baum, Eric B.; Wilczek, Frank

    1988-01-01

    Supervised learning algorithms for feedforward neural networks are investigated analytically. The back-propagation algorithm described by Werbos (1974), Parker (1985), and Rumelhart et al. (1986) is generalized by redefining the values of the input and output neurons as probabilities. The synaptic weights are then varied to follow gradients in the logarithm of likelihood rather than in the error. This modification is shown to provide a more rigorous theoretical basis for the algorithm and to permit more accurate predictions. A typical application involving a medical-diagnosis expert system is discussed.

  19. Neural network representation and learning of mappings and their derivatives

    Science.gov (United States)

    White, Halbert; Hornik, Kurt; Stinchcombe, Maxwell; Gallant, A. Ronald

    1991-01-01

    Discussed here are recent theorems proving that artificial neural networks are capable of approximating an arbitrary mapping and its derivatives as accurately as desired. This fact forms the basis for further results establishing the learnability of the desired approximations, using results from non-parametric statistics. These results have potential applications in robotics, chaotic dynamics, control, and sensitivity analysis. An example involving learning the transfer function and its derivatives for a chaotic map is discussed.

  20. Neural basis of the undermining effect of monetary reward on intrinsic motivation.

    Science.gov (United States)

    Murayama, Kou; Matsumoto, Madoka; Izuma, Keise; Matsumoto, Kenji

    2010-12-07

    Contrary to the widespread belief that people are positively motivated by reward incentives, some studies have shown that performance-based extrinsic reward can actually undermine a person's intrinsic motivation to engage in a task. This "undermining effect" has timely practical implications, given the burgeoning of performance-based incentive systems in contemporary society. It also presents a theoretical challenge for economic and reinforcement learning theories, which tend to assume that monetary incentives monotonically increase motivation. Despite the practical and theoretical importance of this provocative phenomenon, however, little is known about its neural basis. Herein we induced the behavioral undermining effect using a newly developed task, and we tracked its neural correlates using functional MRI. Our results show that performance-based monetary reward indeed undermines intrinsic motivation, as assessed by the number of voluntary engagements in the task. We found that activity in the anterior striatum and the prefrontal areas decreased along with this behavioral undermining effect. These findings suggest that the corticobasal ganglia valuation system underlies the undermining effect through the integration of extrinsic reward value and intrinsic task value.

  1. Supervised neural network modeling: an empirical investigation into learning from imbalanced data with labeling errors.

    Science.gov (United States)

    Khoshgoftaar, Taghi M; Van Hulse, Jason; Napolitano, Amri

    2010-05-01

    Neural network algorithms such as multilayer perceptrons (MLPs) and radial basis function networks (RBFNets) have been used to construct learners which exhibit strong predictive performance. Two data related issues that can have a detrimental impact on supervised learning initiatives are class imbalance and labeling errors (or class noise). Imbalanced data can make it more difficult for the neural network learning algorithms to distinguish between examples of the various classes, and class noise can lead to the formulation of incorrect hypotheses. Both class imbalance and labeling errors are pervasive problems encountered in a wide variety of application domains. Many studies have been performed to investigate these problems in isolation, but few have focused on their combined effects. This study presents a comprehensive empirical investigation using neural network algorithms to learn from imbalanced data with labeling errors. In particular, the first component of our study investigates the impact of class noise and class imbalance on two common neural network learning algorithms, while the second component considers the ability of data sampling (which is commonly used to address the issue of class imbalance) to improve their performances. Our results, for which over two million models were trained and evaluated, show that conclusions drawn using the more commonly studied C4.5 classifier may not apply when using neural networks.

  2. Shaping the learning curve: epigenetic dynamics in neural plasticity

    Directory of Open Access Journals (Sweden)

    Zohar Ziv Bronfman

    2014-07-01

    Full Text Available A key characteristic of learning and neural plasticity is state-dependent acquisition dynamics reflected by the non-linear learning curve that links increase in learning with practice. Here we propose that the manner by which epigenetic states of individual cells change during learning contributes to the shape of the neural and behavioral learning curve. We base our suggestion on recent studies showing that epigenetic mechanisms such as DNA methylation, histone acetylation and RNA-mediated gene regulation are intimately involved in the establishment and maintenance of long-term neural plasticity, reflecting specific learning-histories and influencing future learning. Our model, which is the first to suggest a dynamic molecular account of the shape of the learning curve, leads to several testable predictions regarding the link between epigenetic dynamics at the promoter, gene-network and neural-network levels. This perspective opens up new avenues for therapeutic interventions in neurological pathologies.

  3. Neural Correlates of Morphology Acquisition through a Statistical Learning Paradigm.

    Science.gov (United States)

    Sandoval, Michelle; Patterson, Dianne; Dai, Huanping; Vance, Christopher J; Plante, Elena

    2017-01-01

    The neural basis of statistical learning as it occurs over time was explored with stimuli drawn from a natural language (Russian nouns). The input reflected the "rules" for marking categories of gendered nouns, without making participants explicitly aware of the nature of what they were to learn. Participants were scanned while listening to a series of gender-marked nouns during four sequential scans, and were tested for their learning immediately after each scan. Although participants were not told the nature of the learning task, they exhibited learning after their initial exposure to the stimuli. Independent component analysis of the brain data revealed five task-related sub-networks. Unlike prior statistical learning studies of word segmentation, this morphological learning task robustly activated the inferior frontal gyrus during the learning period. This region was represented in multiple independent components, suggesting it functions as a network hub for this type of learning. Moreover, the results suggest that subnetworks activated by statistical learning are driven by the nature of the input, rather than reflecting a general statistical learning system.

  4. The Neural Basis of Vocal Pitch Imitation in Humans.

    Science.gov (United States)

    Belyk, Michel; Pfordresher, Peter Q; Liotti, Mario; Brown, Steven

    2016-04-01

    Vocal imitation is a phenotype that is unique to humans among all primate species, and so an understanding of its neural basis is critical in explaining the emergence of both speech and song in human evolution. Two principal neural models of vocal imitation have emerged from a consideration of nonhuman animals. One hypothesis suggests that putative mirror neurons in the inferior frontal gyrus pars opercularis of Broca's area may be important for imitation. An alternative hypothesis derived from the study of songbirds suggests that the corticostriate motor pathway performs sensorimotor processes that are specific to vocal imitation. Using fMRI with a sparse event-related sampling design, we investigated the neural basis of vocal imitation in humans by comparing imitative vocal production of pitch sequences with both nonimitative vocal production and pitch discrimination. The strongest difference between these tasks was found in the putamen bilaterally, providing a striking parallel to the role of the analogous region in songbirds. Other areas preferentially activated during imitation included the orofacial motor cortex, Rolandic operculum, and SMA, which together outline the corticostriate motor loop. No differences were seen in the inferior frontal gyrus. The corticostriate system thus appears to be the central pathway for vocal imitation in humans, as predicted from an analogy with songbirds.

  5. Radial basis function neural network for power system load-flow

    International Nuclear Information System (INIS)

    Karami, A.; Mohammadi, M.S.

    2008-01-01

    This paper presents a method for solving the load-flow problem of the electric power systems using radial basis function (RBF) neural network with a fast hybrid training method. The main idea is that some operating conditions (values) are needed to solve the set of non-linear algebraic equations of load-flow by employing an iterative numerical technique. Therefore, we may view the outputs of a load-flow program as functions of the operating conditions. Indeed, we are faced with a function approximation problem and this can be done by an RBF neural network. The proposed approach has been successfully applied to the 10-machine and 39-bus New England test system. In addition, this method has been compared with that of a multi-layer perceptron (MLP) neural network model. The simulation results show that the RBF neural network is a simpler method to implement and requires less training time to converge than the MLP neural network. (author)

  6. Dynamic Learning from Adaptive Neural Control of Uncertain Robots with Guaranteed Full-State Tracking Precision

    Directory of Open Access Journals (Sweden)

    Min Wang

    2017-01-01

    Full Text Available A dynamic learning method is developed for an uncertain n-link robot with unknown system dynamics, achieving predefined performance attributes on the link angular position and velocity tracking errors. For a known nonsingular initial robotic condition, performance functions and unconstrained transformation errors are employed to prevent the violation of the full-state tracking error constraints. By combining two independent Lyapunov functions and radial basis function (RBF neural network (NN approximator, a novel and simple adaptive neural control scheme is proposed for the dynamics of the unconstrained transformation errors, which guarantees uniformly ultimate boundedness of all the signals in the closed-loop system. In the steady-state control process, RBF NNs are verified to satisfy the partial persistent excitation (PE condition. Subsequently, an appropriate state transformation is adopted to achieve the accurate convergence of neural weight estimates. The corresponding experienced knowledge on unknown robotic dynamics is stored in NNs with constant neural weight values. Using the stored knowledge, a static neural learning controller is developed to improve the full-state tracking performance. A comparative simulation study on a 2-link robot illustrates the effectiveness of the proposed scheme.

  7. The neural basis of academic achievement motivation.

    Science.gov (United States)

    Mizuno, Kei; Tanaka, Masaaki; Ishii, Akira; Tanabe, Hiroki C; Onoe, Hirotaka; Sadato, Norihiro; Watanabe, Yasuyoshi

    2008-08-01

    We have used functional magnetic resonance imaging to study the neural correlates of motivation, concentrating on the motivation to learn and gain monetary rewards. We compared the activation in the brain obtained during reported high states of motivation for learning, with the ones observed when the motivation was based on monetary reward. Our results show that motivation to learn correlates with bilateral activity in the putamen, and that the higher the reported motivation, as derived from a questionnaire that each subject filled prior to scanning, the greater the change in the BOLD signals within the putamen. Monetary motivation also activated the putamen bilaterally, though the intensity of activity was not related to the monetary reward. We conclude that the putamen is critical for motivation in different domains and the extent of activity of the putamen may be pivotal to the motivation that drives academic achievement and thus academic successes.

  8. The neural basis of kinesthetic and visual imagery in sports: an ALE meta - analysis.

    Science.gov (United States)

    Filgueiras, Alberto; Quintas Conde, Erick Francisco; Hall, Craig R

    2017-12-19

    Imagery is a widely spread technique in the sport sciences that entails the mental rehearsal of a given situation to improve an athlete's learning, performance and motivation. Two modalities of imagery are reported to tap into distinct brain structures, but sharing common components: kinesthetic and visual imagery. This study aimed to investigate the neural basis of those types of imagery with Activation Likelihood Estimation algorithm to perform a meta - analysis. A systematic search was used to retrieve only experimental studies with athletes or sportspersons. Altogether, nine studies were selected and an ALE meta - analysis was performed. Results indicated significant activation of the premotor, somatosensory cortex, supplementary motor areas, inferior and superior parietal lobule, caudate, cingulate and cerebellum in both imagery tasks. It was concluded that visual and kinesthetic imagery share similar neural networks which suggests that combined interventions are beneficial to athletes whereas separate use of those two modalities of imagery may seem less efficient from a neuropsychological approach.

  9. Machine Learning Topological Invariants with Neural Networks

    Science.gov (United States)

    Zhang, Pengfei; Shen, Huitao; Zhai, Hui

    2018-02-01

    In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

  10. Comparing the neural basis of monetary reward and cognitive feedback during information-integration category learning.

    Science.gov (United States)

    Daniel, Reka; Pollmann, Stefan

    2010-01-06

    The dopaminergic system is known to play a central role in reward-based learning (Schultz, 2006), yet it was also observed to be involved when only cognitive feedback is given (Aron et al., 2004). Within the domain of information-integration category learning, in which information from several stimulus dimensions has to be integrated predecisionally (Ashby and Maddox, 2005), the importance of contingent feedback is well established (Maddox et al., 2003). We examined the common neural correlates of reward anticipation and prediction error in this task. Sixteen subjects performed two parallel information-integration tasks within a single event-related functional magnetic resonance imaging session but received a monetary reward only for one of them. Similar functional areas including basal ganglia structures were activated in both task versions. In contrast, a single structure, the nucleus accumbens, showed higher activation during monetary reward anticipation compared with the anticipation of cognitive feedback in information-integration learning. Additionally, this activation was predicted by measures of intrinsic motivation in the cognitive feedback task and by measures of extrinsic motivation in the rewarded task. Our results indicate that, although all other structures implicated in category learning are not significantly affected by altering the type of reward, the nucleus accumbens responds to the positive incentive properties of an expected reward depending on the specific type of the reward.

  11. Continual Learning through Evolvable Neural Turing Machines

    DEFF Research Database (Denmark)

    Lüders, Benno; Schläger, Mikkel; Risi, Sebastian

    2016-01-01

    Continual learning, i.e. the ability to sequentially learn tasks without catastrophic forgetting of previously learned ones, is an important open challenge in machine learning. In this paper we take a step in this direction by showing that the recently proposed Evolving Neural Turing Machine (ENTM...

  12. Neural Behavior Chain Learning of Mobile Robot Actions

    Directory of Open Access Journals (Sweden)

    Lejla Banjanovic-Mehmedovic

    2012-01-01

    Full Text Available This paper presents a visual/motor behavior learning approach, based on neural networks. We propose Behavior Chain Model (BCM in order to create a way of behavior learning. Our behavior-based system evolution task is a mobile robot detecting a target and driving/acting towards it. First, the mapping relations between the image feature domain of the object and the robot action domain are derived. Second, a multilayer neural network for offline learning of the mapping relations is used. This learning structure through neural network training process represents a connection between the visual perceptions and motor sequence of actions in order to grip a target. Last, using behavior learning through a noticed action chain, we can predict mobile robot behavior for a variety of similar tasks in similar environment. Prediction results suggest that the methodology is adequate and could be recognized as an idea for designing different mobile robot behaviour assistance.

  13. Computing single step operators of logic programming in radial basis function neural networks

    Science.gov (United States)

    Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong

    2014-07-01

    Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (Tp:I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks.

  14. Computing single step operators of logic programming in radial basis function neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong [School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Malaysia)

    2014-07-10

    Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (T{sub p}:I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks.

  15. Computing single step operators of logic programming in radial basis function neural networks

    International Nuclear Information System (INIS)

    Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong

    2014-01-01

    Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (T p :I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks

  16. Design of cognitive engine for cognitive radio based on the rough sets and radial basis function neural network

    Science.gov (United States)

    Yang, Yanchao; Jiang, Hong; Liu, Congbin; Lan, Zhongli

    2013-03-01

    Cognitive radio (CR) is an intelligent wireless communication system which can dynamically adjust the parameters to improve system performance depending on the environmental change and quality of service. The core technology for CR is the design of cognitive engine, which introduces reasoning and learning methods in the field of artificial intelligence, to achieve the perception, adaptation and learning capability. Considering the dynamical wireless environment and demands, this paper proposes a design of cognitive engine based on the rough sets (RS) and radial basis function neural network (RBF_NN). The method uses experienced knowledge and environment information processed by RS module to train the RBF_NN, and then the learning model is used to reconfigure communication parameters to allocate resources rationally and improve system performance. After training learning model, the performance is evaluated according to two benchmark functions. The simulation results demonstrate the effectiveness of the model and the proposed cognitive engine can effectively achieve the goal of learning and reconfiguration in cognitive radio.

  17. Embedding responses in spontaneous neural activity shaped through sequential learning.

    Directory of Open Access Journals (Sweden)

    Tomoki Kurikawa

    Full Text Available Recent experimental measurements have demonstrated that spontaneous neural activity in the absence of explicit external stimuli has remarkable spatiotemporal structure. This spontaneous activity has also been shown to play a key role in the response to external stimuli. To better understand this role, we proposed a viewpoint, "memories-as-bifurcations," that differs from the traditional "memories-as-attractors" viewpoint. Memory recall from the memories-as-bifurcations viewpoint occurs when the spontaneous neural activity is changed to an appropriate output activity upon application of an input, known as a bifurcation in dynamical systems theory, wherein the input modifies the flow structure of the neural dynamics. Learning, then, is a process that helps create neural dynamical systems such that a target output pattern is generated as an attractor upon a given input. Based on this novel viewpoint, we introduce in this paper an associative memory model with a sequential learning process. Using a simple hebbian-type learning, the model is able to memorize a large number of input/output mappings. The neural dynamics shaped through the learning exhibit different bifurcations to make the requested targets stable upon an increase in the input, and the neural activity in the absence of input shows chaotic dynamics with occasional approaches to the memorized target patterns. These results suggest that these dynamics facilitate the bifurcations to each target attractor upon application of the corresponding input, which thus increases the capacity for learning. This theoretical finding about the behavior of the spontaneous neural activity is consistent with recent experimental observations in which the neural activity without stimuli wanders among patterns evoked by previously applied signals. In addition, the neural networks shaped by learning properly reflect the correlations of input and target-output patterns in a similar manner to those designed in

  18. Learning of N-layers neural network

    Directory of Open Access Journals (Sweden)

    Vladimír Konečný

    2005-01-01

    Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.

  19. Uncovering the neural mechanisms underlying learning from tests.

    Directory of Open Access Journals (Sweden)

    Xiaonan L Liu

    Full Text Available People learn better when re-study opportunities are replaced with tests. While researchers have begun to speculate on why testing is superior to study, few studies have directly examined the neural underpinnings of this effect. In this fMRI study, participants engaged in a study phase to learn arbitrary word pairs, followed by a cued recall test (recall second half of pair when cued with first word of pair, re-study of each pair, and finally another cycle of cued recall tests. Brain activation patterns during the first test (recall of the studied pairs predicts performance on the second test. Importantly, while subsequent memory analyses of encoding trials also predict later accuracy, the brain regions involved in predicting later memory success are more extensive for activity during retrieval (testing than during encoding (study. Those additional regions that predict subsequent memory based on their activation at test but not at encoding may be key to understanding the basis of the testing effect.

  20. Neural basis of scientific innovation induced by heuristic prototype.

    Directory of Open Access Journals (Sweden)

    Junlong Luo

    Full Text Available A number of major inventions in history have been based on bionic imitation. Heuristics, by applying biological systems to the creation of artificial devices and machines, might be one of the most critical processes in scientific innovation. In particular, prototype heuristics propositions that innovation may engage automatic activation of a prototype such as a biological system to form novel associations between a prototype's function and problem-solving. We speculated that the cortical dissociation between the automatic activation and forming novel associations in innovation is critical point to heuristic creativity. In the present study, novel and old scientific innovations (NSI and OSI were selected as experimental materials in using learning-testing paradigm to explore the neural basis of scientific innovation induced by heuristic prototype. College students were required to resolve NSI problems (to which they did not know the answers and OSI problems (to which they knew the answers. From two fMRI experiments, our results showed that the subjects could resolve NSI when provided with heuristic prototypes. In Experiment 1, it was found that the lingual gyrus (LG; BA18 might be related to prototype heuristics in college students resolving NSI after learning a relative prototype. In Experiment 2, the LG (BA18 and precuneus (BA31 were significantly activated for NSI compared to OSI when college students learned all prototypes one day before the test. In addition, the mean beta-values of these brain regions of NSI were all correlated with the behavior accuracy of NSI. As our hypothesis indicated, the findings suggested that the LG might be involved in forming novel associations using heuristic information, while the precuneus might be involved in the automatic activation of heuristic prototype during scientific innovation.

  1. Neural basis of scientific innovation induced by heuristic prototype.

    Science.gov (United States)

    Luo, Junlong; Li, Wenfu; Qiu, Jiang; Wei, Dongtao; Liu, Yijun; Zhang, Qinlin

    2013-01-01

    A number of major inventions in history have been based on bionic imitation. Heuristics, by applying biological systems to the creation of artificial devices and machines, might be one of the most critical processes in scientific innovation. In particular, prototype heuristics propositions that innovation may engage automatic activation of a prototype such as a biological system to form novel associations between a prototype's function and problem-solving. We speculated that the cortical dissociation between the automatic activation and forming novel associations in innovation is critical point to heuristic creativity. In the present study, novel and old scientific innovations (NSI and OSI) were selected as experimental materials in using learning-testing paradigm to explore the neural basis of scientific innovation induced by heuristic prototype. College students were required to resolve NSI problems (to which they did not know the answers) and OSI problems (to which they knew the answers). From two fMRI experiments, our results showed that the subjects could resolve NSI when provided with heuristic prototypes. In Experiment 1, it was found that the lingual gyrus (LG; BA18) might be related to prototype heuristics in college students resolving NSI after learning a relative prototype. In Experiment 2, the LG (BA18) and precuneus (BA31) were significantly activated for NSI compared to OSI when college students learned all prototypes one day before the test. In addition, the mean beta-values of these brain regions of NSI were all correlated with the behavior accuracy of NSI. As our hypothesis indicated, the findings suggested that the LG might be involved in forming novel associations using heuristic information, while the precuneus might be involved in the automatic activation of heuristic prototype during scientific innovation.

  2. Upset Prediction in Friction Welding Using Radial Basis Function Neural Network

    Directory of Open Access Journals (Sweden)

    Wei Liu

    2013-01-01

    Full Text Available This paper addresses the upset prediction problem of friction welded joints. Based on finite element simulations of inertia friction welding (IFW, a radial basis function (RBF neural network was developed initially to predict the final upset for a number of welding parameters. The predicted joint upset by the RBF neural network was compared to validated finite element simulations, producing an error of less than 8.16% which is reasonable. Furthermore, the effects of initial rotational speed and axial pressure on the upset were investigated in relation to energy conversion with the RBF neural network. The developed RBF neural network was also applied to linear friction welding (LFW and continuous drive friction welding (CDFW. The correlation coefficients of RBF prediction for LFW and CDFW were 0.963 and 0.998, respectively, which further suggest that an RBF neural network is an effective method for upset prediction of friction welded joints.

  3. Windowed active sampling for reliable neural learning

    NARCIS (Netherlands)

    Barakova, E.I; Spaanenburg, L

    The composition of the example set has a major impact on the quality of neural learning. The popular approach is focused on extensive pre-processing to bridge the representation gap between process measurement and neural presentation. In contrast, windowed active sampling attempts to solve these

  4. SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

    Science.gov (United States)

    Zenke, Friedemann; Ganguli, Surya

    2018-04-13

    A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

  5. Learning-parameter adjustment in neural networks

    Science.gov (United States)

    Heskes, Tom M.; Kappen, Bert

    1992-06-01

    We present a learning-parameter adjustment algorithm, valid for a large class of learning rules in neural-network literature. The algorithm follows directly from a consideration of the statistics of the weights in the network. The characteristic behavior of the algorithm is calculated, both in a fixed and a changing environment. A simple example, Widrow-Hoff learning for statistical classification, serves as an illustration.

  6. Online neural monitoring of statistical learning.

    Science.gov (United States)

    Batterink, Laura J; Paller, Ken A

    2017-05-01

    The extraction of patterns in the environment plays a critical role in many types of human learning, from motor skills to language acquisition. This process is known as statistical learning. Here we propose that statistical learning has two dissociable components: (1) perceptual binding of individual stimulus units into integrated composites and (2) storing those integrated representations for later use. Statistical learning is typically assessed using post-learning tasks, such that the two components are conflated. Our goal was to characterize the online perceptual component of statistical learning. Participants were exposed to a structured stream of repeating trisyllabic nonsense words and a random syllable stream. Online learning was indexed by an EEG-based measure that quantified neural entrainment at the frequency of the repeating words relative to that of individual syllables. Statistical learning was subsequently assessed using conventional measures in an explicit rating task and a reaction-time task. In the structured stream, neural entrainment to trisyllabic words was higher than in the random stream, increased as a function of exposure to track the progression of learning, and predicted performance on the reaction time (RT) task. These results demonstrate that monitoring this critical component of learning via rhythmic EEG entrainment reveals a gradual acquisition of knowledge whereby novel stimulus sequences are transformed into familiar composites. This online perceptual transformation is a critical component of learning. Copyright © 2017 Elsevier Ltd. All rights reserved.

  7. Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding.

    Science.gov (United States)

    Gardner, Brian; Grüning, André

    2016-01-01

    Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule's error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism.

  8. The neural basis of event simulation: an FMRI study.

    Directory of Open Access Journals (Sweden)

    Yukihito Yomogida

    Full Text Available Event simulation (ES is the situational inference process in which perceived event features such as objects, agents, and actions are associated in the brain to represent the whole situation. ES provides a common basis for various cognitive processes, such as perceptual prediction, situational understanding/prediction, and social cognition (such as mentalizing/trait inference. Here, functional magnetic resonance imaging was used to elucidate the neural substrates underlying important subdivisions within ES. First, the study investigated whether ES depends on different neural substrates when it is conducted explicitly and implicitly. Second, the existence of neural substrates specific to the future-prediction component of ES was assessed. Subjects were shown contextually related object pictures implying a situation and performed several picture-word-matching tasks. By varying task goals, subjects were made to infer the implied situation implicitly/explicitly or predict the future consequence of that situation. The results indicate that, whereas implicit ES activated the lateral prefrontal cortex and medial/lateral parietal cortex, explicit ES activated the medial prefrontal cortex, posterior cingulate cortex, and medial/lateral temporal cortex. Additionally, the left temporoparietal junction plays an important role in the future-prediction component of ES. These findings enrich our understanding of the neural substrates of the implicit/explicit/predictive aspects of ES-related cognitive processes.

  9. Sex differences in the neural basis of emotional memories.

    Science.gov (United States)

    Canli, Turhan; Desmond, John E; Zhao, Zuo; Gabrieli, John D E

    2002-08-06

    Psychological studies have found better memory in women than men for emotional events, but the neural basis for this difference is unknown. We used event-related functional MRI to assess whether sex differences in memory for emotional stimuli is associated with activation of different neural systems in men and women. Brain activation in 12 men and 12 women was recorded while they rated their experience of emotional arousal in response to neutral and emotionally negative pictures. In a recognition memory test 3 weeks after scanning, highly emotional pictures were remembered best, and remembered better by women than by men. Men and women activated different neural circuits to encode stimuli effectively into memory even when the analysis was restricted to pictures rated equally arousing by both groups. Men activated significantly more structures than women in a network that included the right amygdala, whereas women activated significantly fewer structures in a network that included the left amygdala. Women had significantly more brain regions where activation correlated with both ongoing evaluation of emotional experience and with subsequent memory for the most emotionally arousing pictures. Greater overlap in brain regions sensitive to current emotion and contributing to subsequent memory may be a neural mechanism for emotions to enhance memory more powerfully in women than in men.

  10. The neural basis of reversal learning: An updated perspective

    Science.gov (United States)

    Izquierdo, Alicia; Brigman, Jonathan L.; Radke, Anna K.; Rudebeck, Peter H.; Holmes, Andrew

    2016-01-01

    Reversal learning paradigms are among the most widely used tests of cognitive flexibility and have been used as assays, across species, for altered cognitive processes in a host of neuropsychiatric conditions. Based on recent studies in humans, non-human primates, and rodents, the notion that reversal learning tasks primarily measure response inhibition, has been revised. In this review, we describe how cognitive flexibility is measured by reversal learning and discuss new definitions of the construct validity of the task that are serving as an heuristic to guide future research in this field. We also provide an update on the available evidence implicating certain cortical and subcortical brain regions in the mediation of reversal learning, and an overview of the principle neurotransmitter systems involved. PMID:26979052

  11. On supertaskers and the neural basis of efficient multitasking.

    Science.gov (United States)

    Medeiros-Ward, Nathan; Watson, Jason M; Strayer, David L

    2015-06-01

    The present study used brain imaging to determine the neural basis of individual differences in multitasking, the ability to successfully perform at least two attention-demanding tasks at once. Multitasking is mentally taxing and, therefore, should recruit the prefrontal cortex to maintain task goals when coordinating attentional control and managing the cognitive load. To investigate this possibility, we used functional neuroimaging to assess neural activity in both extraordinary multitaskers (Supertaskers) and control subjects who were matched on working memory capacity. Participants performed a challenging dual N-back task in which auditory and visual stimuli were presented simultaneously, requiring independent and continuous maintenance, updating, and verification of the contents of verbal and spatial working memory. With the task requirements and considerable cognitive load that accompanied increasing N-back, relative to the controls, the multitasking of Supertaskers was characterized by more efficient recruitment of anterior cingulate and posterior frontopolar prefrontal cortices. Results are interpreted using neuropsychological and evolutionary perspectives on individual differences in multitasking ability and the neural correlates of attentional control.

  12. The Neural Basis of and a Common Neural Circuitry in Different Types of Pro-social Behavior

    Directory of Open Access Journals (Sweden)

    Jun Luo

    2018-06-01

    Full Text Available Pro-social behaviors are voluntary behaviors that benefit other people or society as a whole, such as charitable donations, cooperation, trust, altruistic punishment, and fairness. These behaviors have been widely described through non self-interest decision-making in behavioral experimental studies and are thought to be increased by social preference motives. Importantly, recent studies using a combination of neuroimaging and brain stimulation, designed to reveal the neural mechanisms of pro-social behaviors, have found that a wide range of brain areas, specifically the prefrontal cortex, anterior insula, anterior cingulate cortex, and amygdala, are correlated or causally related with pro-social behaviors. In this review, we summarize the research on the neural basis of various kinds of pro-social behaviors and describe a common shared neural circuitry of these pro-social behaviors. We introduce several general ways in which experimental economics and neuroscience can be combined to develop important contributions to understanding social decision-making and pro-social behaviors. Future research should attempt to explore the neural circuitry between the frontal lobes and deeper brain areas.

  13. Development switch in neural circuitry underlying odor-malaise learning.

    Science.gov (United States)

    Shionoya, Kiseko; Moriceau, Stephanie; Lunday, Lauren; Miner, Cathrine; Roth, Tania L; Sullivan, Regina M

    2006-01-01

    Fetal and infant rats can learn to avoid odors paired with illness before development of brain areas supporting this learning in adults, suggesting an alternate learning circuit. Here we begin to document the transition from the infant to adult neural circuit underlying odor-malaise avoidance learning using LiCl (0.3 M; 1% of body weight, ip) and a 30-min peppermint-odor exposure. Conditioning groups included: Paired odor-LiCl, Paired odor-LiCl-Nursing, LiCl, and odor-saline. Results showed that Paired LiCl-odor conditioning induced a learned odor aversion in postnatal day (PN) 7, 12, and 23 pups. Odor-LiCl Paired Nursing induced a learned odor preference in PN7 and PN12 pups but blocked learning in PN23 pups. 14C 2-deoxyglucose (2-DG) autoradiography indicated enhanced olfactory bulb activity in PN7 and PN12 pups with odor preference and avoidance learning. The odor aversion in weanling aged (PN23) pups resulted in enhanced amygdala activity in Paired odor-LiCl pups, but not if they were nursing. Thus, the neural circuit supporting malaise-induced aversions changes over development, indicating that similar infant and adult-learned behaviors may have distinct neural circuits.

  14. Parameter diagnostics of phases and phase transition learning by neural networks

    Science.gov (United States)

    Suchsland, Philippe; Wessel, Stefan

    2018-05-01

    We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

  15. Neural modularity helps organisms evolve to learn new skills without forgetting old skills.

    Science.gov (United States)

    Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

    2015-04-01

    A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to

  16. Neural modularity helps organisms evolve to learn new skills without forgetting old skills.

    Directory of Open Access Journals (Sweden)

    Kai Olav Ellefsen

    2015-04-01

    Full Text Available A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand. To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1 that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2 that one benefit of the modularity ubiquitous in the brains of natural animals

  17. Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills

    Science.gov (United States)

    Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

    2015-01-01

    A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to

  18. Vicarious neural processing of outcomes during observational learning.

    Directory of Open Access Journals (Sweden)

    Elisabetta Monfardini

    Full Text Available Learning what behaviour is appropriate in a specific context by observing the actions of others and their outcomes is a key constituent of human cognition, because it saves time and energy and reduces exposure to potentially dangerous situations. Observational learning of associative rules relies on the ability to map the actions of others onto our own, process outcomes, and combine these sources of information. Here, we combined newly developed experimental tasks and functional magnetic resonance imaging (fMRI to investigate the neural mechanisms that govern such observational learning. Results show that the neural systems involved in individual trial-and-error learning and in action observation and execution both participate in observational learning. In addition, we identified brain areas that specifically activate for others' incorrect outcomes during learning in the posterior medial frontal cortex (pMFC, the anterior insula and the posterior superior temporal sulcus (pSTS.

  19. Vicarious neural processing of outcomes during observational learning.

    Science.gov (United States)

    Monfardini, Elisabetta; Gazzola, Valeria; Boussaoud, Driss; Brovelli, Andrea; Keysers, Christian; Wicker, Bruno

    2013-01-01

    Learning what behaviour is appropriate in a specific context by observing the actions of others and their outcomes is a key constituent of human cognition, because it saves time and energy and reduces exposure to potentially dangerous situations. Observational learning of associative rules relies on the ability to map the actions of others onto our own, process outcomes, and combine these sources of information. Here, we combined newly developed experimental tasks and functional magnetic resonance imaging (fMRI) to investigate the neural mechanisms that govern such observational learning. Results show that the neural systems involved in individual trial-and-error learning and in action observation and execution both participate in observational learning. In addition, we identified brain areas that specifically activate for others' incorrect outcomes during learning in the posterior medial frontal cortex (pMFC), the anterior insula and the posterior superior temporal sulcus (pSTS).

  20. Learning and adaptation: neural and behavioural mechanisms behind behaviour change

    Science.gov (United States)

    Lowe, Robert; Sandamirskaya, Yulia

    2018-01-01

    This special issue presents perspectives on learning and adaptation as they apply to a number of cognitive phenomena including pupil dilation in humans and attention in robots, natural language acquisition and production in embodied agents (robots), human-robot game play and social interaction, neural-dynamic modelling of active perception and neural-dynamic modelling of infant development in the Piagetian A-not-B task. The aim of the special issue, through its contributions, is to highlight some of the critical neural-dynamic and behavioural aspects of learning as it grounds adaptive responses in robotic- and neural-dynamic systems.

  1. Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control.

    Science.gov (United States)

    Pan, Yongping; Yu, Haoyong

    2017-06-01

    This brief presents a biomimetic hybrid feedback feedforward neural-network learning control (NNLC) strategy inspired by the human motor learning control mechanism for a class of uncertain nonlinear systems. The control structure includes a proportional-derivative controller acting as a feedback servo machine and a radial-basis-function (RBF) NN acting as a feedforward predictive machine. Under the sufficient constraints on control parameters, the closed-loop system achieves semiglobal practical exponential stability, such that an accurate NN approximation is guaranteed in a local region along recurrent reference trajectories. Compared with the existing NNLC methods, the novelties of the proposed method include: 1) the implementation of an adaptive NN control to guarantee plant states being recurrent is not needed, since recurrent reference signals rather than plant states are utilized as NN inputs, which greatly simplifies the analysis and synthesis of the NNLC and 2) the domain of NN approximation can be determined a priori by the given reference signals, which leads to an easy construction of the RBF-NNs. Simulation results have verified the effectiveness of this approach.

  2. Comparison between extreme learning machine and wavelet neural networks in data classification

    Science.gov (United States)

    Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

    2017-03-01

    Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.

  3. Boltzmann learning of parameters in cellular neural networks

    DEFF Research Database (Denmark)

    Hansen, Lars Kai

    1992-01-01

    The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified...

  4. Reconfigurable Flight Control Design using a Robust Servo LQR and Radial Basis Function Neural Networks

    Science.gov (United States)

    Burken, John J.

    2005-01-01

    This viewgraph presentation reviews the use of a Robust Servo Linear Quadratic Regulator (LQR) and a Radial Basis Function (RBF) Neural Network in reconfigurable flight control designs in adaptation to a aircraft part failure. The method uses a robust LQR servomechanism design with model Reference adaptive control, and RBF neural networks. During the failure the LQR servomechanism behaved well, and using the neural networks improved the tracking.

  5. Neural mechanisms of reinforcement learning in unmedicated patients with major depressive disorder.

    Science.gov (United States)

    Rothkirch, Marcus; Tonn, Jonas; Köhler, Stephan; Sterzer, Philipp

    2017-04-01

    According to current concepts, major depressive disorder is strongly related to dysfunctional neural processing of motivational information, entailing impairments in reinforcement learning. While computational modelling can reveal the precise nature of neural learning signals, it has not been used to study learning-related neural dysfunctions in unmedicated patients with major depressive disorder so far. We thus aimed at comparing the neural coding of reward and punishment prediction errors, representing indicators of neural learning-related processes, between unmedicated patients with major depressive disorder and healthy participants. To this end, a group of unmedicated patients with major depressive disorder (n = 28) and a group of age- and sex-matched healthy control participants (n = 30) completed an instrumental learning task involving monetary gains and losses during functional magnetic resonance imaging. The two groups did not differ in their learning performance. Patients and control participants showed the same level of prediction error-related activity in the ventral striatum and the anterior insula. In contrast, neural coding of reward prediction errors in the medial orbitofrontal cortex was reduced in patients. Moreover, neural reward prediction error signals in the medial orbitofrontal cortex and ventral striatum showed negative correlations with anhedonia severity. Using a standard instrumental learning paradigm we found no evidence for an overall impairment of reinforcement learning in medication-free patients with major depressive disorder. Importantly, however, the attenuated neural coding of reward in the medial orbitofrontal cortex and the relation between anhedonia and reduced reward prediction error-signalling in the medial orbitofrontal cortex and ventral striatum likely reflect an impairment in experiencing pleasure from rewarding events as a key mechanism of anhedonia in major depressive disorder. © The Author (2017). Published by Oxford

  6. The Neural Basis of Changing Social Norms through Persuasion

    OpenAIRE

    Yomogida, Yukihito; Matsumoto, Madoka; Aoki, Ryuta; Sugiura, Ayaka; Phillips, Adam N.; Matsumoto, Kenji

    2017-01-01

    Social norms regulate behavior, and changes in norms have a great impact on society. In most modern societies, norms change through interpersonal communication and persuasive messages found in media. Here, we examined the neural basis of persuasion-induced changes in attitude toward and away from norms using fMRI. We measured brain activity while human participants were exposed to persuasive messages directed toward specific norms. Persuasion directed toward social norms specifically activate...

  7. Fastest learning in small-world neural networks

    International Nuclear Information System (INIS)

    Simard, D.; Nadeau, L.; Kroeger, H.

    2005-01-01

    We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition

  8. A Constrained Multi-Objective Learning Algorithm for Feed-Forward Neural Network Classifiers

    Directory of Open Access Journals (Sweden)

    M. Njah

    2017-06-01

    Full Text Available This paper proposes a new approach to address the optimal design of a Feed-forward Neural Network (FNN based classifier. The originality of the proposed methodology, called CMOA, lie in the use of a new constraint handling technique based on a self-adaptive penalty procedure in order to direct the entire search effort towards finding only Pareto optimal solutions that are acceptable. Neurons and connections of the FNN Classifier are dynamically built during the learning process. The approach includes differential evolution to create new individuals and then keeps only the non-dominated ones as the basis for the next generation. The designed FNN Classifier is applied to six binary classification benchmark problems, obtained from the UCI repository, and results indicated the advantages of the proposed approach over other existing multi-objective evolutionary neural networks classifiers reported recently in the literature.

  9. Bounds on Rates of Variable-Basis and Neural-Network Approximation

    Czech Academy of Sciences Publication Activity Database

    Kůrková, Věra; Sanguineti, M.

    2001-01-01

    Roč. 47, č. 6 (2001), s. 2659-2665 ISSN 0018-9448 R&D Projects: GA ČR GA201/00/1482 Institutional research plan: AV0Z1030915 Keywords : approximation by variable-basis functions * bounds on rates of approximation * complexity of neural networks * high-dimensional optimal decision problems Subject RIV: BA - General Mathematics Impact factor: 2.077, year: 2001

  10. Do neural nets learn statistical laws behind natural language?

    Directory of Open Access Journals (Sweden)

    Shuntaro Takahashi

    Full Text Available The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM effectively reproduces Zipf's law and Heaps' law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf's law and Heaps' law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks.

  11. Learning in neural networks based on a generalized fluctuation theorem

    Science.gov (United States)

    Hayakawa, Takashi; Aoyagi, Toshio

    2015-11-01

    Information maximization has been investigated as a possible mechanism of learning governing the self-organization that occurs within the neural systems of animals. Within the general context of models of neural systems bidirectionally interacting with environments, however, the role of information maximization remains to be elucidated. For bidirectionally interacting physical systems, universal laws describing the fluctuation they exhibit and the information they possess have recently been discovered. These laws are termed fluctuation theorems. In the present study, we formulate a theory of learning in neural networks bidirectionally interacting with environments based on the principle of information maximization. Our formulation begins with the introduction of a generalized fluctuation theorem, employing an interpretation appropriate for the present application, which differs from the original thermodynamic interpretation. We analytically and numerically demonstrate that the learning mechanism presented in our theory allows neural networks to efficiently explore their environments and optimally encode information about them.

  12. Evolving Neural Turing Machines for Reward-based Learning

    DEFF Research Database (Denmark)

    Greve, Rasmus Boll; Jacobsen, Emil Juul; Risi, Sebastian

    2016-01-01

    An unsolved problem in neuroevolution (NE) is to evolve artificial neural networks (ANN) that can store and use information to change their behavior online. While plastic neural networks have shown promise in this context, they have difficulties retaining information over longer periods of time...... version of the double T-Maze, a complex reinforcement-like learning problem. In the T-Maze learning task the agent uses the memory bank to display adaptive behavior that normally requires a plastic ANN, thereby suggesting a complementary and effective mechanism for adaptive behavior in NE....

  13. Neural basis of preference for human social hierarchy versus egalitarianism.

    Science.gov (United States)

    Chiao, Joan Y; Mathur, Vani A; Harada, Tokiko; Lipke, Trixie

    2009-06-01

    A fundamental way that individuals differ is in the degree to which they prefer social dominance hierarchy over egalitarianism as a guiding principle of societal structure, a phenomenon known as social dominance orientation. Here we show that preference for hierarchical rather than egalitarian social relations varies as a function of neural responses within left anterior insula and anterior cingulate cortices. Our findings provide novel evidence that preference for social dominance hierarchy is associated with neural functioning within brain regions that are associated with the ability to share and feel concern for the pain of others; this suggests a neurobiological basis for social and political attitudes. Implications of these findings for research on the social neuroscience of fairness, justice, and intergroup relations are discussed.

  14. Statistical learning problem of artificial neural network to control roofing process

    Directory of Open Access Journals (Sweden)

    Lapidus Azariy

    2017-01-01

    Full Text Available Now software developed on the basis of artificial neural networks (ANN has been actively implemented in construction companies to support decision-making in organization and management of construction processes. ANN learning is the main stage of its development. A key question for supervised learning is how many number of training examples we need to approximate the true relationship between network inputs and output with the desired accuracy. Also designing of ANN architecture is related to learning problem known as “curse of dimensionality”. This problem is important for the study of construction process management because of the difficulty to get training data from construction sites. In previous studies the authors have designed a 4-layer feedforward ANN with a unit model of 12-5-4-1 to approximate estimation and prediction of roofing process. This paper presented the statistical learning side of created ANN with simple-error-minimization algorithm. The sample size to efficient training and the confidence interval of network outputs defined. In conclusion the authors predicted successful ANN learning in a large construction business company within a short space of time.

  15. Cultural influences on neural basis of intergroup empathy.

    Science.gov (United States)

    Cheon, Bobby K; Im, Dong-Mi; Harada, Tokiko; Kim, Ji-Sook; Mathur, Vani A; Scimeca, Jason M; Parrish, Todd B; Park, Hyun Wook; Chiao, Joan Y

    2011-07-15

    Cultures vary in the extent to which people prefer social hierarchical or egalitarian relations between individuals and groups. Here we examined the effect of cultural variation in preference for social hierarchy on the neural basis of intergroup empathy. Using cross-cultural neuroimaging, we measured neural responses while Korean and American participants observed scenes of racial ingroup and outgroup members in emotional pain. Compared to Caucasian-American participants, Korean participants reported experiencing greater empathy and elicited stronger activity in the left temporo-parietal junction (L-TPJ), a region previously associated with mental state inference, for ingroup compared to outgroup members. Furthermore, preferential reactivity within this region to the pain of ingroup relative to outgroup members was associated with greater preference for social hierarchy and ingroup biases in empathy. Together, these results suggest that cultural variation in preference for social hierarchy leads to cultural variation in ingroup-preferences in empathy, due to increased engagement of brain regions associated with representing and inferring the mental states of others. Copyright © 2011 Elsevier Inc. All rights reserved.

  16. Incidental regulation of attraction: The neural basis of the derogation of attractive alternatives in romantic relationships

    NARCIS (Netherlands)

    Meyer, M.L.; Berkman, E.T.; Karremans, J.C.T.M.; Lieberman, M.D.

    2011-01-01

    Although a great deal of research addresses the neural basis of deliberate and intentional emotion-regulation strategies, less attention has been paid to the neural mechanisms involved in implicit forms of emotion regulation. Behavioural research suggests that romantically involved participants

  17. Finite time convergent learning law for continuous neural networks.

    Science.gov (United States)

    Chairez, Isaac

    2014-02-01

    This paper addresses the design of a discontinuous finite time convergent learning law for neural networks with continuous dynamics. The neural network was used here to obtain a non-parametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties was the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on discontinuous algorithms was used to adjust the weights of the neural network. The adaptive algorithm was derived by means of a non-standard Lyapunov function that is lower semi-continuous and differentiable in almost the whole space. A compensator term was included in the identifier to reject some specific perturbations using a nonlinear robust algorithm. Two numerical examples demonstrated the improvements achieved by the learning algorithm introduced in this paper compared to classical schemes with continuous learning methods. The first one dealt with a benchmark problem used in the paper to explain how the discontinuous learning law works. The second one used the methane production model to show the benefits in engineering applications of the learning law proposed in this paper. Copyright © 2013 Elsevier Ltd. All rights reserved.

  18. The neural basis of the imitation drive.

    Science.gov (United States)

    Hanawa, Sugiko; Sugiura, Motoaki; Nozawa, Takayuki; Kotozaki, Yuka; Yomogida, Yukihito; Ihara, Mizuki; Akimoto, Yoritaka; Thyreau, Benjamin; Izumi, Shinichi; Kawashima, Ryuta

    2016-01-01

    Spontaneous imitation is assumed to underlie the acquisition of important skills by infants, including language and social interaction. In this study, functional magnetic resonance imaging (fMRI) was used to examine the neural basis of 'spontaneously' driven imitation, which has not yet been fully investigated. Healthy participants were presented with movie clips of meaningless bimanual actions and instructed to observe and imitate them during an fMRI scan. The participants were subsequently shown the movie clips again and asked to evaluate the strength of their 'urge to imitate' (Urge) for each action. We searched for cortical areas where the degree of activation positively correlated with Urge scores; significant positive correlations were observed in the right supplementary motor area (SMA) and bilateral midcingulate cortex (MCC) under the imitation condition. These areas were not explained by explicit reasons for imitation or the kinematic characteristics of the actions. Previous studies performed in monkeys and humans have implicated the SMA and MCC/caudal cingulate zone in voluntary actions. This study also confirmed the functional connectivity between Urge and imitation performance using a psychophysiological interaction analysis. Thus, our findings reveal the critical neural components that underlie spontaneous imitation and provide possible reasons why infants imitate spontaneously. © The Author (2015). Published by Oxford University Press.

  19. Identification and integration of sensory modalities: Neural basis and relation to consciousness

    NARCIS (Netherlands)

    Pennartz, C.M.A.

    2009-01-01

    A key question in studying consciousness is how neural operations in the brain can identify streams of sensory input as belonging to distinct modalities, which contributes to the representation of qualitatively different experiences. The basis for identification of modalities is proposed to be

  20. Neural Monkey: An Open-source Tool for Sequence Learning

    Directory of Open Access Journals (Sweden)

    Helcl Jindřich

    2017-04-01

    Full Text Available In this paper, we announce the development of Neural Monkey – an open-source neural machine translation (NMT and general sequence-to-sequence learning system built over the TensorFlow machine learning library. The system provides a high-level API tailored for fast prototyping of complex architectures with multiple sequence encoders and decoders. Models’ overall architecture is specified in easy-to-read configuration files. The long-term goal of the Neural Monkey project is to create and maintain a growing collection of implementations of recently proposed components or methods, and therefore it is designed to be easily extensible. Trained models can be deployed either for batch data processing or as a web service. In the presented paper, we describe the design of the system and introduce the reader to running experiments using Neural Monkey.

  1. Neural basis of limb ownership in individuals with body integrity identity disorder

    NARCIS (Netherlands)

    van Dijk, Milenna T.; van Wingen, Guido A.; van Lammeren, Anouk; Blom, Rianne M.; de Kwaasteniet, Bart P.; Scholte, H. Steven; Denys, Damiaan

    2013-01-01

    Our body feels like it is ours. However, individuals with body integrity identity disorder (BIID) lack this feeling of ownership for distinct limbs and desire amputation of perfectly healthy body parts. This extremely rare condition provides us with an opportunity to study the neural basis

  2. Spaced Learning Enhances Subsequent Recognition Memory by Reducing Neural Repetition Suppression

    Science.gov (United States)

    Xue, Gui; Mei, Leilei; Chen, Chuansheng; Lu, Zhong-Lin; Poldrack, Russell; Dong, Qi

    2011-01-01

    Spaced learning usually leads to better recognition memory as compared with massed learning, yet the underlying neural mechanisms remain elusive. One open question is whether the spacing effect is achieved by reducing neural repetition suppression. In this fMRI study, participants were scanned while intentionally memorizing 120 novel faces, half…

  3. Neural controller for adaptive movements with unforeseen payloads.

    Science.gov (United States)

    Kuperstein, M; Wang, J

    1990-01-01

    A theory and computer simulation of a neural controller that learns to move and position a link carrying an unforeseen payload accurately are presented. The neural controller learns adaptive dynamic control from its own experience. It does not use information about link mass, link length, or direction of gravity, and it uses only indirect uncalibrated information about payload and actuator limits. Its average positioning accuracy across a large range of payloads after learning is 3% of the positioning range. This neural controller can be used as a basis for coordinating any number of sensory inputs with limbs of any number of joints. The feedforward nature of control allows parallel implementation in real time across multiple joints.

  4. Random neural Q-learning for obstacle avoidance of a mobile robot in unknown environments

    Directory of Open Access Journals (Sweden)

    Jing Yang

    2016-07-01

    Full Text Available The article presents a random neural Q-learning strategy for the obstacle avoidance problem of an autonomous mobile robot in unknown environments. In the proposed strategy, two independent modules, namely, avoidance without considering the target and goal-seeking without considering obstacles, are first trained using the proposed random neural Q-learning algorithm to obtain their best control policies. Then, the two trained modules are combined based on a switching function to realize the obstacle avoidance in unknown environments. For the proposed random neural Q-learning algorithm, a single-hidden layer feedforward network is used to approximate the Q-function to estimate the Q-value. The parameters of the single-hidden layer feedforward network are modified using the recently proposed neural algorithm named the online sequential version of extreme learning machine, where the parameters of the hidden nodes are assigned randomly and the sample data can come one by one. However, different from the original online sequential version of extreme learning machine algorithm, the initial output weights are estimated subjected to quadratic inequality constraint to improve the convergence speed. Finally, the simulation results demonstrate that the proposed random neural Q-learning strategy can successfully solve the obstacle avoidance problem. Also, the higher learning efficiency and better generalization ability are achieved by the proposed random neural Q-learning algorithm compared with the Q-learning based on the back-propagation method.

  5. Deep learning in neural networks: an overview.

    Science.gov (United States)

    Schmidhuber, Jürgen

    2015-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

  6. Radial basis function (RBF) neural network control for mechanical systems design, analysis and Matlab simulation

    CERN Document Server

    Liu, Jinkun

    2013-01-01

    Radial Basis Function (RBF) Neural Network Control for Mechanical Systems is motivated by the need for systematic design approaches to stable adaptive control system design using neural network approximation-based techniques. The main objectives of the book are to introduce the concrete design methods and MATLAB simulation of stable adaptive RBF neural control strategies. In this book, a broad range of implementable neural network control design methods for mechanical systems are presented, such as robot manipulators, inverted pendulums, single link flexible joint robots, motors, etc. Advanced neural network controller design methods and their stability analysis are explored. The book provides readers with the fundamentals of neural network control system design.   This book is intended for the researchers in the fields of neural adaptive control, mechanical systems, Matlab simulation, engineering design, robotics and automation. Jinkun Liu is a professor at Beijing University of Aeronautics and Astronauti...

  7. The neural basis of monitoring goal progress

    Directory of Open Access Journals (Sweden)

    Yael eBenn

    2014-09-01

    Full Text Available The neural basis of progress monitoring has received relatively little attention compared to other sub-processes that are involved in goal directed behavior such as motor control and response inhibition. Studies of error-monitoring have identified the dorsal anterior cingulate cortex (dACC as a structure that is sensitive to conflict detection, and triggers corrective action. However, monitoring goal progress involves monitoring correct as well as erroneous events over a period of time. In the present research, 20 healthy participants underwent fMRI while playing a game that involved monitoring progress towards either a numerical or a visuo-spatial target. The findings confirmed the role of the dACC in detecting situations in which the current state may conflict with the desired state, but also revealed activations in the frontal and parietal regions, pointing to the involvement of processes such as attention and working memory in monitoring progress over time. In addition, activation of the cuneus was associated with monitoring progress towards a specific target presented in the visual modality. This is the first time that activation in this region has been linked to higher-order processing of goal-relevant information, rather than low-level anticipation of visual stimuli. Taken together, these findings identify the neural substrates involved in monitoring progress over time, and how these extend beyond activations observed in conflict and error monitoring.

  8. The neural basis of deception in strategic interactions.

    Science.gov (United States)

    Volz, Kirsten G; Vogeley, Kai; Tittgemeyer, Marc; von Cramon, D Yves; Sutter, Matthias

    2015-01-01

    Communication based on informational asymmetries abounds in politics, business, and almost any other form of social interaction. Informational asymmetries may create incentives for the better-informed party to exploit her advantage by misrepresenting information. Using a game-theoretic setting, we investigate the neural basis of deception in human interaction. Unlike in most previous fMRI research on deception, the participants decide themselves whether to lie or not. We find activation within the right temporo-parietal junction (rTPJ), the dorsal anterior cingulate cortex (ACC), the (pre)cuneus (CUN), and the anterior frontal gyrus (aFG) when contrasting lying with truth telling. Notably, our design also allows for an investigation of the neural foundations of sophisticated deception through telling the truth-when the sender does not expect the receiver to believe her (true) message. Sophisticated deception triggers activation within the same network as plain lies, i.e., we find activity within the rTPJ, the CUN, and aFG. We take this result to show that brain activation can reveal the sender's veridical intention to deceive others, irrespective of whether in fact the sender utters the factual truth or not.

  9. The Neural Basis of Deception in Strategic Interactions

    Directory of Open Access Journals (Sweden)

    Kirsten G Volz

    2015-02-01

    Full Text Available Communication based on informational asymmetries abounds in politics, business, and almost any other form of social interaction. Informational asymmetries may create incentives for the better-informed party to exploit her advantage by misrepresenting information. Using a game-theoretic setting, we investigate the neural basis of deception in human interaction. Unlike in most previous fMRI research on deception, the participants decide themselves whether to lie or not. We find activation within the right temporo-parietal junction (rTPJ, the dorsal anterior cingulate cortex (ACC, the (precuneus (CUN, and the anterior frontal gyrus (aFG when contrasting lying with truth telling. Notably, our design also allows for an investigation of the neural foundations of sophisticated deception through telling the truth—when the sender does not expect the receiver to believe her (true message. Sophisticated deception triggers activation within the same network as plain lies, i.e., we find activity within the rTPJ, the CUN, and aFG. We take this result to show that brain activation can reveal the sender’s veridical intention to deceive others, irrespective of whether in fact the sender utters the factual truth or not.

  10. Maximum entropy methods for extracting the learned features of deep neural networks.

    Science.gov (United States)

    Finnegan, Alex; Song, Jun S

    2017-10-01

    New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

  11. Learning drifting concepts with neural networks

    NARCIS (Netherlands)

    Biehl, Michael; Schwarze, Holm

    1993-01-01

    The learning of time-dependent concepts with a neural network is studied analytically and numerically. The linearly separable target rule is represented by an N-vector, whose time dependence is modelled by a random or deterministic drift process. A single-layer network is trained online using

  12. Temporal-pattern learning in neural models

    CERN Document Server

    Genís, Carme Torras

    1985-01-01

    While the ability of animals to learn rhythms is an unquestionable fact, the underlying neurophysiological mechanisms are still no more than conjectures. This monograph explores the requirements of such mechanisms, reviews those previously proposed and postulates a new one based on a direct electric coding of stimulation frequencies. Experi­ mental support for the option taken is provided both at the single neuron and neural network levels. More specifically, the material presented divides naturally into four parts: a description of the experimental and theoretical framework where this work becomes meaningful (Chapter 2), a detailed specifica­ tion of the pacemaker neuron model proposed together with its valida­ tion through simulation (Chapter 3), an analytic study of the behavior of this model when submitted to rhythmic stimulation (Chapter 4) and a description of the neural network model proposed for learning, together with an analysis of the simulation results obtained when varying seve­ ral factors r...

  13. Neural basis of acquired amusia and its recovery after stroke

    OpenAIRE

    Sihvonen, A.J.; Ripollés, P.; Leo, V.; Rodríguez-Fornells, Antoni; Soinila, S.; Särkämö, T.

    2016-01-01

    Although acquired amusia is a relatively common disorder after stroke, its precise neuroanatomical basis is still unknown. To evaluate which brain regions form the neural substrate for acquired amusia and its recovery, we performed a voxel-based lesion-symptom mapping (VLSM) and morphometry (VBM) study with 77 human stroke subjects. Structural MRIs were acquired at acute and 6 month poststroke stages. Amusia and aphasia were behaviorally assessed at acute and 3 month poststroke stages using t...

  14. Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity

    Science.gov (United States)

    Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan

    2018-02-01

    Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.

  15. Continuous Online Sequence Learning with an Unsupervised Neural Network Model.

    Science.gov (United States)

    Cui, Yuwei; Ahmad, Subutar; Hawkins, Jeff

    2016-09-14

    The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory recently has been proposed as a theoretical framework for sequence learning in the cortex. In this letter, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data. We show the model is able to continuously learn a large number of variableorder temporal sequences using an unsupervised Hebbian-like learning rule. The sparse temporal codes formed by the model can robustly handle branching temporal sequences by maintaining multiple predictions until there is sufficient disambiguating evidence. We compare the HTM sequence memory with other sequence learning algorithms, including statistical methods: autoregressive integrated moving average; feedforward neural networks-time delay neural network and online sequential extreme learning machine; and recurrent neural networks-long short-term memory and echo-state networks on sequence prediction problems with both artificial and real-world data. The HTM model achieves comparable accuracy to other state-of-the-art algorithms. The model also exhibits properties that are critical for sequence learning, including continuous online learning, the ability to handle multiple predictions and branching sequences with high-order statistics, robustness to sensor noise and fault tolerance, and good performance without task-specific hyperparameter tuning. Therefore, the HTM sequence memory not only advances our understanding of how the brain may solve the sequence learning problem but is also applicable to real-world sequence learning problems from continuous data streams.

  16. Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm. (On-Line Harmonics Estimation Application

    Directory of Open Access Journals (Sweden)

    Eyad K Almaita

    2017-03-01

    Keywords: Energy efficiency, Power quality, Radial basis function, neural networks, adaptive, harmonic. Article History: Received Dec 15, 2016; Received in revised form Feb 2nd 2017; Accepted 13rd 2017; Available online How to Cite This Article: Almaita, E.K and Shawawreh J.Al (2017 Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm (On-Line Harmonics Estimation Application.  International Journal of Renewable Energy Develeopment, 6(1, 9-17. http://dx.doi.org/10.14710/ijred.6.1.9-17

  17. The neural basis of attaining conscious awareness of sad mood.

    Science.gov (United States)

    Smith, Ryan; Braden, B Blair; Chen, Kewei; Ponce, Francisco A; Lane, Richard D; Baxter, Leslie C

    2015-09-01

    The neural processes associated with becoming aware of sad mood are not fully understood. We examined the dynamic process of becoming aware of sad mood and recovery from sad mood. Sixteen healthy subjects underwent fMRI while participating in a sadness induction task designed to allow for variable mood induction times. Individualized regressors linearly modeled the time periods during the attainment of self-reported sad and baseline "neutral" mood states, and the validity of the linearity assumption was further tested using independent component analysis. During sadness induction the dorsomedial and ventrolateral prefrontal cortices, and anterior insula exhibited a linear increase in the blood oxygen level-dependent (BOLD) signal until subjects became aware of a sad mood and then a subsequent linear decrease as subjects transitioned from sadness back to the non-sadness baseline condition. These findings extend understanding of the neural basis of conscious emotional experience.

  18. Global Neural Pattern Similarity as a Common Basis for Categorization and Recognition Memory

    Science.gov (United States)

    Xue, Gui; Love, Bradley C.; Preston, Alison R.; Poldrack, Russell A.

    2014-01-01

    Familiarity, or memory strength, is a central construct in models of cognition. In previous categorization and long-term memory research, correlations have been found between psychological measures of memory strength and activation in the medial temporal lobes (MTLs), which suggests a common neural locus for memory strength. However, activation alone is insufficient for determining whether the same mechanisms underlie neural function across domains. Guided by mathematical models of categorization and long-term memory, we develop a theory and a method to test whether memory strength arises from the global similarity among neural representations. In human subjects, we find significant correlations between global similarity among activation patterns in the MTLs and both subsequent memory confidence in a recognition memory task and model-based measures of memory strength in a category learning task. Our work bridges formal cognitive theories and neuroscientific models by illustrating that the same global similarity computations underlie processing in multiple cognitive domains. Moreover, by establishing a link between neural similarity and psychological memory strength, our findings suggest that there may be an isomorphism between psychological and neural representational spaces that can be exploited to test cognitive theories at both the neural and behavioral levels. PMID:24872552

  19. Learning language with the wrong neural scaffolding: The cost of neural commitment to sounds.

    Directory of Open Access Journals (Sweden)

    Amy Sue Finn

    2013-11-01

    Full Text Available Does tuning to one’s native language explain the sensitive period for language learning? We explore the idea that tuning to (or becoming more selective for the properties of one’s native-language could result in being less open (or plastic for tuning to the properties of a new language. To explore how this might lead to the sensitive period for grammar learning, we ask if tuning to an earlier-learned aspect of language (sound structure has an impact on the neural representation of a later-learned aspect (grammar. English-speaking adults learned one of two miniature artificial languages over 4 days in the lab. Compared to English, both languages had novel grammar, but only one was comprised of novel sounds. After learning a language, participants were scanned while judging the grammaticality of sentences. Judgments were performed for the newly learned language and English. Learners of the similar-sounds language recruited regions that overlapped more with English. Learners of the distinct-sounds language, however, recruited the Superior Temporal Gyrus (STG to a greater extent, which was coactive with the Inferior Frontal Gyrus (IFG. Across learners, recruitment of IFG (but not STG predicted both learning success in tests conducted prior to the scan and grammatical judgment ability during the scan. Data suggest that adults’ difficulty learning language, especially grammar, could be due, at least in part, to the neural commitments they have made to the lower level linguistic components of their native language.

  20. Learning language with the wrong neural scaffolding: the cost of neural commitment to sounds

    Science.gov (United States)

    Finn, Amy S.; Hudson Kam, Carla L.; Ettlinger, Marc; Vytlacil, Jason; D'Esposito, Mark

    2013-01-01

    Does tuning to one's native language explain the “sensitive period” for language learning? We explore the idea that tuning to (or becoming more selective for) the properties of one's native-language could result in being less open (or plastic) for tuning to the properties of a new language. To explore how this might lead to the sensitive period for grammar learning, we ask if tuning to an earlier-learned aspect of language (sound structure) has an impact on the neural representation of a later-learned aspect (grammar). English-speaking adults learned one of two miniature artificial languages (MALs) over 4 days in the lab. Compared to English, both languages had novel grammar, but only one was comprised of novel sounds. After learning a language, participants were scanned while judging the grammaticality of sentences. Judgments were performed for the newly learned language and English. Learners of the similar-sounds language recruited regions that overlapped more with English. Learners of the distinct-sounds language, however, recruited the Superior Temporal Gyrus (STG) to a greater extent, which was coactive with the Inferior Frontal Gyrus (IFG). Across learners, recruitment of IFG (but not STG) predicted both learning success in tests conducted prior to the scan and grammatical judgment ability during the scan. Data suggest that adults' difficulty learning language, especially grammar, could be due, at least in part, to the neural commitments they have made to the lower level linguistic components of their native language. PMID:24273497

  1. Multi-modular neural networks for the classification of e+e- hadronic events

    International Nuclear Information System (INIS)

    Proriol, J.

    1994-01-01

    Some multi-modular neural network methods of classifying e + e - hadronic events are presented. We compare the performances of the following neural networks: MLP (multilayer perceptron), MLP and LVQ (learning vector quantization) trained sequentially, and MLP and RBF (radial basis function) trained sequentially. We introduce a MLP-RBF cooperative neural network. Our last study is a multi-MLP neural network. (orig.)

  2. Learning free energy landscapes using artificial neural networks.

    Science.gov (United States)

    Sidky, Hythem; Whitmer, Jonathan K

    2018-03-14

    Existing adaptive bias techniques, which seek to estimate free energies and physical properties from molecular simulations, are limited by their reliance on fixed kernels or basis sets which hinder their ability to efficiently conform to varied free energy landscapes. Further, user-specified parameters are in general non-intuitive yet significantly affect the convergence rate and accuracy of the free energy estimate. Here we propose a novel method, wherein artificial neural networks (ANNs) are used to develop an adaptive biasing potential which learns free energy landscapes. We demonstrate that this method is capable of rapidly adapting to complex free energy landscapes and is not prone to boundary or oscillation problems. The method is made robust to hyperparameters and overfitting through Bayesian regularization which penalizes network weights and auto-regulates the number of effective parameters in the network. ANN sampling represents a promising innovative approach which can resolve complex free energy landscapes in less time than conventional approaches while requiring minimal user input.

  3. Learning free energy landscapes using artificial neural networks

    Science.gov (United States)

    Sidky, Hythem; Whitmer, Jonathan K.

    2018-03-01

    Existing adaptive bias techniques, which seek to estimate free energies and physical properties from molecular simulations, are limited by their reliance on fixed kernels or basis sets which hinder their ability to efficiently conform to varied free energy landscapes. Further, user-specified parameters are in general non-intuitive yet significantly affect the convergence rate and accuracy of the free energy estimate. Here we propose a novel method, wherein artificial neural networks (ANNs) are used to develop an adaptive biasing potential which learns free energy landscapes. We demonstrate that this method is capable of rapidly adapting to complex free energy landscapes and is not prone to boundary or oscillation problems. The method is made robust to hyperparameters and overfitting through Bayesian regularization which penalizes network weights and auto-regulates the number of effective parameters in the network. ANN sampling represents a promising innovative approach which can resolve complex free energy landscapes in less time than conventional approaches while requiring minimal user input.

  4. The neural basis of bounded rational behavior

    Directory of Open Access Journals (Sweden)

    Coricelli, Giorgio

    2012-03-01

    Full Text Available Bounded rational behaviour is commonly observed in experimental games and in real life situations. Neuroeconomics can help to understand the mental processing underlying bounded rationality and out-of-equilibrium behaviour. Here we report results from recent studies on the neural basis of limited steps of reasoning in a competitive setting —the beauty contest game. We use functional magnetic resonance imaging (fMRI to study the neural correlates of human mental processes in strategic games. We apply a cognitive hierarchy model to classify subject’s choices in the experimental game according to the degree of strategic reasoning so that we can identify the neural substrates of different levels of strategizing. We found a correlation between levels of strategic reasoning and activity in a neural network related to mentalizing, i.e. the ability to think about other’s thoughts and mental states. Moreover, brain data showed how complex cognitive processes subserve the higher level of reasoning about others. We describe how a cognitive hierarchy model fits both behavioural and brain data.

    La racionalidad limitada es un fenómeno observado de manera frecuente tanto en juegos experimentales como en situaciones cotidianas. La Neuroeconomía puede mejorar la comprensión de los procesos mentales que caracterizan la racionalidad limitada; en paralelo nos puede ayudar a comprender comportamientos que violan el equilibrio. Nuestro trabajo presenta resultados recientes sobre la bases neuronales del razonamiento estratégico (y sus límite en juegos competitivos —como el juego del “beauty contest”. Estudiamos las bases neuronales del comportamiento estratégico en juegos con interacción entre sujetos usando resonancia magnética funcional (fMRI. Las decisiones de los participantes se clasifican acorde al grado de razonamiento estratégico: el llamado modelo de Jerarquías Cognitivas. Los resultados muestran una correlación entre niveles de

  5. The impact of iconic gestures on foreign language word learning and its neural substrate.

    Science.gov (United States)

    Macedonia, Manuela; Müller, Karsten; Friederici, Angela D

    2011-06-01

    Vocabulary acquisition represents a major challenge in foreign language learning. Research has demonstrated that gestures accompanying speech have an impact on memory for verbal information in the speakers' mother tongue and, as recently shown, also in foreign language learning. However, the neural basis of this effect remains unclear. In a within-subjects design, we compared learning of novel words coupled with iconic and meaningless gestures. Iconic gestures helped learners to significantly better retain the verbal material over time. After the training, participants' brain activity was registered by means of fMRI while performing a word recognition task. Brain activations to words learned with iconic and with meaningless gestures were contrasted. We found activity in the premotor cortices for words encoded with iconic gestures. In contrast, words encoded with meaningless gestures elicited a network associated with cognitive control. These findings suggest that memory performance for newly learned words is not driven by the motor component as such, but by the motor image that matches an underlying representation of the word's semantics. Copyright © 2010 Wiley-Liss, Inc.

  6. Deep Learning Neural Networks in Cybersecurity - Managing Malware with AI

    OpenAIRE

    Rayle, Keith

    2017-01-01

    There’s a lot of talk about the benefits of deep learning (neural networks) and how it’s the new electricity that will power us into the future. Medical diagnosis, computer vision and speech recognition are all examples of use-cases where neural networks are being applied in our everyday business environment. This begs the question…what are the uses of neural-network applications for cyber security? How does the AI process work when applying neural networks to detect malicious software bombar...

  7. Consensus-based distributed cooperative learning from closed-loop neural control systems.

    Science.gov (United States)

    Chen, Weisheng; Hua, Shaoyong; Zhang, Huaguang

    2015-02-01

    In this paper, the neural tracking problem is addressed for a group of uncertain nonlinear systems where the system structures are identical but the reference signals are different. This paper focuses on studying the learning capability of neural networks (NNs) during the control process. First, we propose a novel control scheme called distributed cooperative learning (DCL) control scheme, by establishing the communication topology among adaptive laws of NN weights to share their learned knowledge online. It is further proved that if the communication topology is undirected and connected, all estimated weights of NNs can converge to small neighborhoods around their optimal values over a domain consisting of the union of all state orbits. Second, as a corollary it is shown that the conclusion on the deterministic learning still holds in the decentralized adaptive neural control scheme where, however, the estimated weights of NNs just converge to small neighborhoods of the optimal values along their own state orbits. Thus, the learned controllers obtained by DCL scheme have the better generalization capability than ones obtained by decentralized learning method. A simulation example is provided to verify the effectiveness and advantages of the control schemes proposed in this paper.

  8. Neural-Fitted TD-Leaf Learning for Playing Othello With Structured Neural Networks

    NARCIS (Netherlands)

    van den Dries, Sjoerd; Wiering, Marco A.

    This paper describes a methodology for quickly learning to play games at a strong level. The methodology consists of a novel combination of three techniques, and a variety of experiments on the game of Othello demonstrates their usefulness. First, structures or topologies in neural network

  9. The Biological Basis of Learning and Individuality.

    Science.gov (United States)

    Kandel, Eric R.; Hawkins, Robert D.

    1992-01-01

    Describes the biological basis of learning and individuality. Presents an overview of recent discoveries that suggest learning engages a simple set of rules that modify the strength of connection between neurons in the brain. The changes are cited as playing an important role in making each individual unique. (MCO)

  10. Single-hidden-layer feed-forward quantum neural network based on Grover learning.

    Science.gov (United States)

    Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

    2013-09-01

    In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

  11. Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning

    NARCIS (Netherlands)

    van der Velde, Frank; van der Velde, Frank; Besold, Tarek R.; Lamb, Luis; Serafini, Luciano; Tabor, Whitney

    2016-01-01

    Simulations are presented and discussed of learning sequential control in a Neural Blackboard Architecture (NBA) for in situ concept-based reasoning. Sequential control is learned in a reservoir network, consisting of columns with neural circuits. This allows the reservoir to control the dynamics of

  12. Learning-induced pattern classification in a chaotic neural network

    International Nuclear Information System (INIS)

    Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

    2012-01-01

    In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

  13. The neural basis of human social values: evidence from functional MRI.

    Science.gov (United States)

    Zahn, Roland; Moll, Jorge; Paiva, Mirella; Garrido, Griselda; Krueger, Frank; Huey, Edward D; Grafman, Jordan

    2009-02-01

    Social values are composed of social concepts (e.g., "generosity") and context-dependent moral sentiments (e.g., "pride"). The neural basis of this intricate cognitive architecture has not been investigated thus far. Here, we used functional magnetic resonance imaging while subjects imagined their own actions toward another person (self-agency) which either conformed or were counter to a social value and were associated with pride or guilt, respectively. Imagined actions of another person toward the subjects (other-agency) in accordance with or counter to a value were associated with gratitude or indignation/anger. As hypothesized, superior anterior temporal lobe (aTL) activity increased with conceptual detail in all conditions. During self-agency, activity in the anterior ventromedial prefrontal cortex correlated with pride and guilt, whereas activity in the subgenual cingulate solely correlated with guilt. In contrast, indignation/anger activated lateral orbitofrontal-insular cortices. Pride and gratitude additionally evoked mesolimbic and basal forebrain activations. Our results demonstrate that social values emerge from coactivation of stable abstract social conceptual representations in the superior aTL and context-dependent moral sentiments encoded in fronto-mesolimbic regions. This neural architecture may provide the basis of our ability to communicate about the meaning of social values across cultural contexts without limiting our flexibility to adapt their emotional interpretation.

  14. Social learning in humans and other animals.

    Directory of Open Access Journals (Sweden)

    Jean-François eGariépy

    2014-03-01

    Full Text Available Decisions made by individuals can be influenced by what others think and do. Social learning includes a wide array of behaviors such as imitation, observational learning of novel foraging techniques, peer or parental influences on individual preferences, as well as outright teaching. These processes are believed to underlie an important part of cultural variation among human populations and may also explain intraspecific variation in behavior between geographically distinct populations of animals. Recent neurobiological studies have begun to uncover the neural basis of social learning. Here we review experimental evidence from the past few decades showing that social learning is a widespread set of skills present in multiple animal species. In mammals, the temporoparietal junction, the dorsomedial and dorsolateral prefrontal cortex, as well as the anterior cingulate gyrus, appear to play critical roles in social learning. Birds, fish and insects also learn from others, but the underlying neural mechanisms remain poorly understood. We discuss the evolutionary implications of these findings and highlight the importance of emerging animal models that permit precise modification of neural circuit function for elucidating the neural basis of social learning.

  15. Nonlinear Control of an Active Magnetic Bearing System Achieved Using a Fuzzy Control with Radial Basis Function Neural Network

    Directory of Open Access Journals (Sweden)

    Seng-Chi Chen

    2014-01-01

    Full Text Available Studies on active magnetic bearing (AMB systems are increasing in popularity and practical applications. Magnetic bearings cause less noise, friction, and vibration than the conventional mechanical bearings; however, the control of AMB systems requires further investigation. The magnetic force has a highly nonlinear relation to the control current and the air gap. This paper proposes an intelligent control method for positioning an AMB system that uses a neural fuzzy controller (NFC. The mathematical model of an AMB system comprises identification followed by collection of information from this system. A fuzzy logic controller (FLC, the parameters of which are adjusted using a radial basis function neural network (RBFNN, is applied to the unbalanced vibration in an AMB system. The AMB system exhibited a satisfactory control performance, with low overshoot, and produced improved transient and steady-state responses under various operating conditions. The NFC has been verified on a prototype AMB system. The proposed controller can be feasibly applied to AMB systems exposed to various external disturbances; demonstrating the effectiveness of the NFC with self-learning and self-improving capacities is proven.

  16. Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm

    International Nuclear Information System (INIS)

    Yu, Lean; Wang, Shouyang; Lai, Kin Keung

    2008-01-01

    In this study, an empirical mode decomposition (EMD) based neural network ensemble learning paradigm is proposed for world crude oil spot price forecasting. For this purpose, the original crude oil spot price series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). Then a three-layer feed-forward neural network (FNN) model was used to model each of the extracted IMFs, so that the tendencies of these IMFs could be accurately predicted. Finally, the prediction results of all IMFs are combined with an adaptive linear neural network (ALNN), to formulate an ensemble output for the original crude oil price series. For verification and testing, two main crude oil price series, West Texas Intermediate (WTI) crude oil spot price and Brent crude oil spot price, are used to test the effectiveness of the proposed EMD-based neural network ensemble learning methodology. Empirical results obtained demonstrate attractiveness of the proposed EMD-based neural network ensemble learning paradigm. (author)

  17. Learning and coding in biological neural networks

    Science.gov (United States)

    Fiete, Ila Rani

    How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and

  18. Hypothetical Pattern Recognition Design Using Multi-Layer Perceptorn Neural Network For Supervised Learning

    Directory of Open Access Journals (Sweden)

    Md. Abdullah-al-mamun

    2015-08-01

    Full Text Available Abstract Humans are capable to identifying diverse shape in the different pattern in the real world as effortless fashion due to their intelligence is grow since born with facing several learning process. Same way we can prepared an machine using human like brain called Artificial Neural Network that can be recognize different pattern from the real world object. Although the various techniques is exists to implementation the pattern recognition but recently the artificial neural network approaches have been giving the significant attention. Because the approached of artificial neural network is like a human brain that is learn from different observation and give a decision the previously learning rule. Over the 50 years research now a days pattern recognition for machine learning using artificial neural network got a significant achievement. For this reason many real world problem can be solve by modeling the pattern recognition process. The objective of this paper is to present the theoretical concept for pattern recognition design using Multi-Layer Perceptorn neural networkin the algorithm of artificial Intelligence as the best possible way of utilizing available resources to make a decision that can be a human like performance.

  19. Deep learning classification in asteroseismology using an improved neural network

    DEFF Research Database (Denmark)

    Hon, Marc; Stello, Dennis; Yu, Jie

    2018-01-01

    Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic...... frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS, and PLATO, we train classifiers that are able to classify the evolutionary states of lower...

  20. Neural network-based model reference adaptive control system.

    Science.gov (United States)

    Patino, H D; Liu, D

    2000-01-01

    In this paper, an approach to model reference adaptive control based on neural networks is proposed and analyzed for a class of first-order continuous-time nonlinear dynamical systems. The controller structure can employ either a radial basis function network or a feedforward neural network to compensate adaptively the nonlinearities in the plant. A stable controller-parameter adjustment mechanism, which is determined using the Lyapunov theory, is constructed using a sigma-modification-type updating law. The evaluation of control error in terms of the neural network learning error is performed. That is, the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the neural network. In the design and analysis of neural network-based control systems, it is important to take into account the neural network learning error and its influence on the control error of the plant. Simulation results showing the feasibility and performance of the proposed approach are given.

  1. Incorporating deep learning with convolutional neural networks and position specific scoring matrices for identifying electron transport proteins.

    Science.gov (United States)

    Le, Nguyen-Quoc-Khanh; Ho, Quang-Thai; Ou, Yu-Yen

    2017-09-05

    In several years, deep learning is a modern machine learning technique using in a variety of fields with state-of-the-art performance. Therefore, utilization of deep learning to enhance performance is also an important solution for current bioinformatics field. In this study, we try to use deep learning via convolutional neural networks and position specific scoring matrices to identify electron transport proteins, which is an important molecular function in transmembrane proteins. Our deep learning method can approach a precise model for identifying of electron transport proteins with achieved sensitivity of 80.3%, specificity of 94.4%, and accuracy of 92.3%, with MCC of 0.71 for independent dataset. The proposed technique can serve as a powerful tool for identifying electron transport proteins and can help biologists understand the function of the electron transport proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

  2. Biologically-inspired Learning in Pulsed Neural Networks

    DEFF Research Database (Denmark)

    Lehmann, Torsten; Woodburn, Robin

    1999-01-01

    Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the `biologically-inspired' approach......, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve simple classical-conditioning tasks. We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue...

  3. Sensorimotor learning biases choice behavior: a learning neural field model for decision making.

    Directory of Open Access Journals (Sweden)

    Christian Klaes

    Full Text Available According to a prominent view of sensorimotor processing in primates, selection and specification of possible actions are not sequential operations. Rather, a decision for an action emerges from competition between different movement plans, which are specified and selected in parallel. For action choices which are based on ambiguous sensory input, the frontoparietal sensorimotor areas are considered part of the common underlying neural substrate for selection and specification of action. These areas have been shown capable of encoding alternative spatial motor goals in parallel during movement planning, and show signatures of competitive value-based selection among these goals. Since the same network is also involved in learning sensorimotor associations, competitive action selection (decision making should not only be driven by the sensory evidence and expected reward in favor of either action, but also by the subject's learning history of different sensorimotor associations. Previous computational models of competitive neural decision making used predefined associations between sensory input and corresponding motor output. Such hard-wiring does not allow modeling of how decisions are influenced by sensorimotor learning or by changing reward contingencies. We present a dynamic neural field model which learns arbitrary sensorimotor associations with a reward-driven Hebbian learning algorithm. We show that the model accurately simulates the dynamics of action selection with different reward contingencies, as observed in monkey cortical recordings, and that it correctly predicted the pattern of choice errors in a control experiment. With our adaptive model we demonstrate how network plasticity, which is required for association learning and adaptation to new reward contingencies, can influence choice behavior. The field model provides an integrated and dynamic account for the operations of sensorimotor integration, working memory and action

  4. Ontology Mapping Neural Network: An Approach to Learning and Inferring Correspondences among Ontologies

    Science.gov (United States)

    Peng, Yefei

    2010-01-01

    An ontology mapping neural network (OMNN) is proposed in order to learn and infer correspondences among ontologies. It extends the Identical Elements Neural Network (IENN)'s ability to represent and map complex relationships. The learning dynamics of simultaneous (interlaced) training of similar tasks interact at the shared connections of the…

  5. Learning by stimulation avoidance: A principle to control spiking neural networks dynamics.

    Science.gov (United States)

    Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi

    2017-01-01

    Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle "Learning by Stimulation Avoidance" (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system.

  6. Lifelong learning of human actions with deep neural network self-organization.

    Science.gov (United States)

    Parisi, German I; Tani, Jun; Weber, Cornelius; Wermter, Stefan

    2017-12-01

    Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.

  7. A fast identification algorithm for Box-Cox transformation based radial basis function neural network.

    Science.gov (United States)

    Hong, Xia

    2006-07-01

    In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

  8. Framing effects: behavioral dynamics and neural basis.

    Science.gov (United States)

    Zheng, Hongming; Wang, X T; Zhu, Liqi

    2010-09-01

    This study examined the neural basis of framing effects using life-death decision problems framed either positively in terms of lives saved or negatively in terms of lives lost in large group and small group contexts. Using functional MRI we found differential brain activations to the verbal and social cues embedded in the choice problems. In large group contexts, framing effects were significant where participants were more risk seeking under the negative (loss) framing than under the positive (gain) framing. This behavioral difference in risk preference was mainly regulated by the activation in the right inferior frontal gyrus, including the homologue of the Broca's area. In contrast, framing effects diminished in small group contexts while the insula and parietal lobe in the right hemisphere were distinctively activated, suggesting an important role of emotion in switching choice preference from an indecisive mode to a more consistent risk-taking inclination, governed by a kith-and-kin decision rationality. Copyright 2010 Elsevier Ltd. All rights reserved.

  9. Neural Control of a Tracking Task via Attention-Gated Reinforcement Learning for Brain-Machine Interfaces.

    Science.gov (United States)

    Wang, Yiwen; Wang, Fang; Xu, Kai; Zhang, Qiaosheng; Zhang, Shaomin; Zheng, Xiaoxiang

    2015-05-01

    Reinforcement learning (RL)-based brain machine interfaces (BMIs) enable the user to learn from the environment through interactions to complete the task without desired signals, which is promising for clinical applications. Previous studies exploited Q-learning techniques to discriminate neural states into simple directional actions providing the trial initial timing. However, the movements in BMI applications can be quite complicated, and the action timing explicitly shows the intention when to move. The rich actions and the corresponding neural states form a large state-action space, imposing generalization difficulty on Q-learning. In this paper, we propose to adopt attention-gated reinforcement learning (AGREL) as a new learning scheme for BMIs to adaptively decode high-dimensional neural activities into seven distinct movements (directional moves, holdings and resting) due to the efficient weight-updating. We apply AGREL on neural data recorded from M1 of a monkey to directly predict a seven-action set in a time sequence to reconstruct the trajectory of a center-out task. Compared to Q-learning techniques, AGREL could improve the target acquisition rate to 90.16% in average with faster convergence and more stability to follow neural activity over multiple days, indicating the potential to achieve better online decoding performance for more complicated BMI tasks.

  10. Global and local missions of cAMP signaling in neural plasticity, learning and memory

    Directory of Open Access Journals (Sweden)

    Daewoo eLee

    2015-08-01

    Full Text Available The fruit fly Drosophila melanogaster has been a popular model to study cAMP signaling and resultant behaviors due to its powerful genetic approaches. All molecular components (AC, PDE, PKA, CREB, etc essential for cAMP signaling have been identified in the fly. Among them, adenylyl cyclase (AC gene rutabaga and phosphodiesterase (PDE gene dunce have been intensively studied to understand the role of cAMP signaling. Interestingly, these two mutant genes were originally identified on the basis of associative learning deficits. This commentary summarizes findings on the role of cAMP in Drosophila neuronal excitability, synaptic plasticity and memory. It mainly focuses on two distinct mechanisms (global versus local regulating excitatory and inhibitory synaptic plasticity related to cAMP homeostasis. This dual regulatory role of cAMP is to increase the strength of excitatory neural circuits on one hand, but to act locally on postsynaptic GABA receptors to decrease inhibitory synaptic plasticity on the other. Thus the action of cAMP could result in a global increase in the neural circuit excitability and memory. Implications of this cAMP signaling related to drug discovery for neural diseases are also described.

  11. Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography

    Directory of Open Access Journals (Sweden)

    Murilo Coutinho

    2018-04-01

    Full Text Available Researches in Artificial Intelligence (AI have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC. Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one.

  12. Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography.

    Science.gov (United States)

    Coutinho, Murilo; de Oliveira Albuquerque, Robson; Borges, Fábio; García Villalba, Luis Javier; Kim, Tai-Hoon

    2018-04-24

    Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one.

  13. Introduction to spiking neural networks: Information processing, learning and applications.

    Science.gov (United States)

    Ponulak, Filip; Kasinski, Andrzej

    2011-01-01

    The concept that neural information is encoded in the firing rate of neurons has been the dominant paradigm in neurobiology for many years. This paradigm has also been adopted by the theory of artificial neural networks. Recent physiological experiments demonstrate, however, that in many parts of the nervous system, neural code is founded on the timing of individual action potentials. This finding has given rise to the emergence of a new class of neural models, called spiking neural networks. In this paper we summarize basic properties of spiking neurons and spiking networks. Our focus is, specifically, on models of spike-based information coding, synaptic plasticity and learning. We also survey real-life applications of spiking models. The paper is meant to be an introduction to spiking neural networks for scientists from various disciplines interested in spike-based neural processing.

  14. Using imagination to understand the neural basis of episodic memory

    Science.gov (United States)

    Hassabis, Demis; Kumaran, Dharshan; Maguire, Eleanor A.

    2008-01-01

    Functional MRI (fMRI) studies investigating the neural basis of episodic memory recall, and the related task of thinking about plausible personal future events, have revealed a consistent network of associated brain regions. Surprisingly little, however, is understood about the contributions individual brain areas make to the overall recollective experience. In order to examine this, we employed a novel fMRI paradigm where subjects had to imagine fictitious experiences. In contrast to future thinking, this results in experiences that are not explicitly temporal in nature or as reliant on self-processing. By using previously imagined fictitious experiences as a comparison for episodic memories, we identified the neural basis of a key process engaged in common, namely scene construction, involving the generation, maintenance and visualisation of complex spatial contexts. This was associated with activations in a distributed network, including hippocampus, parahippocampal gyrus, and retrosplenial cortex. Importantly, we disambiguated these common effects from episodic memory-specific responses in anterior medial prefrontal cortex, posterior cingulate cortex and precuneus. These latter regions may support self-schema and familiarity processes, and contribute to the brain's ability to distinguish real from imaginary memories. We conclude that scene construction constitutes a common process underlying episodic memory and imagination of fictitious experiences, and suggest it may partially account for the similar brain networks implicated in navigation, episodic future thinking, and the default mode. We suggest that further brain regions are co-opted into this core network in a task-specific manner to support functions such as episodic memory that may have additional requirements. PMID:18160644

  15. A learning algorithm for oscillatory cellular neural networks.

    Science.gov (United States)

    Ho, C Y.; Kurokawa, H

    1999-07-01

    We present a cellular type oscillatory neural network for temporal segregation of stationary input patterns. The model comprises an array of locally connected neural oscillators with connections limited to a 4-connected neighborhood. The architecture is reminiscent of the well-known cellular neural network that consists of local connection for feature extraction. By means of a novel learning rule and an initialization scheme, global synchronization can be accomplished without incurring any erroneous synchrony among uncorrelated objects. Each oscillator comprises two mutually coupled neurons, and neurons share a piecewise-linear activation function characteristic. The dynamics of traditional oscillatory models is simplified by using only one plastic synapse, and the overall complexity for hardware implementation is reduced. Based on the connectedness of image segments, it is shown that global synchronization and desynchronization can be achieved by means of locally connected synapses, and this opens up a tremendous application potential for the proposed architecture. Furthermore, by using special grouping synapses it is demonstrated that temporal segregation of overlapping gray-level and color segments can also be achieved. Finally, simulation results show that the learning rule proposed circumvents the problem of component mismatches, and hence facilitates a large-scale integration.

  16. Influence of the Training Methods in the Diagnosis of Multiple Sclerosis Using Radial Basis Functions Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Ángel Gutiérrez

    2015-04-01

    Full Text Available The data available in the average clinical study of a disease is very often small. This is one of the main obstacles in the application of neural networks to the classification of biological signals used for diagnosing diseases. A rule of thumb states that the number of parameters (weights that can be used for training a neural network should be around 15% of the available data, to avoid overlearning. This condition puts a limit on the dimension of the input space. Different authors have used different approaches to solve this problem, like eliminating redundancy in the data, preprocessing the data to find centers for the radial basis functions, or extracting a small number of features that were used as inputs. It is clear that the classification would be better the more features we could feed into the network. The approach utilized in this paper is incrementing the number of training elements with randomly expanding training sets. This way the number of original signals does not constraint the dimension of the input set in the radial basis network. Then we train the network using the method that minimizes the error function using the gradient descent algorithm and the method that uses the particle swarm optimization technique. A comparison between the two methods showed that for the same number of iterations on both methods, the particle swarm optimization was faster, it was learning to recognize only the sick people. On the other hand, the gradient method was not as good in general better at identifying those people.

  17. Learning and forgetting on asymmetric, diluted neural networks

    International Nuclear Information System (INIS)

    Derrida, B.; Nadal, J.P.

    1987-01-01

    It is possible to construct diluted asymmetric models of neural networks for which the dynamics can be calculated exactly. The authors test several learning schemes, in particular, models for which the values of the synapses remain bounded and depend on the history. Our analytical results on the relative efficiencies of the various learning schemes are qualitatively similar to the corresponding ones obtained numerically on fully connected symmetric networks

  18. Strategies influence neural activity for feedback learning across child and adolescent development.

    Science.gov (United States)

    Peters, Sabine; Koolschijn, P Cédric M P; Crone, Eveline A; Van Duijvenvoorde, Anna C K; Raijmakers, Maartje E J

    2014-09-01

    Learning from feedback is an important aspect of executive functioning that shows profound improvements during childhood and adolescence. This is accompanied by neural changes in the feedback-learning network, which includes pre-supplementary motor area (pre- SMA)/anterior cingulate cortex (ACC), dorsolateral prefrontal cortex (DLPFC), superior parietal cortex (SPC), and the basal ganglia. However, there can be considerable differences within age ranges in performance that are ascribed to differences in strategy use. This is problematic for traditional approaches of analyzing developmental data, in which age groups are assumed to be homogenous in strategy use. In this study, we used latent variable models to investigate if underlying strategy groups could be detected for a feedback-learning task and whether there were differences in neural activation patterns between strategies. In a sample of 268 participants between ages 8 to 25 years, we observed four underlying strategy groups, which were cut across age groups and varied in the optimality of executive functioning. These strategy groups also differed in neural activity during learning; especially the most optimal performing group showed more activity in DLPFC, SPC and pre-SMA/ACC compared to the other groups. However, age differences remained an important contributor to neural activation, even when correcting for strategy. These findings contribute to the debate of age versus performance predictors of neural development, and highlight the importance of studying individual differences in strategy use when studying development. Copyright © 2014 Elsevier Ltd. All rights reserved.

  19. Vector control of wind turbine on the basis of the fuzzy selective neural net*

    Science.gov (United States)

    Engel, E. A.; Kovalev, I. V.; Engel, N. E.

    2016-04-01

    An article describes vector control of wind turbine based on fuzzy selective neural net. Based on the wind turbine system’s state, the fuzzy selective neural net tracks an maximum power point under random perturbations. Numerical simulations are accomplished to clarify the applicability and advantages of the proposed vector wind turbine’s control on the basis of the fuzzy selective neuronet. The simulation results show that the proposed intelligent control of wind turbine achieves real-time control speed and competitive performance, as compared to a classical control model with PID controllers based on traditional maximum torque control strategy.

  20. Mechanisms and Neural Basis of Object and Pattern Recognition: A Study with Chess Experts

    Science.gov (United States)

    Bilalic, Merim; Langner, Robert; Erb, Michael; Grodd, Wolfgang

    2010-01-01

    Comparing experts with novices offers unique insights into the functioning of cognition, based on the maximization of individual differences. Here we used this expertise approach to disentangle the mechanisms and neural basis behind two processes that contribute to everyday expertise: object and pattern recognition. We compared chess experts and…

  1. Improved Discriminability of Spatiotemporal Neural Patterns in Rat Motor Cortical Areas as Directional Choice Learning Progresses

    Directory of Open Access Journals (Sweden)

    Hongwei eMao

    2015-03-01

    Full Text Available Animals learn to choose a proper action among alternatives to improve their odds of success in food foraging and other activities critical for survival. Through trial-and-error, they learn correct associations between their choices and external stimuli. While a neural network that underlies such learning process has been identified at a high level, it is still unclear how individual neurons and a neural ensemble adapt as learning progresses. In this study, we monitored the activity of single units in the rat medial and lateral agranular (AGm and AGl, respectively areas as rats learned to make a left or right side lever press in response to a left or right side light cue. We noticed that rat movement parameters during the performance of the directional choice task quickly became stereotyped during the first 2-3 days or sessions. But learning the directional choice problem took weeks to occur. Accompanying rats’ behavioral performance adaptation, we observed neural modulation by directional choice in recorded single units. Our analysis shows that ensemble mean firing rates in the cue-on period did not change significantly as learning progressed, and the ensemble mean rate difference between left and right side choices did not show a clear trend of change either. However, the spatiotemporal firing patterns of the neural ensemble exhibited improved discriminability between the two directional choices through learning. These results suggest a spatiotemporal neural coding scheme in a motor cortical neural ensemble that may be responsible for and contributing to learning the directional choice task.

  2. Adaptive competitive learning neural networks

    Directory of Open Access Journals (Sweden)

    Ahmed R. Abas

    2013-11-01

    Full Text Available In this paper, the adaptive competitive learning (ACL neural network algorithm is proposed. This neural network not only groups similar input feature vectors together but also determines the appropriate number of groups of these vectors. This algorithm uses a new proposed criterion referred to as the ACL criterion. This criterion evaluates different clustering structures produced by the ACL neural network for an input data set. Then, it selects the best clustering structure and the corresponding network architecture for this data set. The selected structure is composed of the minimum number of clusters that are compact and balanced in their sizes. The selected network architecture is efficient, in terms of its complexity, as it contains the minimum number of neurons. Synaptic weight vectors of these neurons represent well-separated, compact and balanced clusters in the input data set. The performance of the ACL algorithm is evaluated and compared with the performance of a recently proposed algorithm in the literature in clustering an input data set and determining its number of clusters. Results show that the ACL algorithm is more accurate and robust in both determining the number of clusters and allocating input feature vectors into these clusters than the other algorithm especially with data sets that are sparsely distributed.

  3. The Neural Basis of Aversive Pavlovian Guidance during Planning.

    Science.gov (United States)

    Lally, Níall; Huys, Quentin J M; Eshel, Neir; Faulkner, Paul; Dayan, Peter; Roiser, Jonathan P

    2017-10-18

    Important real-world decisions are often arduous as they frequently involve sequences of choices, with initial selections affecting future options. Evaluating every possible combination of choices is computationally intractable, particularly for longer multistep decisions. Therefore, humans frequently use heuristics to reduce the complexity of decisions. We recently used a goal-directed planning task to demonstrate the profound behavioral influence and ubiquity of one such shortcut, namely aversive pruning, a reflexive Pavlovian process that involves neglecting parts of the decision space residing beyond salient negative outcomes. However, how the brain implements this important decision heuristic and what underlies individual differences have hitherto remained unanswered. Therefore, we administered an adapted version of the same planning task to healthy male and female volunteers undergoing functional magnetic resonance imaging (fMRI) to determine the neural basis of aversive pruning. Through both computational and standard categorical fMRI analyses, we show that when planning was influenced by aversive pruning, the subgenual cingulate cortex was robustly recruited. This neural signature was distinct from those associated with general planning and valuation, two fundamental cognitive components elicited by our task but which are complementary to aversive pruning. Furthermore, we found that individual variation in levels of aversive pruning was associated with the responses of insula and dorsolateral prefrontal cortices to the receipt of large monetary losses, and also with subclinical levels of anxiety. In summary, our data reveal the neural signatures of an important reflexive Pavlovian process that shapes goal-directed evaluations and thereby determines the outcome of high-level sequential cognitive processes. SIGNIFICANCE STATEMENT Multistep decisions are complex because initial choices constrain future options. Evaluating every path for long decision sequences

  4. The Neural Basis of Aversive Pavlovian Guidance during Planning

    Science.gov (United States)

    Faulkner, Paul

    2017-01-01

    Important real-world decisions are often arduous as they frequently involve sequences of choices, with initial selections affecting future options. Evaluating every possible combination of choices is computationally intractable, particularly for longer multistep decisions. Therefore, humans frequently use heuristics to reduce the complexity of decisions. We recently used a goal-directed planning task to demonstrate the profound behavioral influence and ubiquity of one such shortcut, namely aversive pruning, a reflexive Pavlovian process that involves neglecting parts of the decision space residing beyond salient negative outcomes. However, how the brain implements this important decision heuristic and what underlies individual differences have hitherto remained unanswered. Therefore, we administered an adapted version of the same planning task to healthy male and female volunteers undergoing functional magnetic resonance imaging (fMRI) to determine the neural basis of aversive pruning. Through both computational and standard categorical fMRI analyses, we show that when planning was influenced by aversive pruning, the subgenual cingulate cortex was robustly recruited. This neural signature was distinct from those associated with general planning and valuation, two fundamental cognitive components elicited by our task but which are complementary to aversive pruning. Furthermore, we found that individual variation in levels of aversive pruning was associated with the responses of insula and dorsolateral prefrontal cortices to the receipt of large monetary losses, and also with subclinical levels of anxiety. In summary, our data reveal the neural signatures of an important reflexive Pavlovian process that shapes goal-directed evaluations and thereby determines the outcome of high-level sequential cognitive processes. SIGNIFICANCE STATEMENT Multistep decisions are complex because initial choices constrain future options. Evaluating every path for long decision sequences

  5. Quantum neural networks: Current status and prospects for development

    Science.gov (United States)

    Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.

    2014-11-01

    The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.

  6. Nuclear power plant monitoring using real-time learning neural network

    International Nuclear Information System (INIS)

    Nabeshima, Kunihiko; Tuerkcan, E.; Ciftcioglu, O.

    1994-01-01

    In the present research, artificial neural network (ANN) with real-time adaptive learning is developed for the plant wide monitoring of Borssele Nuclear Power Plant (NPP). Adaptive ANN learning capability is integrated to the monitoring system so that robust and sensitive on-line monitoring is achieved in real-time environment. The major advantages provided by ANN are that system modelling is formed by means of measurement information obtained from a multi-output process system, explicit modelling is not required and the modelling is not restricted to linear systems. Also ANN can respond very fast to anomalous operational conditions. The real-time ANN learning methodology with adaptive real-time monitoring capability is described below for the wide-range and plant-wide data from an operating nuclear power plant. The layered neural network with error backpropagation algorithm for learning has three layers. The network type is auto-associative, inputs and outputs are exactly the same, using 12 plant signals. (author)

  7. A Self-Organizing Incremental Neural Network based on local distribution learning.

    Science.gov (United States)

    Xing, Youlu; Shi, Xiaofeng; Shen, Furao; Zhou, Ke; Zhao, Jinxi

    2016-12-01

    In this paper, we propose an unsupervised incremental learning neural network based on local distribution learning, which is called Local Distribution Self-Organizing Incremental Neural Network (LD-SOINN). The LD-SOINN combines the advantages of incremental learning and matrix learning. It can automatically discover suitable nodes to fit the learning data in an incremental way without a priori knowledge such as the structure of the network. The nodes of the network store rich local information regarding the learning data. The adaptive vigilance parameter guarantees that LD-SOINN is able to add new nodes for new knowledge automatically and the number of nodes will not grow unlimitedly. While the learning process continues, nodes that are close to each other and have similar principal components are merged to obtain a concise local representation, which we call a relaxation data representation. A denoising process based on density is designed to reduce the influence of noise. Experiments show that the LD-SOINN performs well on both artificial and real-word data. Copyright © 2016 Elsevier Ltd. All rights reserved.

  8. A novel Bayesian learning method for information aggregation in modular neural networks

    DEFF Research Database (Denmark)

    Wang, Pan; Xu, Lida; Zhou, Shang-Ming

    2010-01-01

    Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight...... benchmark problems have demonstrated that the proposed method can perform information aggregation efficiently in data modeling....

  9. Neural prediction errors reveal a risk-sensitive reinforcement-learning process in the human brain.

    Science.gov (United States)

    Niv, Yael; Edlund, Jeffrey A; Dayan, Peter; O'Doherty, John P

    2012-01-11

    Humans and animals are exquisitely, though idiosyncratically, sensitive to risk or variance in the outcomes of their actions. Economic, psychological, and neural aspects of this are well studied when information about risk is provided explicitly. However, we must normally learn about outcomes from experience, through trial and error. Traditional models of such reinforcement learning focus on learning about the mean reward value of cues and ignore higher order moments such as variance. We used fMRI to test whether the neural correlates of human reinforcement learning are sensitive to experienced risk. Our analysis focused on anatomically delineated regions of a priori interest in the nucleus accumbens, where blood oxygenation level-dependent (BOLD) signals have been suggested as correlating with quantities derived from reinforcement learning. We first provide unbiased evidence that the raw BOLD signal in these regions corresponds closely to a reward prediction error. We then derive from this signal the learned values of cues that predict rewards of equal mean but different variance and show that these values are indeed modulated by experienced risk. Moreover, a close neurometric-psychometric coupling exists between the fluctuations of the experience-based evaluations of risky options that we measured neurally and the fluctuations in behavioral risk aversion. This suggests that risk sensitivity is integral to human learning, illuminating economic models of choice, neuroscientific models of affective learning, and the workings of the underlying neural mechanisms.

  10. Parallelization of learning problems by artificial neural networks. Application in external radiotherapy

    International Nuclear Information System (INIS)

    Sauget, M.

    2007-12-01

    This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

  11. On-line learning in radial basis functions networks

    OpenAIRE

    Freeman, Jason; Saad, David

    1997-01-01

    An analytic investigation of the average case learning and generalization properties of Radial Basis Function Networks (RBFs) is presented, utilising on-line gradient descent as the learning rule. The analytic method employed allows both the calculation of generalization error and the examination of the internal dynamics of the network. The generalization error and internal dynamics are then used to examine the role of the learning rate and the specialization of the hidden units, which gives ...

  12. Neural correlates of context-dependent feature conjunction learning in visual search tasks.

    Science.gov (United States)

    Reavis, Eric A; Frank, Sebastian M; Greenlee, Mark W; Tse, Peter U

    2016-06-01

    Many perceptual learning experiments show that repeated exposure to a basic visual feature such as a specific orientation or spatial frequency can modify perception of that feature, and that those perceptual changes are associated with changes in neural tuning early in visual processing. Such perceptual learning effects thus exert a bottom-up influence on subsequent stimulus processing, independent of task-demands or endogenous influences (e.g., volitional attention). However, it is unclear whether such bottom-up changes in perception can occur as more complex stimuli such as conjunctions of visual features are learned. It is not known whether changes in the efficiency with which people learn to process feature conjunctions in a task (e.g., visual search) reflect true bottom-up perceptual learning versus top-down, task-related learning (e.g., learning better control of endogenous attention). Here we show that feature conjunction learning in visual search leads to bottom-up changes in stimulus processing. First, using fMRI, we demonstrate that conjunction learning in visual search has a distinct neural signature: an increase in target-evoked activity relative to distractor-evoked activity (i.e., a relative increase in target salience). Second, we demonstrate that after learning, this neural signature is still evident even when participants passively view learned stimuli while performing an unrelated, attention-demanding task. This suggests that conjunction learning results in altered bottom-up perceptual processing of the learned conjunction stimuli (i.e., a perceptual change independent of the task). We further show that the acquired change in target-evoked activity is contextually dependent on the presence of distractors, suggesting that search array Gestalts are learned. Hum Brain Mapp 37:2319-2330, 2016. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

  13. Neural Correlates of High Performance in Foreign Language Vocabulary Learning

    Science.gov (United States)

    Macedonia, Manuela; Muller, Karsten; Friederici, Angela D.

    2010-01-01

    Learning vocabulary in a foreign language is a laborious task which people perform with varying levels of success. Here, we investigated the neural underpinning of high performance on this task. In a within-subjects paradigm, participants learned 92 vocabulary items under two multimodal conditions: one condition paired novel words with iconic…

  14. Learning characteristics of a space-time neural network as a tether skiprope observer

    Science.gov (United States)

    Lea, Robert N.; Villarreal, James A.; Jani, Yashvant; Copeland, Charles

    1993-01-01

    The Software Technology Laboratory at the Johnson Space Center is testing a Space Time Neural Network (STNN) for observing tether oscillations present during retrieval of a tethered satellite. Proper identification of tether oscillations, known as 'skiprope' motion, is vital to safe retrieval of the tethered satellite. Our studies indicate that STNN has certain learning characteristics that must be understood properly to utilize this type of neural network for the tethered satellite problem. We present our findings on the learning characteristics including a learning rate versus momentum performance table.

  15. The neural basis of testable and non-testable beliefs.

    Directory of Open Access Journals (Sweden)

    Jonathon R Howlett

    Full Text Available Beliefs about the state of the world are an important influence on both normal behavior and psychopathology. However, understanding of the neural basis of belief processing remains incomplete, and several aspects of belief processing have only recently been explored. Specifically, different types of beliefs may involve fundamentally different inferential processes and thus recruit distinct brain regions. Additionally, neural processing of truth and falsity may differ from processing of certainty and uncertainty. The purpose of this study was to investigate the neural underpinnings of assessment of testable and non-testable propositions in terms of truth or falsity and the level of certainty in a belief. Functional magnetic resonance imaging (fMRI was used to study 14 adults while they rated propositions as true or false and also rated the level of certainty in their judgments. Each proposition was classified as testable or non-testable. Testable propositions activated the DLPFC and posterior cingulate cortex, while non-testable statements activated areas including inferior frontal gyrus, superior temporal gyrus, and an anterior region of the superior frontal gyrus. No areas were more active when a proposition was accepted, while the dorsal anterior cingulate was activated when a proposition was rejected. Regardless of whether a proposition was testable or not, certainty that the proposition was true or false activated a common network of regions including the medial prefrontal cortex, caudate, posterior cingulate, and a region of middle temporal gyrus near the temporo-parietal junction. Certainty in the truth or falsity of a non-testable proposition (a strong belief without empirical evidence activated the insula. The results suggest that different brain regions contribute to the assessment of propositions based on the type of content, while a common network may mediate the influence of beliefs on motivation and behavior based on the level of

  16. Neural Basis of Limb Ownership in Individuals with Body Integrity Identity Disorder

    OpenAIRE

    van Dijk, Milenna T.; van Wingen, Guido A.; van Lammeren, Anouk; Blom, Rianne M.; de Kwaasteniet, Bart P.; Scholte, H. Steven; Denys, Damiaan

    2013-01-01

    Our body feels like it is ours. However, individuals with body integrity identity disorder (BIID) lack this feeling of ownership for distinct limbs and desire amputation of perfectly healthy body parts. This extremely rare condition provides us with an opportunity to study the neural basis underlying the feeling of limb ownership, since these individuals have a feeling of disownership for a limb in the absence of apparent brain damage. Here we directly compared brain activation between limbs ...

  17. Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models

    Science.gov (United States)

    Mills, Kyle; Tamblyn, Isaac

    2018-03-01

    We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4 ×4 Ising model. Using its success at this task, we motivate the study of the larger 8 ×8 Ising model, showing that the deep neural network can learn the nearest-neighbor Ising Hamiltonian after only seeing a vanishingly small fraction of configuration space. Additionally, we show that the neural network has learned both the energy and magnetization operators with sufficient accuracy to replicate the low-temperature Ising phase transition. We then demonstrate the ability of the neural network to learn other spin models, teaching the convolutional deep neural network to accurately predict the long-range interaction of a screened Coulomb Hamiltonian, a sinusoidally attenuated screened Coulomb Hamiltonian, and a modified Potts model Hamiltonian. In the case of the long-range interaction, we demonstrate the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method. Furthermore, in the case of the long-range interaction, the benefits of the neural network become apparent; it is able to make predictions with a high degree of accuracy, and do so 1600 times faster than a CUDA-optimized exact calculation. Additionally, we demonstrate how the neural network succeeds at these tasks by looking at the weights learned in a simplified demonstration.

  18. Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning.

    Science.gov (United States)

    Xu, Tao; Xiao, Na; Zhai, Xiaolong; Kwan Chan, Pak; Tin, Chung

    2018-02-01

    Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.

  19. The shared neural basis of music and language.

    Science.gov (United States)

    Yu, Mengxia; Xu, Miao; Li, Xueting; Chen, Zhencai; Song, Yiying; Liu, Jia

    2017-08-15

    Human musical ability is proposed to play a key phylogenetical role in the evolution of language, and the similarity of hierarchical structure in music and language has led to considerable speculation about their shared mechanisms. While behavioral and electrophysioglocial studies have revealed associations between music and linguistic abilities, results from functional magnetic resonance imaging (fMRI) studies on their relations are contradictory, possibly because these studies usually treat music or language as single entities without breaking down to their components. Here, we examined the relations between different components of music (i.e., melodic and rhythmic analysis) and language (i.e., semantic and phonological processing) using both behavioral tests and resting-state fMRI. Behaviorally, we found that individuals with music training experiences were better at semantic processing, but not at phonological processing, than those without training. Further correlation analyses showed that semantic processing of language was related to melodic, but not rhythmic, analysis of music. Neurally, we found that performances in both semantic processing and melodic analysis were correlated with spontaneous brain activities in the bilateral precentral gyrus (PCG) and superior temporal plane at the regional level, and with the resting-state functional connectivity of the left PCG with the left supramarginal gyrus and left superior temporal gyrus at the network level. Together, our study revealed the shared spontaneous neural basis of music and language based on the behavioral link between melodic analysis and semantic processing, which possibly relied on a common mechanism of automatic auditory-motor integration. Copyright © 2017 IBRO. Published by Elsevier Ltd. All rights reserved.

  20. Opponent appetitive-aversive neural processes underlie predictive learning of pain relief.

    Science.gov (United States)

    Seymour, Ben; O'Doherty, John P; Koltzenburg, Martin; Wiech, Katja; Frackowiak, Richard; Friston, Karl; Dolan, Raymond

    2005-09-01

    Termination of a painful or unpleasant event can be rewarding. However, whether the brain treats relief in a similar way as it treats natural reward is unclear, and the neural processes that underlie its representation as a motivational goal remain poorly understood. We used fMRI (functional magnetic resonance imaging) to investigate how humans learn to generate expectations of pain relief. Using a pavlovian conditioning procedure, we show that subjects experiencing prolonged experimentally induced pain can be conditioned to predict pain relief. This proceeds in a manner consistent with contemporary reward-learning theory (average reward/loss reinforcement learning), reflected by neural activity in the amygdala and midbrain. Furthermore, these reward-like learning signals are mirrored by opposite aversion-like signals in lateral orbitofrontal cortex and anterior cingulate cortex. This dual coding has parallels to 'opponent process' theories in psychology and promotes a formal account of prediction and expectation during pain.

  1. Deep learning with convolutional neural network in radiology.

    Science.gov (United States)

    Yasaka, Koichiro; Akai, Hiroyuki; Kunimatsu, Akira; Kiryu, Shigeru; Abe, Osamu

    2018-04-01

    Deep learning with a convolutional neural network (CNN) is gaining attention recently for its high performance in image recognition. Images themselves can be utilized in a learning process with this technique, and feature extraction in advance of the learning process is not required. Important features can be automatically learned. Thanks to the development of hardware and software in addition to techniques regarding deep learning, application of this technique to radiological images for predicting clinically useful information, such as the detection and the evaluation of lesions, etc., are beginning to be investigated. This article illustrates basic technical knowledge regarding deep learning with CNNs along the actual course (collecting data, implementing CNNs, and training and testing phases). Pitfalls regarding this technique and how to manage them are also illustrated. We also described some advanced topics of deep learning, results of recent clinical studies, and the future directions of clinical application of deep learning techniques.

  2. Variability of Neuronal Responses: Types and Functional Significance in Neuroplasticity and Neural Darwinism.

    Science.gov (United States)

    Chervyakov, Alexander V; Sinitsyn, Dmitry O; Piradov, Michael A

    2016-01-01

    HIGHLIGHTS We suggest classifying variability of neuronal responses as follows: false (associated with a lack of knowledge about the influential factors), "genuine harmful" (noise), "genuine neutral" (synonyms, repeats), and "genuine useful" (the basis of neuroplasticity and learning).The genuine neutral variability is considered in terms of the phenomenon of degeneracy.Of particular importance is the genuine useful variability that is considered as a potential basis for neuroplasticity and learning. This type of variability is considered in terms of the neural Darwinism theory. In many cases, neural signals detected under the same external experimental conditions significantly change from trial to trial. The variability phenomenon, which complicates extraction of reproducible results and is ignored in many studies by averaging, has attracted attention of researchers in recent years. In this paper, we classify possible types of variability based on its functional significance and describe features of each type. We describe the key adaptive significance of variability at the neural network level and the degeneracy phenomenon that may be important for learning processes in connection with the principle of neuronal group selection.

  3. Learning speaker-specific characteristics with a deep neural architecture.

    Science.gov (United States)

    Chen, Ke; Salman, Ahmad

    2011-11-01

    Speech signals convey various yet mixed information ranging from linguistic to speaker-specific information. However, most of acoustic representations characterize all different kinds of information as whole, which could hinder either a speech or a speaker recognition (SR) system from producing a better performance. In this paper, we propose a novel deep neural architecture (DNA) especially for learning speaker-specific characteristics from mel-frequency cepstral coefficients, an acoustic representation commonly used in both speech recognition and SR, which results in a speaker-specific overcomplete representation. In order to learn intrinsic speaker-specific characteristics, we come up with an objective function consisting of contrastive losses in terms of speaker similarity/dissimilarity and data reconstruction losses used as regularization to normalize the interference of non-speaker-related information. Moreover, we employ a hybrid learning strategy for learning parameters of the deep neural networks: i.e., local yet greedy layerwise unsupervised pretraining for initialization and global supervised learning for the ultimate discriminative goal. With four Linguistic Data Consortium (LDC) benchmarks and two non-English corpora, we demonstrate that our overcomplete representation is robust in characterizing various speakers, no matter whether their utterances have been used in training our DNA, and highly insensitive to text and languages spoken. Extensive comparative studies suggest that our approach yields favorite results in speaker verification and segmentation. Finally, we discuss several issues concerning our proposed approach.

  4. Bayesian and neural networks for preliminary ship design

    DEFF Research Database (Denmark)

    Clausen, H. B.; Lützen, Marie; Friis-Hansen, Andreas

    2001-01-01

    000 ships is acquired and various methods for derivation of empirical relations are employed. A regression analysis is carried out to fit functions to the data. Further, the data are used to learn Bayesian and neural networks to encode the relations between the characteristics. On the basis...

  5. Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning

    Science.gov (United States)

    Xu, Tao; Xiao, Na; Zhai, Xiaolong; Chan, Pak Kwan; Tin, Chung

    2018-02-01

    Objective. Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). Approach. The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. Main results. This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. Significance. This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.

  6. Learning Mixtures of Truncated Basis Functions from Data

    DEFF Research Database (Denmark)

    Langseth, Helge; Nielsen, Thomas Dyhre; Pérez-Bernabé, Inmaculada

    2014-01-01

    In this paper we investigate methods for learning hybrid Bayesian networks from data. First we utilize a kernel density estimate of the data in order to translate the data into a mixture of truncated basis functions (MoTBF) representation using a convex optimization technique. When utilizing a ke...... propose an alternative learning method that relies on the cumulative distribution function of the data. Empirical results demonstrate the usefulness of the approaches: Even though the methods produce estimators that are slightly poorer than the state of the art (in terms of log......In this paper we investigate methods for learning hybrid Bayesian networks from data. First we utilize a kernel density estimate of the data in order to translate the data into a mixture of truncated basis functions (MoTBF) representation using a convex optimization technique. When utilizing......-likelihood), they are significantly faster, and therefore indicate that the MoTBF framework can be used for inference and learning in reasonably sized domains. Furthermore, we show how a particular sub- class of MoTBF potentials (learnable by the proposed methods) can be exploited to significantly reduce complexity during inference....

  7. Adaptive Learning Rule for Hardware-based Deep Neural Networks Using Electronic Synapse Devices

    OpenAIRE

    Lim, Suhwan; Bae, Jong-Ho; Eum, Jai-Ho; Lee, Sungtae; Kim, Chul-Heung; Kwon, Dongseok; Park, Byung-Gook; Lee, Jong-Ho

    2017-01-01

    In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance characteristics. This adaptive learning rule, which enables forward, backward propagation, as well as weight updates in hardware, is helpful during the implementation of power-efficient and high-speed deep neural networks. In simulations using a three-layer perceptron net...

  8. The neural basis of the bystander effect--the influence of group size on neural activity when witnessing an emergency.

    Science.gov (United States)

    Hortensius, Ruud; de Gelder, Beatrice

    2014-06-01

    Naturalistic observation and experimental studies in humans and other primates show that observing an individual in need automatically triggers helping behavior. The aim of the present study is to clarify the neurofunctional basis of social influences on individual helping behavior. We investigate whether when participants witness an emergency, while performing an unrelated color-naming task in an fMRI scanner, the number of bystanders present at the emergency influences neural activity in regions related to action preparation. The results show a decrease in activity with the increase in group size in the left pre- and postcentral gyri and left medial frontal gyrus. In contrast, regions related to visual perception and attention show an increase in activity. These results demonstrate the neural mechanisms of social influence on automatic action preparation that is at the core of helping behavior when witnessing an emergency. Copyright © 2014 Elsevier Inc. All rights reserved.

  9. Evolvable synthetic neural system

    Science.gov (United States)

    Curtis, Steven A. (Inventor)

    2009-01-01

    An evolvable synthetic neural system includes an evolvable neural interface operably coupled to at least one neural basis function. Each neural basis function includes an evolvable neural interface operably coupled to a heuristic neural system to perform high-level functions and an autonomic neural system to perform low-level functions. In some embodiments, the evolvable synthetic neural system is operably coupled to one or more evolvable synthetic neural systems in a hierarchy.

  10. Learning in Neural Networks: VLSI Implementation Strategies

    Science.gov (United States)

    Duong, Tuan Anh

    1995-01-01

    Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.

  11. Image Classification, Deep Learning and Convolutional Neural Networks : A Comparative Study of Machine Learning Frameworks

    OpenAIRE

    Airola, Rasmus; Hager, Kristoffer

    2017-01-01

    The use of machine learning and specifically neural networks is a growing trend in software development, and has grown immensely in the last couple of years in the light of an increasing need to handle big data and large information flows. Machine learning has a broad area of application, such as human-computer interaction, predicting stock prices, real-time translation, and self driving vehicles. Large companies such as Microsoft and Google have already implemented machine learning in some o...

  12. Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory

    DEFF Research Database (Denmark)

    Lüders, Benno; Schläger, Mikkel; Korach, Aleksandra

    2017-01-01

    it easier to find unused memory location and therefor facilitates the evolution of continual learning networks. Our results suggest that augmenting evolving networks with an external memory component is not only a viable mechanism for adaptive behaviors in neuroevolution but also allows these networks...... a new task is learned. This paper takes a step in overcoming this limitation by building on the recently proposed Evolving Neural Turing Machine (ENTM) approach. In the ENTM, neural networks are augmented with an external memory component that they can write to and read from, which allows them to store...... associations quickly and over long periods of time. The results in this paper demonstrate that the ENTM is able to perform one-shot learning in reinforcement learning tasks without catastrophic forgetting of previously stored associations. Additionally, we introduce a new ENTM default jump mechanism that makes...

  13. Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks.

    Science.gov (United States)

    Walter, Florian; Röhrbein, Florian; Knoll, Alois

    2015-12-01

    The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks. Copyright © 2015 Elsevier Ltd. All rights reserved.

  14. The Neural Basis of Changing Social Norms through Persuasion.

    Science.gov (United States)

    Yomogida, Yukihito; Matsumoto, Madoka; Aoki, Ryuta; Sugiura, Ayaka; Phillips, Adam N; Matsumoto, Kenji

    2017-11-24

    Social norms regulate behavior, and changes in norms have a great impact on society. In most modern societies, norms change through interpersonal communication and persuasive messages found in media. Here, we examined the neural basis of persuasion-induced changes in attitude toward and away from norms using fMRI. We measured brain activity while human participants were exposed to persuasive messages directed toward specific norms. Persuasion directed toward social norms specifically activated a set of brain regions including temporal poles, temporo-parietal junction, and medial prefrontal cortex. Beyond these regions, when successful, persuasion away from an accepted norm specifically recruited the left middle temporal and supramarginal gyri. Furthermore, in combination with data from a separate attitude-rating task, we found that left supramarginal gyrus activity represented participant attitude toward norms and tracked the persuasion-induced attitude changes that were away from agreement.

  15. Comparative Application of Radial Basis Function and Multilayer Perceptron Neural Networks to Predict Traffic Noise Pollution in Tehran Roads

    Directory of Open Access Journals (Sweden)

    Ali Mansourkhaki

    2018-01-01

    Full Text Available Noise pollution is a level of environmental noise which is considered as a disturbing and annoying phenomenon for human and wildlife. It is one of the environmental problems which has not been considered as harmful as the air and water pollution. Compared with other pollutants, the attempts to control noise pollution have largely been unsuccessful due to the inadequate knowledge of its effectson humans, as well as the lack of clear standards in previous years. However, with an increase of traveling vehicles, the adverse impact of increasing noise pollution on human health is progressively emerging. Hence, investigators all around the world are seeking to findnew approaches for predicting, estimating and controlling this problem and various models have been proposed. Recently, developing learning algorithms such as neural network has led to novel solutions for this challenge. These algorithms provide intelligent performance based on the situations and input data, enabling to obtain the best result for predicting noise level. In this study, two types of neural networks – multilayer perceptron and radial basis function – were developed for predicting equivalent continuous sound level (LA eq by measuring the traffivolume, average speed and percentage of heavy vehicles in some roads in west and northwest of Tehran. Then, their prediction results were compared based on the coefficienof determination (R 2 and the Mean Squared Error (MSE. Although both networks are of high accuracy in prediction of noise level, multilayer perceptron neural network based on selected criteria had a better performance.

  16. Changing pulse-shape basis for molecular learning control

    International Nuclear Information System (INIS)

    Cardoza, David; Langhojer, Florian; Trallero-Herrero, Carlos; Weinacht, Thomas; Monti, Oliver L.A.

    2004-01-01

    We interpret the results of a molecular fragmentation learning control experiment. We show that in the case of a system where control can be related to the structure of the optimal pulse matching the vibrational dynamics of the molecule, a simple change of pulse-shape basis in which the learning algorithm performs the search can reduce the dimensionality of the search space to one or two degrees of freedom

  17. METHODS OF TEXT INFORMATION CLASSIFICATION ON THE BASIS OF ARTIFICIAL NEURAL AND SEMANTIC NETWORKS

    Directory of Open Access Journals (Sweden)

    L. V. Serebryanaya

    2016-01-01

    Full Text Available The article covers the use of perseptron, Hopfild artificial neural network and semantic network for classification of text information. Network training algorithms are studied. An algorithm of inverse mistake spreading for perceptron network and convergence algorithm for Hopfild network are implemented. On the basis of the offered models and algorithms automatic text classification software is developed and its operation results are evaluated.

  18. Biologically-inspired On-chip Learning in Pulsed Neural Networks

    DEFF Research Database (Denmark)

    Lehmann, Torsten; Woodburn, Robin

    1999-01-01

    Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the "biologically-inspired" approach......, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve simple classical-conditioning tasks, We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue...

  19. Learning and Generalisation in Neural Networks with Local Preprocessing

    OpenAIRE

    Kutsia, Merab

    2007-01-01

    We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the net...

  20. Explaining neural signals in human visual cortex with an associative learning model.

    Science.gov (United States)

    Jiang, Jiefeng; Schmajuk, Nestor; Egner, Tobias

    2012-08-01

    "Predictive coding" models posit a key role for associative learning in visual cognition, viewing perceptual inference as a process of matching (learned) top-down predictions (or expectations) against bottom-up sensory evidence. At the neural level, these models propose that each region along the visual processing hierarchy entails one set of processing units encoding predictions of bottom-up input, and another set computing mismatches (prediction error or surprise) between predictions and evidence. This contrasts with traditional views of visual neurons operating purely as bottom-up feature detectors. In support of the predictive coding hypothesis, a recent human neuroimaging study (Egner, Monti, & Summerfield, 2010) showed that neural population responses to expected and unexpected face and house stimuli in the "fusiform face area" (FFA) could be well-described as a summation of hypothetical face-expectation and -surprise signals, but not by feature detector responses. Here, we used computer simulations to test whether these imaging data could be formally explained within the broader framework of a mathematical neural network model of associative learning (Schmajuk, Gray, & Lam, 1996). Results show that FFA responses could be fit very closely by model variables coding for conditional predictions (and their violations) of stimuli that unconditionally activate the FFA. These data document that neural population signals in the ventral visual stream that deviate from classic feature detection responses can formally be explained by associative prediction and surprise signals.

  1. Using machine learning, neural networks and statistics to predict bankruptcy

    NARCIS (Netherlands)

    Pompe, P.P.M.; Feelders, A.J.; Feelders, A.J.

    1997-01-01

    Recent literature strongly suggests that machine learning approaches to classification outperform "classical" statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees, and neural networks in predicting corporate bankruptcy. Linear

  2. A recurrent neural network with ever changing synapses

    NARCIS (Netherlands)

    Heerema, M.; van Leeuwen, W.A.

    2000-01-01

    A recurrent neural network with noisy input is studied analytically, on the basis of a Discrete Time Master Equation. The latter is derived from a biologically realizable learning rule for the weights of the connections. In a numerical study it is found that the fixed points of the dynamics of the

  3. Media Multitasking and Cognitive, Psychological, Neural, and Learning Differences.

    Science.gov (United States)

    Uncapher, Melina R; Lin, Lin; Rosen, Larry D; Kirkorian, Heather L; Baron, Naomi S; Bailey, Kira; Cantor, Joanne; Strayer, David L; Parsons, Thomas D; Wagner, Anthony D

    2017-11-01

    American youth spend more time with media than any other waking activity: an average of 7.5 hours per day, every day. On average, 29% of that time is spent juggling multiple media streams simultaneously (ie, media multitasking). This phenomenon is not limited to American youth but is paralleled across the globe. Given that a large number of media multitaskers (MMTs) are children and young adults whose brains are still developing, there is great urgency to understand the neurocognitive profiles of MMTs. It is critical to understand the relation between the relevant cognitive domains and underlying neural structure and function. Of equal importance is understanding the types of information processing that are necessary in 21st century learning environments. The present review surveys the growing body of evidence demonstrating that heavy MMTs show differences in cognition (eg, poorer memory), psychosocial behavior (eg, increased impulsivity), and neural structure (eg, reduced volume in anterior cingulate cortex). Furthermore, research indicates that multitasking with media during learning (in class or at home) can negatively affect academic outcomes. Until the direction of causality is understood (whether media multitasking causes such behavioral and neural differences or whether individuals with such differences tend to multitask with media more often), the data suggest that engagement with concurrent media streams should be thoughtfully considered. Findings from such research promise to inform policy and practice on an increasingly urgent societal issue while significantly advancing our understanding of the intersections between cognitive, psychosocial, neural, and academic factors. Copyright © 2017 by the American Academy of Pediatrics.

  4. Investigating the Influence of Biological Sex on the Behavioral and Neural Basis of Face Recognition.

    Science.gov (United States)

    Scherf, K Suzanne; Elbich, Daniel B; Motta-Mena, Natalie V

    2017-01-01

    There is interest in understanding the influence of biological factors, like sex, on the organization of brain function. We investigated the influence of biological sex on the behavioral and neural basis of face recognition in healthy, young adults. In behavior, there were no sex differences on the male Cambridge Face Memory Test (CFMT)+ or the female CFMT+ (that we created) and no own-gender bias (OGB) in either group. We evaluated the functional topography of ventral stream organization by measuring the magnitude and functional neural size of 16 individually defined face-, two object-, and two place-related regions bilaterally. There were no sex differences in any of these measures of neural function in any of the regions of interest (ROIs) or in group level comparisons. These findings reveal that men and women have similar category-selective topographic organization in the ventral visual pathway. Next, in a separate task, we measured activation within the 16 face-processing ROIs specifically during recognition of target male and female faces. There were no sex differences in the magnitude of the neural responses in any face-processing region. Furthermore, there was no OGB in the neural responses of either the male or female participants. Our findings suggest that face recognition behavior, including the OGB, is not inherently sexually dimorphic. Face recognition is an essential skill for navigating human social interactions, which is reflected equally in the behavior and neural architecture of men and women.

  5. Investigating the Influence of Biological Sex on the Behavioral and Neural Basis of Face Recognition

    Science.gov (United States)

    2017-01-01

    Abstract There is interest in understanding the influence of biological factors, like sex, on the organization of brain function. We investigated the influence of biological sex on the behavioral and neural basis of face recognition in healthy, young adults. In behavior, there were no sex differences on the male Cambridge Face Memory Test (CFMT)+ or the female CFMT+ (that we created) and no own-gender bias (OGB) in either group. We evaluated the functional topography of ventral stream organization by measuring the magnitude and functional neural size of 16 individually defined face-, two object-, and two place-related regions bilaterally. There were no sex differences in any of these measures of neural function in any of the regions of interest (ROIs) or in group level comparisons. These findings reveal that men and women have similar category-selective topographic organization in the ventral visual pathway. Next, in a separate task, we measured activation within the 16 face-processing ROIs specifically during recognition of target male and female faces. There were no sex differences in the magnitude of the neural responses in any face-processing region. Furthermore, there was no OGB in the neural responses of either the male or female participants. Our findings suggest that face recognition behavior, including the OGB, is not inherently sexually dimorphic. Face recognition is an essential skill for navigating human social interactions, which is reflected equally in the behavior and neural architecture of men and women. PMID:28497111

  6. A neural learning classifier system with self-adaptive constructivism for mobile robot control.

    Science.gov (United States)

    Hurst, Jacob; Bull, Larry

    2006-01-01

    For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform.

  7. Competitive Learning Neural Network Ensemble Weighted by Predicted Performance

    Science.gov (United States)

    Ye, Qiang

    2010-01-01

    Ensemble approaches have been shown to enhance classification by combining the outputs from a set of voting classifiers. Diversity in error patterns among base classifiers promotes ensemble performance. Multi-task learning is an important characteristic for Neural Network classifiers. Introducing a secondary output unit that receives different…

  8. Breast Cancer Diagnosis using Artificial Neural Networks with Extreme Learning Techniques

    OpenAIRE

    Chandra Prasetyo Utomo; Aan Kardiana; Rika Yuliwulandari

    2014-01-01

    Breast cancer is the second cause of dead among women. Early detection followed by appropriate cancer treatment can reduce the deadly risk. Medical professionals can make mistakes while identifying a disease. The help of technology such as data mining and machine learning can substantially improve the diagnosis accuracy. Artificial Neural Networks (ANN) has been widely used in intelligent breast cancer diagnosis. However, the standard Gradient-Based Back Propagation Artificial Neural Networks...

  9. Self-learning Monte Carlo with deep neural networks

    Science.gov (United States)

    Shen, Huitao; Liu, Junwei; Fu, Liang

    2018-05-01

    The self-learning Monte Carlo (SLMC) method is a general algorithm to speedup MC simulations. Its efficiency has been demonstrated in various systems by introducing an effective model to propose global moves in the configuration space. In this paper, we show that deep neural networks can be naturally incorporated into SLMC, and without any prior knowledge can learn the original model accurately and efficiently. Demonstrated in quantum impurity models, we reduce the complexity for a local update from O (β2) in Hirsch-Fye algorithm to O (β lnβ ) , which is a significant speedup especially for systems at low temperatures.

  10. Fundamentals of computational intelligence neural networks, fuzzy systems, and evolutionary computation

    CERN Document Server

    Keller, James M; Fogel, David B

    2016-01-01

    This book covers the three fundamental topics that form the basis of computational intelligence: neural networks, fuzzy systems, and evolutionary computation. The text focuses on inspiration, design, theory, and practical aspects of implementing procedures to solve real-world problems. While other books in the three fields that comprise computational intelligence are written by specialists in one discipline, this book is co-written by current former Editor-in-Chief of IEEE Transactions on Neural Networks and Learning Systems, a former Editor-in-Chief of IEEE Transactions on Fuzzy Systems, and the founding Editor-in-Chief of IEEE Transactions on Evolutionary Computation. The coverage across the three topics is both uniform and consistent in style and notation. Discusses single-layer and multilayer neural networks, radial-basi function networks, and recurrent neural networks Covers fuzzy set theory, fuzzy relations, fuzzy logic interference, fuzzy clustering and classification, fuzzy measures and fuzz...

  11. Minimal-Learning-Parameter Technique Based Adaptive Neural Sliding Mode Control of MEMS Gyroscope

    Directory of Open Access Journals (Sweden)

    Bin Xu

    2017-01-01

    Full Text Available This paper investigates an adaptive neural sliding mode controller for MEMS gyroscopes with minimal-learning-parameter technique. Considering the system uncertainty in dynamics, neural network is employed for approximation. Minimal-learning-parameter technique is constructed to decrease the number of update parameters, and in this way the computation burden is greatly reduced. Sliding mode control is designed to cancel the effect of time-varying disturbance. The closed-loop stability analysis is established via Lyapunov approach. Simulation results are presented to demonstrate the effectiveness of the method.

  12. Learning to Recognize Actions From Limited Training Examples Using a Recurrent Spiking Neural Model

    Science.gov (United States)

    Panda, Priyadarshini; Srinivasa, Narayan

    2018-01-01

    A fundamental challenge in machine learning today is to build a model that can learn from few examples. Here, we describe a reservoir based spiking neural model for learning to recognize actions with a limited number of labeled videos. First, we propose a novel encoding, inspired by how microsaccades influence visual perception, to extract spike information from raw video data while preserving the temporal correlation across different frames. Using this encoding, we show that the reservoir generalizes its rich dynamical activity toward signature action/movements enabling it to learn from few training examples. We evaluate our approach on the UCF-101 dataset. Our experiments demonstrate that our proposed reservoir achieves 81.3/87% Top-1/Top-5 accuracy, respectively, on the 101-class data while requiring just 8 video examples per class for training. Our results establish a new benchmark for action recognition from limited video examples for spiking neural models while yielding competitive accuracy with respect to state-of-the-art non-spiking neural models. PMID:29551962

  13. Criticality meets learning: Criticality signatures in a self-organizing recurrent neural network.

    Science.gov (United States)

    Del Papa, Bruno; Priesemann, Viola; Triesch, Jochen

    2017-01-01

    Many experiments have suggested that the brain operates close to a critical state, based on signatures of criticality such as power-law distributed neuronal avalanches. In neural network models, criticality is a dynamical state that maximizes information processing capacities, e.g. sensitivity to input, dynamical range and storage capacity, which makes it a favorable candidate state for brain function. Although models that self-organize towards a critical state have been proposed, the relation between criticality signatures and learning is still unclear. Here, we investigate signatures of criticality in a self-organizing recurrent neural network (SORN). Investigating criticality in the SORN is of particular interest because it has not been developed to show criticality. Instead, the SORN has been shown to exhibit spatio-temporal pattern learning through a combination of neural plasticity mechanisms and it reproduces a number of biological findings on neural variability and the statistics and fluctuations of synaptic efficacies. We show that, after a transient, the SORN spontaneously self-organizes into a dynamical state that shows criticality signatures comparable to those found in experiments. The plasticity mechanisms are necessary to attain that dynamical state, but not to maintain it. Furthermore, onset of external input transiently changes the slope of the avalanche distributions - matching recent experimental findings. Interestingly, the membrane noise level necessary for the occurrence of the criticality signatures reduces the model's performance in simple learning tasks. Overall, our work shows that the biologically inspired plasticity and homeostasis mechanisms responsible for the SORN's spatio-temporal learning abilities can give rise to criticality signatures in its activity when driven by random input, but these break down under the structured input of short repeating sequences.

  14. Incidental regulation of attraction: The neural basis of the derogation of attractive alternatives in romantic relationships

    Science.gov (United States)

    Meyer, Meghan L.; Berkman, Elliot T.; Karremans, Johan C.; Lieberman, Matthew D.

    2011-01-01

    Although a great deal of research addresses the neural basis of deliberate and intentional emotion-regulation strategies, less attention has been paid to the neural mechanisms involved in implicit forms of emotion regulation. Behavioural research suggests that romantically involved participants implicitly derogate the attractiveness of alternative partners, and the present study sought to examine the neural basis of this effect. Romantically committed participants in the present study were scanned with functional magnetic resonance imaging (fMRI) while indicating whether they would consider each of a series of attractive (or unattractive) opposite-sex others as a hypothetical dating partner both while under cognitive load and no cognitive load. Successful derogation of attractive others during the no cognitive load compared to the cognitive load trials corresponded with increased activation in the ventrolateral prefrontal cortex (VLPFC) and posterior dorsomedial prefrontal cortex (pDMPFC), and decreased activation in the ventral striatum, a pattern similar to those reported in deliberate emotion-regulation studies. Activation in the VLPFC and pDMPFC was not significant in the cognitive load condition, indicating that while the derogation effect may be implicit, it nonetheless requires cognitive resources. Additionally, activation in the right VLPFC correlated with participants’ level of relationship investment. These findings suggest that the RVLPFC may play a particularly important role in implicitly regulating the emotions that threaten the stability of a romantic relationship. PMID:21432689

  15. Extent and neural basis of semantic memory impairment in mild cognitive impairment.

    Science.gov (United States)

    Barbeau, Emmanuel J; Didic, Mira; Joubert, Sven; Guedj, Eric; Koric, Lejla; Felician, Olivier; Ranjeva, Jean-Philippe; Cozzone, Patrick; Ceccaldi, Mathieu

    2012-01-01

    An increasing number of studies indicate that semantic memory is impaired in mild cognitive impairment (MCI). However, the extent and the neural basis of this impairment remain unknown. The aim of the present study was: 1) to evaluate whether all or only a subset of semantic domains are impaired in MCI patients; and 2) to assess the neural substrate of the semantic impairment in MCI patients using voxel-based analysis of MR grey matter density and SPECT perfusion. 29 predominantly amnestic MCI patients and 29 matched control subjects participated in this study. All subjects underwent a full neuropsychological assessment, along with a battery of five tests evaluating different domains of semantic memory. A semantic memory composite Z-score was established on the basis of this battery and was correlated with MRI grey matter density and SPECT perfusion measures. MCI patients were found to have significantly impaired performance across all semantic tasks, in addition to their anterograde memory deficit. Moreover, no temporal gradient was found for famous faces or famous public events and knowledge for the most remote decades was also impaired. Neuroimaging analyses revealed correlations between semantic knowledge and perirhinal/entorhinal areas as well as the anterior hippocampus. Therefore, the deficits in the realm of semantic memory in patients with MCI is more widespread than previously thought and related to dysfunction of brain areas beyond the limbic-diencephalic system involved in episodic memory. The severity of the semantic impairment may indicate a decline of semantic memory that began many years before the patients first consulted.

  16. Differential theory of learning for efficient neural network pattern recognition

    Science.gov (United States)

    Hampshire, John B., II; Vijaya Kumar, Bhagavatula

    1993-09-01

    We describe a new theory of differential learning by which a broad family of pattern classifiers (including many well-known neural network paradigms) can learn stochastic concepts efficiently. We describe the relationship between a classifier's ability to generate well to unseen test examples and the efficiency of the strategy by which it learns. We list a series of proofs that differential learning is efficient in its information and computational resource requirements, whereas traditional probabilistic learning strategies are not. The proofs are illustrated by a simple example that lends itself to closed-form analysis. We conclude with an optical character recognition task for which three different types of differentially generated classifiers generalize significantly better than their probabilistically generated counterparts.

  17. Outsmarting neural networks: an alternative paradigm for machine learning

    Energy Technology Data Exchange (ETDEWEB)

    Protopopescu, V.; Rao, N.S.V.

    1996-10-01

    We address three problems in machine learning, namely: (i) function learning, (ii) regression estimation, and (iii) sensor fusion, in the Probably and Approximately Correct (PAC) framework. We show that, under certain conditions, one can reduce the three problems above to the regression estimation. The latter is usually tackled with artificial neural networks (ANNs) that satisfy the PAC criteria, but have high computational complexity. We propose several computationally efficient PAC alternatives to ANNs to solve the regression estimation. Thereby we also provide efficient PAC solutions to the function learning and sensor fusion problems. The approach is based on cross-fertilizing concepts and methods from statistical estimation, nonlinear algorithms, and the theory of computational complexity, and is designed as part of a new, coherent paradigm for machine learning.

  18. Design and FPGA-implementation of multilayer neural networks with on-chip learning

    International Nuclear Information System (INIS)

    Haggag, S.S.M.Y

    2008-01-01

    Artificial Neural Networks (ANN) is used in many applications in the industry because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. For example identifying the orange and apple in the sorting machine with neural network is easier than using image processing techniques to do the same thing. There are different software for designing, training, and testing the ANN, but in order to use the ANN in the industry, it should be implemented on hardware outside the computer. Neural networks are artificial systems inspired on the brain's cognitive behavior, which can learn tasks with some degree of complexity, such as signal processing, diagnosis, robotics, image processing, and pattern recognition. Many applications demand a high computing power and the traditional software implementation are not sufficient.This thesis presents design and FPGA implementation of Multilayer Neural Networks with On-chip learning in re-configurable hardware. Hardware implementation of neural network algorithm is very interesting due their high performance and they can easily be made parallel. The architecture proposed herein takes advantage of distinct data paths for the forward and backward propagation stages and a pipelined adaptation of the on- line backpropagation algorithm to significantly improve the performance of the learning phase. The architecture is easily scalable and able to cope with arbitrary network sizes with the same hardware. The implementation is targeted diagnosis of the Research Reactor accidents to avoid the risk of occurrence of a nuclear accident. The proposed designed circuits are implemented using Xilinx FPGA Chip XC40150xv and occupied 73% of Chip CLBs. It achieved 10.8 μs to take decision in the forward propagation compared with current software implemented of RPS which take 24 ms. The results show that the proposed architecture leads to significant speed up comparing to high end software solutions. On

  19. Neural Basis of Visual Distraction

    Science.gov (United States)

    Kim, So-Yeon; Hopfinger, Joseph B.

    2010-01-01

    The ability to maintain focus and avoid distraction by goal-irrelevant stimuli is critical for performing many tasks and may be a key deficit in attention-related problems. Recent studies have demonstrated that irrelevant stimuli that are consciously perceived may be filtered out on a neural level and not cause the distraction triggered by…

  20. Neural correlates of face gender discrimination learning.

    Science.gov (United States)

    Su, Junzhu; Tan, Qingleng; Fang, Fang

    2013-04-01

    Using combined psychophysics and event-related potentials (ERPs), we investigated the effect of perceptual learning on face gender discrimination and probe the neural correlates of the learning effect. Human subjects were trained to perform a gender discrimination task with male or female faces. Before and after training, they were tested with the trained faces and other faces with the same and opposite genders. ERPs responding to these faces were recorded. Psychophysical results showed that training significantly improved subjects' discrimination performance and the improvement was specific to the trained gender, as well as to the trained identities. The training effect indicates that learning occurs at two levels-the category level (gender) and the exemplar level (identity). ERP analyses showed that the gender and identity learning was associated with the N170 latency reduction at the left occipital-temporal area and the N170 amplitude reduction at the right occipital-temporal area, respectively. These findings provide evidence for the facilitation model and the sharpening model on neuronal plasticity from visual experience, suggesting a faster processing speed and a sparser representation of face induced by perceptual learning.

  1. Automated radial basis function neural network based image classification system for diabetic retinopathy detection in retinal images

    Science.gov (United States)

    Anitha, J.; Vijila, C. Kezi Selva; Hemanth, D. Jude

    2010-02-01

    Diabetic retinopathy (DR) is a chronic eye disease for which early detection is highly essential to avoid any fatal results. Image processing of retinal images emerge as a feasible tool for this early diagnosis. Digital image processing techniques involve image classification which is a significant technique to detect the abnormality in the eye. Various automated classification systems have been developed in the recent years but most of them lack high classification accuracy. Artificial neural networks are the widely preferred artificial intelligence technique since it yields superior results in terms of classification accuracy. In this work, Radial Basis function (RBF) neural network based bi-level classification system is proposed to differentiate abnormal DR Images and normal retinal images. The results are analyzed in terms of classification accuracy, sensitivity and specificity. A comparative analysis is performed with the results of the probabilistic classifier namely Bayesian classifier to show the superior nature of neural classifier. Experimental results show promising results for the neural classifier in terms of the performance measures.

  2. The neural basis of financial risk taking.

    Science.gov (United States)

    Kuhnen, Camelia M; Knutson, Brian

    2005-09-01

    Investors systematically deviate from rationality when making financial decisions, yet the mechanisms responsible for these deviations have not been identified. Using event-related fMRI, we examined whether anticipatory neural activity would predict optimal and suboptimal choices in a financial decision-making task. We characterized two types of deviations from the optimal investment strategy of a rational risk-neutral agent as risk-seeking mistakes and risk-aversion mistakes. Nucleus accumbens activation preceded risky choices as well as risk-seeking mistakes, while anterior insula activation preceded riskless choices as well as risk-aversion mistakes. These findings suggest that distinct neural circuits linked to anticipatory affect promote different types of financial choices and indicate that excessive activation of these circuits may lead to investing mistakes. Thus, consideration of anticipatory neural mechanisms may add predictive power to the rational actor model of economic decision making.

  3. Learning Methods for Radial Basis Functions Networks

    Czech Academy of Sciences Publication Activity Database

    Neruda, Roman; Kudová, Petra

    2005-01-01

    Roč. 21, - (2005), s. 1131-1142 ISSN 0167-739X R&D Projects: GA ČR GP201/03/P163; GA ČR GA201/02/0428 Institutional research plan: CEZ:AV0Z10300504 Keywords : radial basis function networks * hybrid supervised learning * genetic algorithms * benchmarking Subject RIV: BA - General Mathematics Impact factor: 0.555, year: 2005

  4. Patterns recognition of electric brain activity using artificial neural networks

    Science.gov (United States)

    Musatov, V. Yu.; Pchelintseva, S. V.; Runnova, A. E.; Hramov, A. E.

    2017-04-01

    An approach for the recognition of various cognitive processes in the brain activity in the perception of ambiguous images. On the basis of developed theoretical background and the experimental data, we propose a new classification of oscillating patterns in the human EEG by using an artificial neural network approach. After learning of the artificial neural network reliably identified cube recognition processes, for example, left-handed or right-oriented Necker cube with different intensity of their edges, construct an artificial neural network based on Perceptron architecture and demonstrate its effectiveness in the pattern recognition of the EEG in the experimental.

  5. Neural correlates of threat perception: neural equivalence of conspecific and heterospecific mobbing calls is learned.

    Directory of Open Access Journals (Sweden)

    Marc T Avey

    Full Text Available Songbird auditory areas (i.e., CMM and NCM are preferentially activated to playback of conspecific vocalizations relative to heterospecific and arbitrary noise. Here, we asked if the neural response to auditory stimulation is not simply preferential for conspecific vocalizations but also for the information conveyed by the vocalization. Black-capped chickadees use their chick-a-dee mobbing call to recruit conspecifics and other avian species to mob perched predators. Mobbing calls produced in response to smaller, higher-threat predators contain more "D" notes compared to those produced in response to larger, lower-threat predators and thus convey the degree of threat of predators. We specifically asked whether the neural response varies with the degree of threat conveyed by the mobbing calls of chickadees and whether the neural response is the same for actual predator calls that correspond to the degree of threat of the chickadee mobbing calls. Our results demonstrate that, as degree of threat increases in conspecific chickadee mobbing calls, there is a corresponding increase in immediate early gene (IEG expression in telencephalic auditory areas. We also demonstrate that as the degree of threat increases for the heterospecific predator, there is a corresponding increase in IEG expression in the auditory areas. Furthermore, there was no significant difference in the amount IEG expression between conspecific mobbing calls or heterospecific predator calls that were the same degree of threat. In a second experiment, using hand-reared chickadees without predator experience, we found more IEG expression in response to mobbing calls than corresponding predator calls, indicating that degree of threat is learned. Our results demonstrate that degree of threat corresponds to neural activity in the auditory areas and that threat can be conveyed by different species signals and that these signals must be learned.

  6. Neural Correlates of Threat Perception: Neural Equivalence of Conspecific and Heterospecific Mobbing Calls Is Learned

    Science.gov (United States)

    Avey, Marc T.; Hoeschele, Marisa; Moscicki, Michele K.; Bloomfield, Laurie L.; Sturdy, Christopher B.

    2011-01-01

    Songbird auditory areas (i.e., CMM and NCM) are preferentially activated to playback of conspecific vocalizations relative to heterospecific and arbitrary noise [1]–[2]. Here, we asked if the neural response to auditory stimulation is not simply preferential for conspecific vocalizations but also for the information conveyed by the vocalization. Black-capped chickadees use their chick-a-dee mobbing call to recruit conspecifics and other avian species to mob perched predators [3]. Mobbing calls produced in response to smaller, higher-threat predators contain more “D” notes compared to those produced in response to larger, lower-threat predators and thus convey the degree of threat of predators [4]. We specifically asked whether the neural response varies with the degree of threat conveyed by the mobbing calls of chickadees and whether the neural response is the same for actual predator calls that correspond to the degree of threat of the chickadee mobbing calls. Our results demonstrate that, as degree of threat increases in conspecific chickadee mobbing calls, there is a corresponding increase in immediate early gene (IEG) expression in telencephalic auditory areas. We also demonstrate that as the degree of threat increases for the heterospecific predator, there is a corresponding increase in IEG expression in the auditory areas. Furthermore, there was no significant difference in the amount IEG expression between conspecific mobbing calls or heterospecific predator calls that were the same degree of threat. In a second experiment, using hand-reared chickadees without predator experience, we found more IEG expression in response to mobbing calls than corresponding predator calls, indicating that degree of threat is learned. Our results demonstrate that degree of threat corresponds to neural activity in the auditory areas and that threat can be conveyed by different species signals and that these signals must be learned. PMID:21909363

  7. Neural correlates of threat perception: neural equivalence of conspecific and heterospecific mobbing calls is learned.

    Science.gov (United States)

    Avey, Marc T; Hoeschele, Marisa; Moscicki, Michele K; Bloomfield, Laurie L; Sturdy, Christopher B

    2011-01-01

    Songbird auditory areas (i.e., CMM and NCM) are preferentially activated to playback of conspecific vocalizations relative to heterospecific and arbitrary noise. Here, we asked if the neural response to auditory stimulation is not simply preferential for conspecific vocalizations but also for the information conveyed by the vocalization. Black-capped chickadees use their chick-a-dee mobbing call to recruit conspecifics and other avian species to mob perched predators. Mobbing calls produced in response to smaller, higher-threat predators contain more "D" notes compared to those produced in response to larger, lower-threat predators and thus convey the degree of threat of predators. We specifically asked whether the neural response varies with the degree of threat conveyed by the mobbing calls of chickadees and whether the neural response is the same for actual predator calls that correspond to the degree of threat of the chickadee mobbing calls. Our results demonstrate that, as degree of threat increases in conspecific chickadee mobbing calls, there is a corresponding increase in immediate early gene (IEG) expression in telencephalic auditory areas. We also demonstrate that as the degree of threat increases for the heterospecific predator, there is a corresponding increase in IEG expression in the auditory areas. Furthermore, there was no significant difference in the amount IEG expression between conspecific mobbing calls or heterospecific predator calls that were the same degree of threat. In a second experiment, using hand-reared chickadees without predator experience, we found more IEG expression in response to mobbing calls than corresponding predator calls, indicating that degree of threat is learned. Our results demonstrate that degree of threat corresponds to neural activity in the auditory areas and that threat can be conveyed by different species signals and that these signals must be learned.

  8. Behavior and neural basis of near-optimal visual search

    Science.gov (United States)

    Ma, Wei Ji; Navalpakkam, Vidhya; Beck, Jeffrey M; van den Berg, Ronald; Pouget, Alexandre

    2013-01-01

    The ability to search efficiently for a target in a cluttered environment is one of the most remarkable functions of the nervous system. This task is difficult under natural circumstances, as the reliability of sensory information can vary greatly across space and time and is typically a priori unknown to the observer. In contrast, visual-search experiments commonly use stimuli of equal and known reliability. In a target detection task, we randomly assigned high or low reliability to each item on a trial-by-trial basis. An optimal observer would weight the observations by their trial-to-trial reliability and combine them using a specific nonlinear integration rule. We found that humans were near-optimal, regardless of whether distractors were homogeneous or heterogeneous and whether reliability was manipulated through contrast or shape. We present a neural-network implementation of near-optimal visual search based on probabilistic population coding. The network matched human performance. PMID:21552276

  9. Single-Iteration Learning Algorithm for Feed-Forward Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Barhen, J.; Cogswell, R.; Protopopescu, V.

    1999-07-31

    A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.

  10. On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks.

    Directory of Open Access Journals (Sweden)

    Paul Tonelli

    Full Text Available A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1 the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2 synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT. Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1 in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2 whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities.

  11. Learning behavior and temporary minima of two-layer neural networks

    NARCIS (Netherlands)

    Annema, Anne J.; Hoen, Klaas; Hoen, Klaas; Wallinga, Hans

    1994-01-01

    This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of

  12. Extruded Bread Classification on the Basis of Acoustic Emission Signal With Application of Artificial Neural Networks

    Science.gov (United States)

    Świetlicka, Izabela; Muszyński, Siemowit; Marzec, Agata

    2015-04-01

    The presented work covers the problem of developing a method of extruded bread classification with the application of artificial neural networks. Extruded flat graham, corn, and rye breads differening in water activity were used. The breads were subjected to the compression test with simultaneous registration of acoustic signal. The amplitude-time records were analyzed both in time and frequency domains. Acoustic emission signal parameters: single energy, counts, amplitude, and duration acoustic emission were determined for the breads in four water activities: initial (0.362 for rye, 0.377 for corn, and 0.371 for graham bread), 0.432, 0.529, and 0.648. For classification and the clustering process, radial basis function, and self-organizing maps (Kohonen network) were used. Artificial neural networks were examined with respect to their ability to classify or to cluster samples according to the bread type, water activity value, and both of them. The best examination results were achieved by the radial basis function network in classification according to water activity (88%), while the self-organizing maps network yielded 81% during bread type clustering.

  13. Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

    Science.gov (United States)

    Ferreria, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

    2017-01-01

    Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

  14. Functionally segregated neural substrates for arbitrary audiovisual paired-association learning.

    Science.gov (United States)

    Tanabe, Hiroki C; Honda, Manabu; Sadato, Norihiro

    2005-07-06

    To clarify the neural substrates and their dynamics during crossmodal association learning, we conducted functional magnetic resonance imaging (MRI) during audiovisual paired-association learning of delayed matching-to-sample tasks. Thirty subjects were involved in the study; 15 performed an audiovisual paired-association learning task, and the remainder completed a control visuo-visual task. Each trial consisted of the successive presentation of a pair of stimuli. Subjects were asked to identify predefined audiovisual or visuo-visual pairs by trial and error. Feedback for each trial was given regardless of whether the response was correct or incorrect. During the delay period, several areas showed an increase in the MRI signal as learning proceeded: crossmodal activity increased in unimodal areas corresponding to visual or auditory areas, and polymodal responses increased in the occipitotemporal junction and parahippocampal gyrus. This pattern was not observed in the visuo-visual intramodal paired-association learning task, suggesting that crossmodal associations might be formed by binding unimodal sensory areas via polymodal regions. In both the audiovisual and visuo-visual tasks, the MRI signal in the superior temporal sulcus (STS) in response to the second stimulus and feedback peaked during the early phase of learning and then decreased, indicating that the STS might be key to the creation of paired associations, regardless of stimulus type. In contrast to the activity changes in the regions discussed above, there was constant activity in the frontoparietal circuit during the delay period in both tasks, implying that the neural substrates for the formation and storage of paired associates are distinct from working memory circuits.

  15. LEARNING ALGORITHM EFFECT ON MULTILAYER FEED FORWARD ARTIFICIAL NEURAL NETWORK PERFORMANCE IN IMAGE CODING

    Directory of Open Access Journals (Sweden)

    OMER MAHMOUD

    2007-08-01

    Full Text Available One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms.

  16. A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

    Science.gov (United States)

    Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

    2015-12-01

    Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

  17. Potential usefulness of an artificial neural network for assessing ventricular size

    International Nuclear Information System (INIS)

    Fukuda, Haruyuki; Nakajima, Hideyuki; Usuki, Noriaki; Saiwai, Shigeo; Miyamoto, Takeshi; Inoue, Yuichi; Onoyama, Yasuto.

    1995-01-01

    An artificial neural network approach was applied to assess ventricular size from computed tomograms. Three layer, feed-forward neural networks with a back propagation algorithm were designed to distinguish between three degree of enlargement of the ventricles on the basis of patient's age and six items of computed tomographic information. Data for training and testing the neural network were created with computed tomograms of the brains selected at random from daily examinations. Four radiologists decided by mutual consent subjectively based on their experience whether the ventricles were within normal limits, slightly enlarged, or enlarged for the patient's age. The data for training was obtained from 38 patients. The data for testing was obtained from 47 other patients. The performance of the neural network trained using the data for training was evaluated by the rate of correct answers to the data for testing. The valid solution ratio to response of the test data obtained from the trained neural networks was more than 90% for all conditions in this study. The solutions were completely valid in the neural networks with two or three units at the hidden layer with 2,200 learning iterations, and with two units at the hidden layer with 11,000 learning iterations. The squared error decreased remarkably in the range from 0 to 500 learning iterations, and was close to a contrast over two thousand learning iterations. The neural network with a hidden layer having two or three units showed high decision performance. The preliminary results strongly suggest that the neural network approach has potential utility in computer-aided estimation of enlargement of the ventricles. (author)

  18. Modeling of mass transfer of Phospholipids in separation process with supercritical CO2 fluid by RBF artificial neural networks

    Science.gov (United States)

    An artificial Radial Basis Function (RBF) neural network model was developed for the prediction of mass transfer of the phospholipids from canola meal in supercritical CO2 fluid. The RBF kind of artificial neural networks (ANN) with orthogonal least squares (OLS) learning algorithm were used for mod...

  19. Integrating the behavioral and neural dynamics of response selection in a dual-task paradigm: a dynamic neural field model of Dux et al. (2009).

    Science.gov (United States)

    Buss, Aaron T; Wifall, Tim; Hazeltine, Eliot; Spencer, John P

    2014-02-01

    People are typically slower when executing two tasks than when only performing a single task. These dual-task costs are initially robust but are reduced with practice. Dux et al. (2009) explored the neural basis of dual-task costs and learning using fMRI. Inferior frontal junction (IFJ) showed a larger hemodynamic response on dual-task trials compared with single-task trial early in learning. As dual-task costs were eliminated, dual-task hemodynamics in IFJ reduced to single-task levels. Dux and colleagues concluded that the reduction of dual-task costs is accomplished through increased efficiency of information processing in IFJ. We present a dynamic field theory of response selection that addresses two questions regarding these results. First, what mechanism leads to the reduction of dual-task costs and associated changes in hemodynamics? We show that a simple Hebbian learning mechanism is able to capture the quantitative details of learning at both the behavioral and neural levels. Second, is efficiency isolated to cognitive control areas such as IFJ, or is it also evident in sensory motor areas? To investigate this, we restrict Hebbian learning to different parts of the neural model. None of the restricted learning models showed the same reductions in dual-task costs as the unrestricted learning model, suggesting that efficiency is distributed across cognitive control and sensory motor processing systems.

  20. The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding.

    Science.gov (United States)

    Testolin, Alberto; De Filippo De Grazia, Michele; Zorzi, Marco

    2017-01-01

    The recent "deep learning revolution" in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems.

  1. Advanced Test Reactor Safety Basis Upgrade Lessons Learned Relative to Design Basis Verification and Safety Basis Management

    International Nuclear Information System (INIS)

    G. L. Sharp; R. T. McCracken

    2004-01-01

    The Advanced Test Reactor (ATR) is a pressurized light-water reactor with a design thermal power of 250 MW. The principal function of the ATR is to provide a high neutron flux for testing reactor fuels and other materials. The reactor also provides other irradiation services such as radioisotope production. The ATR and its support facilities are located at the Test Reactor Area of the Idaho National Engineering and Environmental Laboratory (INEEL). An audit conducted by the Department of Energy's Office of Independent Oversight and Performance Assurance (DOE OA) raised concerns that design conditions at the ATR were not adequately analyzed in the safety analysis and that legacy design basis management practices had the potential to further impact safe operation of the facility.1 The concerns identified by the audit team, and issues raised during additional reviews performed by ATR safety analysts, were evaluated through the unreviewed safety question process resulting in shutdown of the ATR for more than three months while these concerns were resolved. Past management of the ATR safety basis, relative to facility design basis management and change control, led to concerns that discrepancies in the safety basis may have developed. Although not required by DOE orders or regulations, not performing design basis verification in conjunction with development of the 10 CFR 830 Subpart B upgraded safety basis allowed these potential weaknesses to be carried forward. Configuration management and a clear definition of the existing facility design basis have a direct relation to developing and maintaining a high quality safety basis which properly identifies and mitigates all hazards and postulated accident conditions. These relations and the impact of past safety basis management practices have been reviewed in order to identify lessons learned from the safety basis upgrade process and appropriate actions to resolve possible concerns with respect to the current ATR safety

  2. Neural mechanisms of human perceptual learning: electrophysiological evidence for a two-stage process.

    Science.gov (United States)

    Hamamé, Carlos M; Cosmelli, Diego; Henriquez, Rodrigo; Aboitiz, Francisco

    2011-04-26

    Humans and other animals change the way they perceive the world due to experience. This process has been labeled as perceptual learning, and implies that adult nervous systems can adaptively modify the way in which they process sensory stimulation. However, the mechanisms by which the brain modifies this capacity have not been sufficiently analyzed. We studied the neural mechanisms of human perceptual learning by combining electroencephalographic (EEG) recordings of brain activity and the assessment of psychophysical performance during training in a visual search task. All participants improved their perceptual performance as reflected by an increase in sensitivity (d') and a decrease in reaction time. The EEG signal was acquired throughout the entire experiment revealing amplitude increments, specific and unspecific to the trained stimulus, in event-related potential (ERP) components N2pc and P3 respectively. P3 unspecific modification can be related to context or task-based learning, while N2pc may be reflecting a more specific attentional-related boosting of target detection. Moreover, bell and U-shaped profiles of oscillatory brain activity in gamma (30-60 Hz) and alpha (8-14 Hz) frequency bands may suggest the existence of two phases for learning acquisition, which can be understood as distinctive optimization mechanisms in stimulus processing. We conclude that there are reorganizations in several neural processes that contribute differently to perceptual learning in a visual search task. We propose an integrative model of neural activity reorganization, whereby perceptual learning takes place as a two-stage phenomenon including perceptual, attentional and contextual processes.

  3. Unsupervised learning of a steerable basis for invariant image representations

    Science.gov (United States)

    Bethge, Matthias; Gerwinn, Sebastian; Macke, Jakob H.

    2007-02-01

    There are two aspects to unsupervised learning of invariant representations of images: First, we can reduce the dimensionality of the representation by finding an optimal trade-off between temporal stability and informativeness. We show that the answer to this optimization problem is generally not unique so that there is still considerable freedom in choosing a suitable basis. Which of the many optimal representations should be selected? Here, we focus on this second aspect, and seek to find representations that are invariant under geometrical transformations occuring in sequences of natural images. We utilize ideas of 'steerability' and Lie groups, which have been developed in the context of filter design. In particular, we show how an anti-symmetric version of canonical correlation analysis can be used to learn a full-rank image basis which is steerable with respect to rotations. We provide a geometric interpretation of this algorithm by showing that it finds the two-dimensional eigensubspaces of the average bivector. For data which exhibits a variety of transformations, we develop a bivector clustering algorithm, which we use to learn a basis of generalized quadrature pairs (i.e. 'complex cells') from sequences of natural images.

  4. Learning representations for the early detection of sepsis with deep neural networks.

    Science.gov (United States)

    Kam, Hye Jin; Kim, Ha Young

    2017-10-01

    Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

  5. Incidental regulation of attraction: the neural basis of the derogation of attractive alternatives in romantic relationships.

    Science.gov (United States)

    Meyer, Meghan L; Berkman, Elliot T; Karremans, Johan C; Lieberman, Matthew D

    2011-04-01

    Although a great deal of research addresses the neural basis of deliberate and intentional emotion-regulation strategies, less attention has been paid to the neural mechanisms involved in implicit forms of emotion regulation. Behavioural research suggests that romantically involved participants implicitly derogate the attractiveness of alternative partners, and the present study sought to examine the neural basis of this effect. Romantically committed participants in the present study were scanned with functional magnetic resonance imaging (fMRI) while indicating whether they would consider each of a series of attractive (or unattractive) opposite-sex others as a hypothetical dating partner both while under cognitive load and no cognitive load. Successful derogation of attractive others during the no cognitive load compared to the cognitive load trials corresponded with increased activation in the ventrolateral prefrontal cortex (VLPFC) and posterior dorsomedial prefrontal cortex (pDMPFC), and decreased activation in the ventral striatum, a pattern similar to those reported in deliberate emotion-regulation studies. Activation in the VLPFC and pDMPFC was not significant in the cognitive load condition, indicating that while the derogation effect may be implicit, it nonetheless requires cognitive resources. Additionally, activation in the right VLPFC correlated with participants' level of relationship investment. These findings suggest that the RVLPFC may play a particularly important role in implicitly regulating the emotions that threaten the stability of a romantic relationship. © 2011 Psychology Press, an imprint of the Taylor & Francis Group, an Informa business

  6. Culture in the mind's mirror: how anthropology and neuroscience can inform a model of the neural substrate for cultural imitative learning.

    Science.gov (United States)

    Losin, Elizabeth A Reynolds; Dapretto, Mirella; Iacoboni, Marco

    2009-01-01

    Cultural neuroscience, the study of how cultural experience shapes the brain, is an emerging subdiscipline in the neurosciences. Yet, a foundational question to the study of culture and the brain remains neglected by neuroscientific inquiry: "How does cultural information get into the brain in the first place?" Fortunately, the tools needed to explore the neural architecture of cultural learning - anthropological theories and cognitive neuroscience methodologies - already exist; they are merely separated by disciplinary boundaries. Here we review anthropological theories of cultural learning derived from fieldwork and modeling; since cultural learning theory suggests that sophisticated imitation abilities are at the core of human cultural learning, we focus our review on cultural imitative learning. Accordingly we proceed to discuss the neural underpinnings of imitation and other mechanisms important for cultural learning: learning biases, mental state attribution, and reinforcement learning. Using cultural neuroscience theory and cognitive neuroscience research as our guides, we then propose a preliminary model of the neural architecture of cultural learning. Finally, we discuss future studies needed to test this model and fully explore and explain the neural underpinnings of cultural imitative learning.

  7. Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

    Science.gov (United States)

    Williams-Hayes, Peggy S.

    2004-01-01

    The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

  8. Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

    Directory of Open Access Journals (Sweden)

    Ryan Henderson

    2017-09-01

    Full Text Available Picasso is a free open-source (Eclipse Public License web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two visualizations which help reveal issues that evaluation metrics like loss and accuracy might hide: for example, learning a proxy classification task. Picasso works with the Tensorflow deep learning framework, and Keras (when the model can be loaded into the Tensorflow backend. Picasso can be used with minimal configuration by deep learning researchers and engineers alike across various neural network architectures. Adding new visualizations is simple: the user can specify their visualization code and HTML template separately from the application code.

  9. A stochastic learning algorithm for layered neural networks

    International Nuclear Information System (INIS)

    Bartlett, E.B.; Uhrig, R.E.

    1992-01-01

    The random optimization method typically uses a Gaussian probability density function (PDF) to generate a random search vector. In this paper the random search technique is applied to the neural network training problem and is modified to dynamically seek out the optimal probability density function (OPDF) from which to select the search vector. The dynamic OPDF search process, combined with an auto-adaptive stratified sampling technique and a dynamic node architecture (DNA) learning scheme, completes the modifications of the basic method. The DNA technique determines the appropriate number of hidden nodes needed for a given training problem. By using DNA, researchers do not have to set the neural network architectures before training is initiated. The approach is applied to networks of generalized, fully interconnected, continuous perceptions. Computer simulation results are given

  10. Specific neural basis of Chinese idioms processing: an event-related functional MRI study

    International Nuclear Information System (INIS)

    Chen Shaoqi; Zhang Yanzhen; Xiao Zhuangwei; Zhang Xuexin

    2007-01-01

    Objective: To address the neural basis of Chinese idioms processing with different kinds of stimuli using an event-related fMRI design. Methods: Sixteen native Chinese speakers were asked to perform a semantic decision task during fMRI scanning. Three kinds of stimuli were used: Real idioms (Real-idiom condition); Literally plausible phrases (Pseudo-idiom condition, the last character of a real idiom was replaced by a character with similar meaning); Literally implausible strings (Non-idiom condition, the last character of a real idiom was replaced by a character with unrelated meaning). Reaction time and correct rate were recorded at the same time. Results: The error rate was 2.6%, 5.2% and 0.9% (F=3.51, P 0.05) for real idioms, pseudo-idioms and wrong idioms, respectively. Similar neural network was activated in all of the three conditions. However, the right hippocampus was only activated in the real idiom condition, and significant activations were found in anterior portion of left inferior frontal gyms (BA47) in real-and pseudo-idiom conditions, but not in non-idiom condition. Conclusion: The right hippocampus plays a specific role in the particular wording of the Chinese idioms. And the left anterior inferior frontal gyms (BA47) may be engaged in the semantic processing of Chinese idioms. The results support the notion that there were specific neural bases for Chinese idioms processing. (authors)

  11. Deep learning for steganalysis via convolutional neural networks

    Science.gov (United States)

    Qian, Yinlong; Dong, Jing; Wang, Wei; Tan, Tieniu

    2015-03-01

    Current work on steganalysis for digital images is focused on the construction of complex handcrafted features. This paper proposes a new paradigm for steganalysis to learn features automatically via deep learning models. We novelly propose a customized Convolutional Neural Network for steganalysis. The proposed model can capture the complex dependencies that are useful for steganalysis. Compared with existing schemes, this model can automatically learn feature representations with several convolutional layers. The feature extraction and classification steps are unified under a single architecture, which means the guidance of classification can be used during the feature extraction step. We demonstrate the effectiveness of the proposed model on three state-of-theart spatial domain steganographic algorithms - HUGO, WOW, and S-UNIWARD. Compared to the Spatial Rich Model (SRM), our model achieves comparable performance on BOSSbase and the realistic and large ImageNet database.

  12. Critical heat flux prediction by using radial basis function and multilayer perceptron neural networks: A comparison study

    International Nuclear Information System (INIS)

    Vaziri, Nima; Hojabri, Alireza; Erfani, Ali; Monsefi, Mehrdad; Nilforooshan, Behnam

    2007-01-01

    Critical heat flux (CHF) is an important parameter for the design of nuclear reactors. Although many experimental and theoretical researches have been performed, there is not a single correlation to predict CHF because it is influenced by many parameters. These parameters are based on fixed inlet, local and fixed outlet conditions. Artificial neural networks (ANNs) have been applied to a wide variety of different areas such as prediction, approximation, modeling and classification. In this study, two types of neural networks, radial basis function (RBF) and multilayer perceptron (MLP), are trained with the experimental CHF data and their performances are compared. RBF predicts CHF with root mean square (RMS) errors of 0.24%, 7.9%, 0.16% and MLP predicts CHF with RMS errors of 1.29%, 8.31% and 2.71%, in fixed inlet conditions, local conditions and fixed outlet conditions, respectively. The results show that neural networks with RBF structure have superior performance in CHF data prediction over MLP neural networks. The parametric trends of CHF obtained by the trained ANNs are also evaluated and results reported

  13. The neural basis of emotions varies over time: different regions go with onset- and offset-bound processes underlying emotion intensity.

    Science.gov (United States)

    Résibois, Maxime; Verduyn, Philippe; Delaveau, Pauline; Rotgé, Jean-Yves; Kuppens, Peter; Van Mechelen, Iven; Fossati, Philippe

    2017-08-01

    According to theories of emotion dynamics, emotions unfold across two phases in which different types of processes come to the fore: emotion onset and emotion offset. Differences in onset-bound processes are reflected by the degree of explosiveness or steepness of the response at onset, and differences in offset-bound processes by the degree of accumulation or intensification of the subsequent response. Whether onset- and offset-bound processes have distinctive neural correlates and, hence, whether the neural basis of emotions varies over time, still remains unknown. In the present fMRI study, we address this question using a recently developed paradigm that allows to disentangle explosiveness and accumulation. Thirty-one participants were exposed to neutral and negative social feedback, and asked to reflect on its contents. Emotional intensity while reading and thinking about the feedback was measured with an intensity profile tracking approach. Using non-negative matrix factorization, the resulting profile data were decomposed in explosiveness and accumulation components, which were subsequently entered as continuous regressors of the BOLD response. It was found that the neural basis of emotion intensity shifts as emotions unfold over time with emotion explosiveness and accumulation having distinctive neural correlates. © The Author (2017). Published by Oxford University Press.

  14. Advanced approach to numerical forecasting using artificial neural networks

    Directory of Open Access Journals (Sweden)

    Michael Štencl

    2009-01-01

    Full Text Available Current global market is driven by many factors, such as the information age, the time and amount of information distributed by many data channels it is practically impossible analyze all kinds of incoming information flows and transform them to data with classical methods. New requirements could be met by using other methods. Once trained on patterns artificial neural networks can be used for forecasting and they are able to work with extremely big data sets in reasonable time. The patterns used for learning process are samples of past data. This paper uses Radial Basis Functions neural network in comparison with Multi Layer Perceptron network with Back-propagation learning algorithm on prediction task. The task works with simplified numerical time series and includes forty observations with prediction for next five observations. The main topic of the article is the identification of the main differences between used neural networks architectures together with numerical forecasting. Detected differences then verify on practical comparative example.

  15. Motor sequence learning-induced neural efficiency in functional brain connectivity.

    Science.gov (United States)

    Karim, Helmet T; Huppert, Theodore J; Erickson, Kirk I; Wollam, Mariegold E; Sparto, Patrick J; Sejdić, Ervin; VanSwearingen, Jessie M

    2017-02-15

    Previous studies have shown the functional neural circuitry differences before and after an explicitly learned motor sequence task, but have not assessed these changes during the process of motor skill learning. Functional magnetic resonance imaging activity was measured while participants (n=13) were asked to tap their fingers to visually presented sequences in blocks that were either the same sequence repeated (learning block) or random sequences (control block). Motor learning was associated with a decrease in brain activity during learning compared to control. Lower brain activation was noted in the posterior parietal association area and bilateral thalamus during the later periods of learning (not during the control). Compared to the control condition, we found the task-related motor learning was associated with decreased connectivity between the putamen and left inferior frontal gyrus and left middle cingulate brain regions. Motor learning was associated with changes in network activity, spatial extent, and connectivity. Copyright © 2016 Elsevier B.V. All rights reserved.

  16. Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

    Science.gov (United States)

    Carpenter, Gail A.

    1997-11-01

    A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network.

  17. Stress affects the neural ensemble for integrating new information and prior knowledge.

    Science.gov (United States)

    Vogel, Susanne; Kluen, Lisa Marieke; Fernández, Guillén; Schwabe, Lars

    2018-06-01

    Prior knowledge, represented as a schema, facilitates memory encoding. This schema-related learning is assumed to rely on the medial prefrontal cortex (mPFC) that rapidly integrates new information into the schema, whereas schema-incongruent or novel information is encoded by the hippocampus. Stress is a powerful modulator of prefrontal and hippocampal functioning and first studies suggest a stress-induced deficit of schema-related learning. However, the underlying neural mechanism is currently unknown. To investigate the neural basis of a stress-induced schema-related learning impairment, participants first acquired a schema. One day later, they underwent a stress induction or a control procedure before learning schema-related and novel information in the MRI scanner. In line with previous studies, learning schema-related compared to novel information activated the mPFC, angular gyrus, and precuneus. Stress, however, affected the neural ensemble activated during learning. Whereas the control group distinguished between sets of brain regions for related and novel information, stressed individuals engaged the hippocampus even when a relevant schema was present. Additionally, stressed participants displayed aberrant functional connectivity between brain regions involved in schema processing when encoding novel information. The failure to segregate functional connectivity patterns depending on the presence of prior knowledge was linked to impaired performance after stress. Our results show that stress affects the neural ensemble underlying the efficient use of schemas during learning. These findings may have relevant implications for clinical and educational settings. Copyright © 2018 Elsevier Inc. All rights reserved.

  18. Computational modeling of neural plasticity for self-organization of neural networks.

    Science.gov (United States)

    Chrol-Cannon, Joseph; Jin, Yaochu

    2014-11-01

    Self-organization in biological nervous systems during the lifetime is known to largely occur through a process of plasticity that is dependent upon the spike-timing activity in connected neurons. In the field of computational neuroscience, much effort has been dedicated to building up computational models of neural plasticity to replicate experimental data. Most recently, increasing attention has been paid to understanding the role of neural plasticity in functional and structural neural self-organization, as well as its influence on the learning performance of neural networks for accomplishing machine learning tasks such as classification and regression. Although many ideas and hypothesis have been suggested, the relationship between the structure, dynamics and learning performance of neural networks remains elusive. The purpose of this article is to review the most important computational models for neural plasticity and discuss various ideas about neural plasticity's role. Finally, we suggest a few promising research directions, in particular those along the line that combines findings in computational neuroscience and systems biology, and their synergetic roles in understanding learning, memory and cognition, thereby bridging the gap between computational neuroscience, systems biology and computational intelligence. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

  19. The neural basis of responsibility attribution in decision-making.

    Science.gov (United States)

    Li, Peng; Shen, Yue; Sui, Xue; Chen, Changming; Feng, Tingyong; Li, Hong; Holroyd, Clay

    2013-01-01

    Social responsibility links personal behavior with societal expectations and plays a key role in affecting an agent's emotional state following a decision. However, the neural basis of responsibility attribution remains unclear. In two previous event-related brain potential (ERP) studies we found that personal responsibility modulated outcome evaluation in gambling tasks. Here we conducted a functional magnetic resonance imaging (fMRI) study to identify particular brain regions that mediate responsibility attribution. In a context involving team cooperation, participants completed a task with their teammates and on each trial received feedback about team success and individual success sequentially. We found that brain activity differed between conditions involving team success vs. team failure. Further, different brain regions were associated with reinforcement of behavior by social praise vs. monetary reward. Specifically, right temporoparietal junction (RTPJ) was associated with social pride whereas dorsal striatum and dorsal anterior cingulate cortex (ACC) were related to reinforcement of behaviors leading to personal gain. The present study provides evidence that the RTPJ is an important region for determining whether self-generated behaviors are deserving of praise in a social context.

  20. A Cognitive Neural Architecture Able to Learn and Communicate through Natural Language.

    Directory of Open Access Journals (Sweden)

    Bruno Golosio

    Full Text Available Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.

  1. Neural basis of individualistic and collectivistic views of self.

    Science.gov (United States)

    Chiao, Joan Y; Harada, Tokiko; Komeda, Hidetsugu; Li, Zhang; Mano, Yoko; Saito, Daisuke; Parrish, Todd B; Sadato, Norihiro; Iidaka, Tetsuya

    2009-09-01

    Individualism and collectivism refer to cultural values that influence how people construe themselves and their relation to the world. Individualists perceive themselves as stable entities, autonomous from other people and their environment, while collectivists view themselves as dynamic entities, continually defined by their social context and relationships. Despite rich understanding of how individualism and collectivism influence social cognition at a behavioral level, little is known about how these cultural values modulate neural representations underlying social cognition. Using cross-cultural functional magnetic resonance imaging (fMRI), we examined whether the cultural values of individualism and collectivism modulate neural activity within medial prefrontal cortex (MPFC) during processing of general and contextual self judgments. Here, we show that neural activity within the anterior rostral portion of the MPFC during processing of general and contextual self judgments positively predicts how individualistic or collectivistic a person is across cultures. These results reveal two kinds of neural representations of self (eg, a general self and a contextual self) within MPFC and demonstrate how cultural values of individualism and collectivism shape these neural representations. 2008 Wiley-Liss, Inc.

  2. Learning to Produce Syllabic Speech Sounds via Reward-Modulated Neural Plasticity

    Science.gov (United States)

    Warlaumont, Anne S.; Finnegan, Megan K.

    2016-01-01

    At around 7 months of age, human infants begin to reliably produce well-formed syllables containing both consonants and vowels, a behavior called canonical babbling. Over subsequent months, the frequency of canonical babbling continues to increase. How the infant’s nervous system supports the acquisition of this ability is unknown. Here we present a computational model that combines a spiking neural network, reinforcement-modulated spike-timing-dependent plasticity, and a human-like vocal tract to simulate the acquisition of canonical babbling. Like human infants, the model’s frequency of canonical babbling gradually increases. The model is rewarded when it produces a sound that is more auditorily salient than sounds it has previously produced. This is consistent with data from human infants indicating that contingent adult responses shape infant behavior and with data from deaf and tracheostomized infants indicating that hearing, including hearing one’s own vocalizations, is critical for canonical babbling development. Reward receipt increases the level of dopamine in the neural network. The neural network contains a reservoir with recurrent connections and two motor neuron groups, one agonist and one antagonist, which control the masseter and orbicularis oris muscles, promoting or inhibiting mouth closure. The model learns to increase the number of salient, syllabic sounds it produces by adjusting the base level of muscle activation and increasing their range of activity. Our results support the possibility that through dopamine-modulated spike-timing-dependent plasticity, the motor cortex learns to harness its natural oscillations in activity in order to produce syllabic sounds. It thus suggests that learning to produce rhythmic mouth movements for speech production may be supported by general cortical learning mechanisms. The model makes several testable predictions and has implications for our understanding not only of how syllabic vocalizations develop

  3. Dissociable neural representations of reinforcement and belief prediction errors underlie strategic learning.

    Science.gov (United States)

    Zhu, Lusha; Mathewson, Kyle E; Hsu, Ming

    2012-01-31

    Decision-making in the presence of other competitive intelligent agents is fundamental for social and economic behavior. Such decisions require agents to behave strategically, where in addition to learning about the rewards and punishments available in the environment, they also need to anticipate and respond to actions of others competing for the same rewards. However, whereas we know much about strategic learning at both theoretical and behavioral levels, we know relatively little about the underlying neural mechanisms. Here, we show using a multi-strategy competitive learning paradigm that strategic choices can be characterized by extending the reinforcement learning (RL) framework to incorporate agents' beliefs about the actions of their opponents. Furthermore, using this characterization to generate putative internal values, we used model-based functional magnetic resonance imaging to investigate neural computations underlying strategic learning. We found that the distinct notions of prediction errors derived from our computational model are processed in a partially overlapping but distinct set of brain regions. Specifically, we found that the RL prediction error was correlated with activity in the ventral striatum. In contrast, activity in the ventral striatum, as well as the rostral anterior cingulate (rACC), was correlated with a previously uncharacterized belief-based prediction error. Furthermore, activity in rACC reflected individual differences in degree of engagement in belief learning. These results suggest a model of strategic behavior where learning arises from interaction of dissociable reinforcement and belief-based inputs.

  4. Organisms modeling: The question of radial basis function networks

    Directory of Open Access Journals (Sweden)

    Muzy Alexandre

    2014-01-01

    Full Text Available There exists usually a gap between bio-inspired computational techniques and what biologists can do with these techniques in their current researches. Although biology is the root of system-theory and artifical neural networks, computer scientists are tempted to build their own systems independently of biological issues. This publication is a first-step re-evalution of an usual machine learning technique (radial basis funtion(RBF networks in the context of systems and biological reactive organisms.

  5. Growing adaptive machines combining development and learning in artificial neural networks

    CERN Document Server

    Bredeche, Nicolas; Doursat, René

    2014-01-01

    The pursuit of artificial intelligence has been a highly active domain of research for decades, yielding exciting scientific insights and productive new technologies. In terms of generating intelligence, however, this pursuit has yielded only limited success. This book explores the hypothesis that adaptive growth is a means of moving forward. By emulating the biological process of development, we can incorporate desirable characteristics of natural neural systems into engineered designs, and thus move closer towards the creation of brain-like systems. The particular focus is on how to design artificial neural networks for engineering tasks. The book consists of contributions from 18 researchers, ranging from detailed reviews of recent domains by senior scientists, to exciting new contributions representing the state of the art in machine learning research. The book begins with broad overviews of artificial neurogenesis and bio-inspired machine learning, suitable both as an introduction to the domains and as a...

  6. Learning-Related Changes in Adolescents' Neural Networks during Hypothesis-Generating and Hypothesis-Understanding Training

    Science.gov (United States)

    Lee, Jun-Ki; Kwon, Yongju

    2012-01-01

    Fourteen science high school students participated in this study, which investigated neural-network plasticity associated with hypothesis-generating and hypothesis-understanding in learning. The students were divided into two groups and participated in either hypothesis-generating or hypothesis-understanding type learning programs, which were…

  7. Optical implementation of neural learning algorithms based on cross-gain modulation in a semiconductor optical amplifier

    Science.gov (United States)

    Li, Qiang; Wang, Zhi; Le, Yansi; Sun, Chonghui; Song, Xiaojia; Wu, Chongqing

    2016-10-01

    Neuromorphic engineering has a wide range of applications in the fields of machine learning, pattern recognition, adaptive control, etc. Photonics, characterized by its high speed, wide bandwidth, low power consumption and massive parallelism, is an ideal way to realize ultrafast spiking neural networks (SNNs). Synaptic plasticity is believed to be critical for learning, memory and development in neural circuits. Experimental results have shown that changes of synapse are highly dependent on the relative timing of pre- and postsynaptic spikes. Synaptic plasticity in which presynaptic spikes preceding postsynaptic spikes results in strengthening, while the opposite timing results in weakening is called antisymmetric spike-timing-dependent plasticity (STDP) learning rule. And synaptic plasticity has the opposite effect under the same conditions is called antisymmetric anti-STDP learning rule. We proposed and experimentally demonstrated an optical implementation of neural learning algorithms, which can achieve both of antisymmetric STDP and anti-STDP learning rule, based on the cross-gain modulation (XGM) within a single semiconductor optical amplifier (SOA). The weight and height of the potentitation and depression window can be controlled by adjusting the injection current of the SOA, to mimic the biological antisymmetric STDP and anti-STDP learning rule more realistically. As the injection current increases, the width of depression and potentitation window decreases and height increases, due to the decreasing of recovery time and increasing of gain under a stronger injection current. Based on the demonstrated optical STDP circuit, ultrafast learning in optical SNNs can be realized.

  8. Ventral Tegmental Area and Substantia Nigra Neural Correlates of Spatial Learning

    Science.gov (United States)

    Martig, Adria K.; Mizumori, Sheri J. Y.

    2011-01-01

    The ventral tegmental area (VTA) and substantia nigra pars compacta (SNc) may provide modulatory signals that, respectively, influence hippocampal (HPC)- and striatal-dependent memory. Electrophysiological studies investigating neural correlates of learning and memory of dopamine (DA) neurons during classical conditioning tasks have found DA…

  9. The neural coding of feedback learning across child and adolescent development

    NARCIS (Netherlands)

    Peters, S.; Braams, B.R.; Raijmakers, M.E.J.; Koolschijn, P.C.M.P.; Crone, E.A.

    2014-01-01

    The ability to learn from environmental cues is an important contributor to successful performance in a variety of settings, including school. Despite the progress in unraveling the neural correlates of cognitive control in childhood and adolescence, relatively little is known about how these brain

  10. Neural changes associated to procedural learning and automatization process in Developmental Coordination Disorder and/or Developmental Dyslexia.

    Science.gov (United States)

    Biotteau, Maëlle; Péran, Patrice; Vayssière, Nathalie; Tallet, Jessica; Albaret, Jean-Michel; Chaix, Yves

    2017-03-01

    Recent theories hypothesize that procedural learning may support the frequent overlap between neurodevelopmental disorders. The neural circuitry supporting procedural learning includes, among others, cortico-cerebellar and cortico-striatal loops. Alteration of these loops may account for the frequent comorbidity between Developmental Coordination Disorder (DCD) and Developmental Dyslexia (DD). The aim of our study was to investigate cerebral changes due to the learning and automatization of a sequence learning task in children with DD, or DCD, or both disorders. fMRI on 48 children (aged 8-12) with DD, DCD or DD + DCD was used to explore their brain activity during procedural tasks, performed either after two weeks of training or in the early stage of learning. Firstly, our results indicate that all children were able to perform the task with the same level of automaticity, but recruit different brain processes to achieve the same performance. Secondly, our fMRI results do not appear to confirm Nicolson and Fawcett's model. The neural correlates recruited for procedural learning by the DD and the comorbid groups are very close, while the DCD group presents distinct characteristics. This provide a promising direction on the neural mechanisms associated with procedural learning in neurodevelopmental disorders and for understanding comorbidity. Published by Elsevier Ltd.

  11. Design and Modeling of RF Power Amplifiers with Radial Basis Function Artificial Neural Networks

    OpenAIRE

    Ali Reza Zirak; Sobhan Roshani

    2016-01-01

    A radial basis function (RBF) artificial neural network model for a designed high efficiency radio frequency class-F power amplifier (PA) is presented in this paper. The presented amplifier is designed at 1.8 GHz operating frequency with 12 dB of gain and 36 dBm of 1dB output compression point. The obtained power added efficiency (PAE) for the presented PA is 76% under 26 dBm input power. The proposed RBF model uses input and DC power of the PA as inputs variables and considers output power a...

  12. Neural Network Machine Learning and Dimension Reduction for Data Visualization

    Science.gov (United States)

    Liles, Charles A.

    2014-01-01

    Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

  13. Neural basis for dynamic updating of object representation in visual working memory.

    Science.gov (United States)

    Takahama, Sachiko; Miyauchi, Satoru; Saiki, Jun

    2010-02-15

    In real world, objects have multiple features and change dynamically. Thus, object representations must satisfy dynamic updating and feature binding. Previous studies have investigated the neural activity of dynamic updating or feature binding alone, but not both simultaneously. We investigated the neural basis of feature-bound object representation in a dynamically updating situation by conducting a multiple object permanence tracking task, which required observers to simultaneously process both the maintenance and dynamic updating of feature-bound objects. Using an event-related design, we separated activities during memory maintenance and change detection. In the search for regions showing selective activation in dynamic updating of feature-bound objects, we identified a network during memory maintenance that was comprised of the inferior precentral sulcus, superior parietal lobule, and middle frontal gyrus. In the change detection period, various prefrontal regions, including the anterior prefrontal cortex, were activated. In updating object representation of dynamically moving objects, the inferior precentral sulcus closely cooperates with a so-called "frontoparietal network", and subregions of the frontoparietal network can be decomposed into those sensitive to spatial updating and feature binding. The anterior prefrontal cortex identifies changes in object representation by comparing memory and perceptual representations rather than maintaining object representations per se, as previously suggested. Copyright 2009 Elsevier Inc. All rights reserved.

  14. Tracting the neural basis of music: Deficient structural connectivity underlying acquired amusia.

    Science.gov (United States)

    Sihvonen, Aleksi J; Ripollés, Pablo; Särkämö, Teppo; Leo, Vera; Rodríguez-Fornells, Antoni; Saunavaara, Jani; Parkkola, Riitta; Soinila, Seppo

    2017-12-01

    Acquired amusia provides a unique opportunity to investigate the fundamental neural architectures of musical processing due to the transition from a functioning to defective music processing system. Yet, the white matter (WM) deficits in amusia remain systematically unexplored. To evaluate which WM structures form the neural basis for acquired amusia and its recovery, we studied 42 stroke patients longitudinally at acute, 3-month, and 6-month post-stroke stages using DTI [tract-based spatial statistics (TBSS) and deterministic tractography (DT)] and the Scale and Rhythm subtests of the Montreal Battery of Evaluation of Amusia (MBEA). Non-recovered amusia was associated with structural damage and subsequent degeneration in multiple WM tracts including the right inferior fronto-occipital fasciculus (IFOF), arcuate fasciculus (AF), inferior longitudinal fasciculus (ILF), uncinate fasciculus (UF), and frontal aslant tract (FAT), as well as in the corpus callosum (CC) and its posterior part (tapetum). In a linear regression analysis, the volume of the right IFOF was the main predictor of MBEA performance across time. Overall, our results provide a comprehensive picture of the large-scale deficits in intra- and interhemispheric structural connectivity underlying amusia, and conversely highlight which pathways are crucial for normal music perception. Copyright © 2017 Elsevier Ltd. All rights reserved.

  15. A positron emission tomography study of the neural basis of informational and energetic masking effects in speech perception

    Science.gov (United States)

    Scott, Sophie K.; Rosen, Stuart; Wickham, Lindsay; Wise, Richard J. S.

    2004-02-01

    Positron emission tomography (PET) was used to investigate the neural basis of the comprehension of speech in unmodulated noise (``energetic'' masking, dominated by effects at the auditory periphery), and when presented with another speaker (``informational'' masking, dominated by more central effects). Each type of signal was presented at four different signal-to-noise ratios (SNRs) (+3, 0, -3, -6 dB for the speech-in-speech, +6, +3, 0, -3 dB for the speech-in-noise), with listeners instructed to listen for meaning to the target speaker. Consistent with behavioral studies, there was SNR-dependent activation associated with the comprehension of speech in noise, with no SNR-dependent activity for the comprehension of speech-in-speech (at low or negative SNRs). There was, in addition, activation in bilateral superior temporal gyri which was associated with the informational masking condition. The extent to which this activation of classical ``speech'' areas of the temporal lobes might delineate the neural basis of the informational masking is considered, as is the relationship of these findings to the interfering effects of unattended speech and sound on more explicit working memory tasks. This study is a novel demonstration of candidate neural systems involved in the perception of speech in noisy environments, and of the processing of multiple speakers in the dorso-lateral temporal lobes.

  16. Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

    Science.gov (United States)

    Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

    2018-05-10

    The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

  17. Biologically plausible learning in neural networks: a lesson from bacterial chemotaxis.

    Science.gov (United States)

    Shimansky, Yury P

    2009-12-01

    Learning processes in the brain are usually associated with plastic changes made to optimize the strength of connections between neurons. Although many details related to biophysical mechanisms of synaptic plasticity have been discovered, it is unclear how the concurrent performance of adaptive modifications in a huge number of spatial locations is organized to minimize a given objective function. Since direct experimental observation of even a relatively small subset of such changes is not feasible, computational modeling is an indispensable investigation tool for solving this problem. However, the conventional method of error back-propagation (EBP) employed for optimizing synaptic weights in artificial neural networks is not biologically plausible. This study based on computational experiments demonstrated that such optimization can be performed rather efficiently using the same general method that bacteria employ for moving closer to an attractant or away from a repellent. With regard to neural network optimization, this method consists of regulating the probability of an abrupt change in the direction of synaptic weight modification according to the temporal gradient of the objective function. Neural networks utilizing this method (regulation of modification probability, RMP) can be viewed as analogous to swimming in the multidimensional space of their parameters in the flow of biochemical agents carrying information about the optimality criterion. The efficiency of RMP is comparable to that of EBP, while RMP has several important advantages. Since the biological plausibility of RMP is beyond a reasonable doubt, the RMP concept provides a constructive framework for the experimental analysis of learning in natural neural networks.

  18. Neural Basis of Enhanced Executive Function in Older Video Game Players: An fMRI Study.

    Science.gov (United States)

    Wang, Ping; Zhu, Xing-Ting; Qi, Zhigang; Huang, Silin; Li, Hui-Jie

    2017-01-01

    Video games have been found to have positive influences on executive function in older adults; however, the underlying neural basis of the benefits from video games has been unclear. Adopting a task-based functional magnetic resonance imaging (fMRI) study targeted at the flanker task, the present study aims to explore the neural basis of the improved executive function in older adults with video game experiences. Twenty video game players (VGPs) and twenty non-video game players (NVGPs) of 60 years of age or older participated in the present study, and there are no significant differences in age ( t = 0.62, p = 0.536), gender ratio ( t = 1.29, p = 0.206) and years of education ( t = 1.92, p = 0.062) between VGPs and NVGPs. The results show that older VGPs present significantly better behavioral performance than NVGPs. Older VGPs activate greater than NVGPs in brain regions, mainly in frontal-parietal areas, including the right dorsolateral prefrontal cortex, the left supramarginal gyrus, the right angular gyrus, the right precuneus and the left paracentral lobule. The present study reveals that video game experiences may have positive influences on older adults in behavioral performance and the underlying brain activation. These results imply the potential role that video games can play as an effective tool to improve cognitive ability in older adults.

  19. Neural Basis of Enhanced Executive Function in Older Video Game Players: An fMRI Study

    Directory of Open Access Journals (Sweden)

    Ping Wang

    2017-11-01

    Full Text Available Video games have been found to have positive influences on executive function in older adults; however, the underlying neural basis of the benefits from video games has been unclear. Adopting a task-based functional magnetic resonance imaging (fMRI study targeted at the flanker task, the present study aims to explore the neural basis of the improved executive function in older adults with video game experiences. Twenty video game players (VGPs and twenty non-video game players (NVGPs of 60 years of age or older participated in the present study, and there are no significant differences in age (t = 0.62, p = 0.536, gender ratio (t = 1.29, p = 0.206 and years of education (t = 1.92, p = 0.062 between VGPs and NVGPs. The results show that older VGPs present significantly better behavioral performance than NVGPs. Older VGPs activate greater than NVGPs in brain regions, mainly in frontal-parietal areas, including the right dorsolateral prefrontal cortex, the left supramarginal gyrus, the right angular gyrus, the right precuneus and the left paracentral lobule. The present study reveals that video game experiences may have positive influences on older adults in behavioral performance and the underlying brain activation. These results imply the potential role that video games can play as an effective tool to improve cognitive ability in older adults.

  20. Automated sleep stage detection with a classical and a neural learning algorithm--methodological aspects.

    Science.gov (United States)

    Schwaibold, M; Schöchlin, J; Bolz, A

    2002-01-01

    For classification tasks in biosignal processing, several strategies and algorithms can be used. Knowledge-based systems allow prior knowledge about the decision process to be integrated, both by the developer and by self-learning capabilities. For the classification stages in a sleep stage detection framework, three inference strategies were compared regarding their specific strengths: a classical signal processing approach, artificial neural networks and neuro-fuzzy systems. Methodological aspects were assessed to attain optimum performance and maximum transparency for the user. Due to their effective and robust learning behavior, artificial neural networks could be recommended for pattern recognition, while neuro-fuzzy systems performed best for the processing of contextual information.

  1. Learning Universal Computations with Spikes

    Science.gov (United States)

    Thalmeier, Dominik; Uhlmann, Marvin; Kappen, Hilbert J.; Memmesheimer, Raoul-Martin

    2016-01-01

    Providing the neurobiological basis of information processing in higher animals, spiking neural networks must be able to learn a variety of complicated computations, including the generation of appropriate, possibly delayed reactions to inputs and the self-sustained generation of complex activity patterns, e.g. for locomotion. Many such computations require previous building of intrinsic world models. Here we show how spiking neural networks may solve these different tasks. Firstly, we derive constraints under which classes of spiking neural networks lend themselves to substrates of powerful general purpose computing. The networks contain dendritic or synaptic nonlinearities and have a constrained connectivity. We then combine such networks with learning rules for outputs or recurrent connections. We show that this allows to learn even difficult benchmark tasks such as the self-sustained generation of desired low-dimensional chaotic dynamics or memory-dependent computations. Furthermore, we show how spiking networks can build models of external world systems and use the acquired knowledge to control them. PMID:27309381

  2. Neural basis of decision making guided by emotional outcomes.

    Science.gov (United States)

    Katahira, Kentaro; Matsuda, Yoshi-Taka; Fujimura, Tomomi; Ueno, Kenichi; Asamizuya, Takeshi; Suzuki, Chisato; Cheng, Kang; Okanoya, Kazuo; Okada, Masato

    2015-05-01

    Emotional events resulting from a choice influence an individual's subsequent decision making. Although the relationship between emotion and decision making has been widely discussed, previous studies have mainly investigated decision outcomes that can easily be mapped to reward and punishment, including monetary gain/loss, gustatory stimuli, and pain. These studies regard emotion as a modulator of decision making that can be made rationally in the absence of emotions. In our daily lives, however, we often encounter various emotional events that affect decisions by themselves, and mapping the events to a reward or punishment is often not straightforward. In this study, we investigated the neural substrates of how such emotional decision outcomes affect subsequent decision making. By using functional magnetic resonance imaging (fMRI), we measured brain activities of humans during a stochastic decision-making task in which various emotional pictures were presented as decision outcomes. We found that pleasant pictures differentially activated the midbrain, fusiform gyrus, and parahippocampal gyrus, whereas unpleasant pictures differentially activated the ventral striatum, compared with neutral pictures. We assumed that the emotional decision outcomes affect the subsequent decision by updating the value of the options, a process modeled by reinforcement learning models, and that the brain regions representing the prediction error that drives the reinforcement learning are involved in guiding subsequent decisions. We found that some regions of the striatum and the insula were separately correlated with the prediction error for either pleasant pictures or unpleasant pictures, whereas the precuneus was correlated with prediction errors for both pleasant and unpleasant pictures. Copyright © 2015 the American Physiological Society.

  3. Neural basis of decision making guided by emotional outcomes

    Science.gov (United States)

    Matsuda, Yoshi-Taka; Fujimura, Tomomi; Ueno, Kenichi; Asamizuya, Takeshi; Suzuki, Chisato; Cheng, Kang; Okanoya, Kazuo; Okada, Masato

    2015-01-01

    Emotional events resulting from a choice influence an individual's subsequent decision making. Although the relationship between emotion and decision making has been widely discussed, previous studies have mainly investigated decision outcomes that can easily be mapped to reward and punishment, including monetary gain/loss, gustatory stimuli, and pain. These studies regard emotion as a modulator of decision making that can be made rationally in the absence of emotions. In our daily lives, however, we often encounter various emotional events that affect decisions by themselves, and mapping the events to a reward or punishment is often not straightforward. In this study, we investigated the neural substrates of how such emotional decision outcomes affect subsequent decision making. By using functional magnetic resonance imaging (fMRI), we measured brain activities of humans during a stochastic decision-making task in which various emotional pictures were presented as decision outcomes. We found that pleasant pictures differentially activated the midbrain, fusiform gyrus, and parahippocampal gyrus, whereas unpleasant pictures differentially activated the ventral striatum, compared with neutral pictures. We assumed that the emotional decision outcomes affect the subsequent decision by updating the value of the options, a process modeled by reinforcement learning models, and that the brain regions representing the prediction error that drives the reinforcement learning are involved in guiding subsequent decisions. We found that some regions of the striatum and the insula were separately correlated with the prediction error for either pleasant pictures or unpleasant pictures, whereas the precuneus was correlated with prediction errors for both pleasant and unpleasant pictures. PMID:25695644

  4. The interchangeability of learning rate and gain in backpropagation neural networks

    NARCIS (Netherlands)

    Thimm, G.; Moerland, P.; Fiesler, E.

    1996-01-01

    The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the gain of its activation function(s) is investigated. In specific, it is proven that changing the gain of the activation function is equivalent to changing the learning rate and the weights.

  5. Optimal Search Strategy of Robotic Assembly Based on Neural Vibration Learning

    Directory of Open Access Journals (Sweden)

    Lejla Banjanovic-Mehmedovic

    2011-01-01

    Full Text Available This paper presents implementation of optimal search strategy (OSS in verification of assembly process based on neural vibration learning. The application problem is the complex robot assembly of miniature parts in the example of mating the gears of one multistage planetary speed reducer. Assembly of tube over the planetary gears was noticed as the most difficult problem of overall assembly. The favourable influence of vibration and rotation movement on compensation of tolerance was also observed. With the proposed neural-network-based learning algorithm, it is possible to find extended scope of vibration state parameter. Using optimal search strategy based on minimal distance path between vibration parameter stage sets (amplitude and frequencies of robots gripe vibration and recovery parameter algorithm, we can improve the robot assembly behaviour, that is, allow the fastest possible way of mating. We have verified by using simulation programs that search strategy is suitable for the situation of unexpected events due to uncertainties.

  6. Neural basis of moral elevation demonstrated through inter-subject synchronization of cortical activity during free-viewing.

    Directory of Open Access Journals (Sweden)

    Zoë A Englander

    Full Text Available Most research investigating the neural basis of social emotions has examined emotions that give rise to negative evaluations of others (e.g. anger, disgust. Emotions triggered by the virtues and excellences of others have been largely ignored. Using fMRI, we investigated the neural basis of two "other-praising" emotions--Moral Elevation (a response to witnessing acts of moral beauty, and Admiration (which we restricted to admiration for physical skill.Ten participants viewed the same nine video clips. Three clips elicited moral elevation, three elicited admiration, and three were emotionally neutral. We then performed pair-wise voxel-by-voxel correlations of the BOLD signal between individuals for each video clip and a separate resting-state run. We observed a high degree of inter-subject synchronization, regardless of stimulus type, across several brain regions during free-viewing of videos. Videos in the elevation condition evoked significant inter-subject synchronization in brain regions previously implicated in self-referential and interoceptive processes, including the medial prefrontal cortex, precuneus, and insula. The degree of synchronization was highly variable over the course of the videos, with the strongest synchrony occurring during portions of the videos that were independently rated as most emotionally arousing. Synchrony in these same brain regions was not consistently observed during the admiration videos, and was absent for the neutral videos.Results suggest that the neural systems supporting moral elevation are remarkably consistent across subjects viewing the same emotional content. We demonstrate that model-free techniques such as inter-subject synchronization may be a useful tool for studying complex, context dependent emotions such as self-transcendent emotion.

  7. The neural basis of learning to spell again: An fMRI study of spelling training in acquired dysgraphia.

    Directory of Open Access Journals (Sweden)

    Jeremy Purcell

    2015-05-01

    1 For all participants we identified brain areas associated with a normalized response for the TRAINING words at the post-training time point. 2 For all participants we identified an up-regulation of the TRAINING response (i.e., the TRAINING neural response was initially low and then increased post-training; whereas in only one participant did we also observe a down-regulation of the training response (i.e., the TRAINING neural response was initially high, but then decreased post-training. 3 Although the areas associated with the normalized TRAINING response were different in each individual, they all include areas typically associated with the spelling system (Purcell et al. 2011, including the right homologues of typically left hemisphere spelling regions. Across the participants, the following areas of normalization were observed: bilateral superior temporal gyrus, inferior frontal gyrus, and the bilateral inferior temporal/fusiform gyrus. Discussion: We found that the predominant BOLD response to training involved an up-regulation of the neural response to spelling the TRAINING items. In addition, we found individual differences in the neurotopography of the normalization response patterns although all were with within brain areas that form a part of the spelling network(Purcell et al. 2011. This work provides evidence regarding one aspect of the multiplicity of neural responses associated with recovery of spelling in individuals with acquired dysgraphia.

  8. Forecasting financial asset processes: stochastic dynamics via learning neural networks.

    Science.gov (United States)

    Giebel, S; Rainer, M

    2010-01-01

    Models for financial asset dynamics usually take into account their inherent unpredictable nature by including a suitable stochastic component into their process. Unknown (forward) values of financial assets (at a given time in the future) are usually estimated as expectations of the stochastic asset under a suitable risk-neutral measure. This estimation requires the stochastic model to be calibrated to some history of sufficient length in the past. Apart from inherent limitations, due to the stochastic nature of the process, the predictive power is also limited by the simplifying assumptions of the common calibration methods, such as maximum likelihood estimation and regression methods, performed often without weights on the historic time series, or with static weights only. Here we propose a novel method of "intelligent" calibration, using learning neural networks in order to dynamically adapt the parameters of the stochastic model. Hence we have a stochastic process with time dependent parameters, the dynamics of the parameters being themselves learned continuously by a neural network. The back propagation in training the previous weights is limited to a certain memory length (in the examples we consider 10 previous business days), which is similar to the maximal time lag of autoregressive processes. We demonstrate the learning efficiency of the new algorithm by tracking the next-day forecasts for the EURTRY and EUR-HUF exchange rates each.

  9. A role for adult TLX-positive neural stem cells in learning and behaviour.

    Science.gov (United States)

    Zhang, Chun-Li; Zou, Yuhua; He, Weimin; Gage, Fred H; Evans, Ronald M

    2008-02-21

    Neurogenesis persists in the adult brain and can be regulated by a plethora of external stimuli, such as learning, memory, exercise, environment and stress. Although newly generated neurons are able to migrate and preferentially incorporate into the neural network, how these cells are molecularly regulated and whether they are required for any normal brain function are unresolved questions. The adult neural stem cell pool is composed of orphan nuclear receptor TLX-positive cells. Here, using genetic approaches in mice, we demonstrate that TLX (also called NR2E1) regulates adult neural stem cell proliferation in a cell-autonomous manner by controlling a defined genetic network implicated in cell proliferation and growth. Consequently, specific removal of TLX from the adult mouse brain through inducible recombination results in a significant reduction of stem cell proliferation and a marked decrement in spatial learning. In contrast, the resulting suppression of adult neurogenesis does not affect contextual fear conditioning, locomotion or diurnal rhythmic activities, indicating a more selective contribution of newly generated neurons to specific cognitive functions.

  10. Stochastic sensitivity analysis and Langevin simulation for neural network learning

    International Nuclear Information System (INIS)

    Koda, Masato

    1997-01-01

    A comprehensive theoretical framework is proposed for the learning of a class of gradient-type neural networks with an additive Gaussian white noise process. The study is based on stochastic sensitivity analysis techniques, and formal expressions are obtained for stochastic learning laws in terms of functional derivative sensitivity coefficients. The present method, based on Langevin simulation techniques, uses only the internal states of the network and ubiquitous noise to compute the learning information inherent in the stochastic correlation between noise signals and the performance functional. In particular, the method does not require the solution of adjoint equations of the back-propagation type. Thus, the present algorithm has the potential for efficiently learning network weights with significantly fewer computations. Application to an unfolded multi-layered network is described, and the results are compared with those obtained by using a back-propagation method

  11. Neural Basis of Video Gaming: A Systematic Review

    OpenAIRE

    Marc Palaus; Elena M. Marron; Raquel Viejo-Sobera; Raquel Viejo-Sobera; Diego Redolar-Ripoll

    2017-01-01

    Background: Video gaming is an increasingly popular activity in contemporary society, especially among young people, and video games are increasing in popularity not only as a research tool but also as a field of study. Many studies have focused on the neural and behavioral effects of video games, providing a great deal of video game derived brain correlates in recent decades. There is a great amount of information, obtained through a myriad of methods, providing neural correlates of video ga...

  12. Neural Basis of Video Gaming: A Systematic Review

    OpenAIRE

    Palaus, Marc; Marron, Elena M.; Viejo-Sobera, Raquel; Redolar-Ripoll, Diego

    2017-01-01

    Video gaming is an increasingly popular activity in contemporary society, especially among young people, and video games are increasing in popularity not only as a research tool but also as a field of study. Many studies have focused on the neural and behavioral effects of video games, providing a great deal of video game derived brain correlates in recent decades. There is a great amount of information, obtained through a myriad of methods, providing neural correlates of video games. We aim ...

  13. Adaptive neural network/expert system that learns fault diagnosis for different structures

    Science.gov (United States)

    Simon, Solomon H.

    1992-08-01

    Corporations need better real-time monitoring and control systems to improve productivity by watching quality and increasing production flexibility. The innovative technology to achieve this goal is evolving in the form artificial intelligence and neural networks applied to sensor processing, fusion, and interpretation. By using these advanced Al techniques, we can leverage existing systems and add value to conventional techniques. Neural networks and knowledge-based expert systems can be combined into intelligent sensor systems which provide real-time monitoring, control, evaluation, and fault diagnosis for production systems. Neural network-based intelligent sensor systems are more reliable because they can provide continuous, non-destructive monitoring and inspection. Use of neural networks can result in sensor fusion and the ability to model highly, non-linear systems. Improved models can provide a foundation for more accurate performance parameters and predictions. We discuss a research software/hardware prototype which integrates neural networks, expert systems, and sensor technologies and which can adapt across a variety of structures to perform fault diagnosis. The flexibility and adaptability of the prototype in learning two structures is presented. Potential applications are discussed.

  14. A Theoretical Basis for Adult Learning Facilitation: Review of Selected Articles

    Science.gov (United States)

    Muneja, Mussa S.

    2015-01-01

    The aim of this paper is to synthesize a theoretical basis for adult learning facilitation in order to provide a valuable systematic resource in the field of adult education. The paper has reviewed 6 journal articles with topics ranging from theory of andragogy; the effect of globalization on adult learning; the contribution of Malcolm Knowles;…

  15. Modeling and control of magnetorheological fluid dampers using neural networks

    Science.gov (United States)

    Wang, D. H.; Liao, W. H.

    2005-02-01

    Due to the inherent nonlinear nature of magnetorheological (MR) fluid dampers, one of the challenging aspects for utilizing these devices to achieve high system performance is the development of accurate models and control algorithms that can take advantage of their unique characteristics. In this paper, the direct identification and inverse dynamic modeling for MR fluid dampers using feedforward and recurrent neural networks are studied. The trained direct identification neural network model can be used to predict the damping force of the MR fluid damper on line, on the basis of the dynamic responses across the MR fluid damper and the command voltage, and the inverse dynamic neural network model can be used to generate the command voltage according to the desired damping force through supervised learning. The architectures and the learning methods of the dynamic neural network models and inverse neural network models for MR fluid dampers are presented, and some simulation results are discussed. Finally, the trained neural network models are applied to predict and control the damping force of the MR fluid damper. Moreover, validation methods for the neural network models developed are proposed and used to evaluate their performance. Validation results with different data sets indicate that the proposed direct identification dynamic model using the recurrent neural network can be used to predict the damping force accurately and the inverse identification dynamic model using the recurrent neural network can act as a damper controller to generate the command voltage when the MR fluid damper is used in a semi-active mode.

  16. The neural basis of responsibility attribution in decision-making.

    Directory of Open Access Journals (Sweden)

    Peng Li

    Full Text Available Social responsibility links personal behavior with societal expectations and plays a key role in affecting an agent's emotional state following a decision. However, the neural basis of responsibility attribution remains unclear. In two previous event-related brain potential (ERP studies we found that personal responsibility modulated outcome evaluation in gambling tasks. Here we conducted a functional magnetic resonance imaging (fMRI study to identify particular brain regions that mediate responsibility attribution. In a context involving team cooperation, participants completed a task with their teammates and on each trial received feedback about team success and individual success sequentially. We found that brain activity differed between conditions involving team success vs. team failure. Further, different brain regions were associated with reinforcement of behavior by social praise vs. monetary reward. Specifically, right temporoparietal junction (RTPJ was associated with social pride whereas dorsal striatum and dorsal anterior cingulate cortex (ACC were related to reinforcement of behaviors leading to personal gain. The present study provides evidence that the RTPJ is an important region for determining whether self-generated behaviors are deserving of praise in a social context.

  17. Incremental learning of perceptual and conceptual representations and the puzzle of neural repetition suppression.

    Science.gov (United States)

    Gotts, Stephen J

    2016-08-01

    Incremental learning models of long-term perceptual and conceptual knowledge hold that neural representations are gradually acquired over many individual experiences via Hebbian-like activity-dependent synaptic plasticity across cortical connections of the brain. In such models, variation in task relevance of information, anatomic constraints, and the statistics of sensory inputs and motor outputs lead to qualitative alterations in the nature of representations that are acquired. Here, the proposal that behavioral repetition priming and neural repetition suppression effects are empirical markers of incremental learning in the cortex is discussed, and research results that both support and challenge this position are reviewed. Discussion is focused on a recent fMRI-adaptation study from our laboratory that shows decoupling of experience-dependent changes in neural tuning, priming, and repetition suppression, with representational changes that appear to work counter to the explicit task demands. Finally, critical experiments that may help to clarify and resolve current challenges are outlined.

  18. Vibration control of uncertain multiple launch rocket system using radial basis function neural network

    Science.gov (United States)

    Li, Bo; Rui, Xiaoting

    2018-01-01

    Poor dispersion characteristics of rockets due to the vibration of Multiple Launch Rocket System (MLRS) have always restricted the MLRS development for several decades. Vibration control is a key technique to improve the dispersion characteristics of rockets. For a mechanical system such as MLRS, the major difficulty in designing an appropriate control strategy that can achieve the desired vibration control performance is to guarantee the robustness and stability of the control system under the occurrence of uncertainties and nonlinearities. To approach this problem, a computed torque controller integrated with a radial basis function neural network is proposed to achieve the high-precision vibration control for MLRS. In this paper, the vibration response of a computed torque controlled MLRS is described. The azimuth and elevation mechanisms of the MLRS are driven by permanent magnet synchronous motors and supposed to be rigid. First, the dynamic model of motor-mechanism coupling system is established using Lagrange method and field-oriented control theory. Then, in order to deal with the nonlinearities, a computed torque controller is designed to control the vibration of the MLRS when it is firing a salvo of rockets. Furthermore, to compensate for the lumped uncertainty due to parametric variations and un-modeled dynamics in the design of the computed torque controller, a radial basis function neural network estimator is developed to adapt the uncertainty based on Lyapunov stability theory. Finally, the simulated results demonstrate the effectiveness of the proposed control system and show that the proposed controller is robust with regard to the uncertainty.

  19. Neural basis for generalized quantifier comprehension.

    Science.gov (United States)

    McMillan, Corey T; Clark, Robin; Moore, Peachie; Devita, Christian; Grossman, Murray

    2005-01-01

    Generalized quantifiers like "all cars" are semantically well understood, yet we know little about their neural representation. Our model of quantifier processing includes a numerosity device, operations that combine number elements and working memory. Semantic theory posits two types of quantifiers: first-order quantifiers identify a number state (e.g. "at least 3") and higher-order quantifiers additionally require maintaining a number state actively in working memory for comparison with another state (e.g. "less than half"). We used BOLD fMRI to test the hypothesis that all quantifiers recruit inferior parietal cortex associated with numerosity, while only higher-order quantifiers recruit prefrontal cortex associated with executive resources like working memory. Our findings showed that first-order and higher-order quantifiers both recruit right inferior parietal cortex, suggesting that a numerosity component contributes to quantifier comprehension. Moreover, only probes of higher-order quantifiers recruited right dorsolateral prefrontal cortex, suggesting involvement of executive resources like working memory. We also observed activation of thalamus and anterior cingulate that may be associated with selective attention. Our findings are consistent with a large-scale neural network centered in frontal and parietal cortex that supports comprehension of generalized quantifiers.

  20. Chaos Synchronization Using Adaptive Dynamic Neural Network Controller with Variable Learning Rates

    Directory of Open Access Journals (Sweden)

    Chih-Hong Kao

    2011-01-01

    Full Text Available This paper addresses the synchronization of chaotic gyros with unknown parameters and external disturbance via an adaptive dynamic neural network control (ADNNC system. The proposed ADNNC system is composed of a neural controller and a smooth compensator. The neural controller uses a dynamic RBF (DRBF network to online approximate an ideal controller. The DRBF network can create new hidden neurons online if the input data falls outside the hidden layer and prune the insignificant hidden neurons online if the hidden neuron is inappropriate. The smooth compensator is designed to compensate for the approximation error between the neural controller and the ideal controller. Moreover, the variable learning rates of the parameter adaptation laws are derived based on a discrete-type Lyapunov function to speed up the convergence rate of the tracking error. Finally, the simulation results which verified the chaotic behavior of two nonlinear identical chaotic gyros can be synchronized using the proposed ADNNC scheme.

  1. Sentiment analysis: a comparison of deep learning neural network algorithm with SVM and naϊve Bayes for Indonesian text

    Science.gov (United States)

    Calvin Frans Mariel, Wahyu; Mariyah, Siti; Pramana, Setia

    2018-03-01

    Deep learning is a new era of machine learning techniques that essentially imitate the structure and function of the human brain. It is a development of deeper Artificial Neural Network (ANN) that uses more than one hidden layer. Deep Learning Neural Network has a great ability on recognizing patterns from various data types such as picture, audio, text, and many more. In this paper, the authors tries to measure that algorithm’s ability by applying it into the text classification. The classification task herein is done by considering the content of sentiment in a text which is also called as sentiment analysis. By using several combinations of text preprocessing and feature extraction techniques, we aim to compare the precise modelling results of Deep Learning Neural Network with the other two commonly used algorithms, the Naϊve Bayes and Support Vector Machine (SVM). This algorithm comparison uses Indonesian text data with balanced and unbalanced sentiment composition. Based on the experimental simulation, Deep Learning Neural Network clearly outperforms the Naϊve Bayes and SVM and offers a better F-1 Score while for the best feature extraction technique which improves that modelling result is Bigram.

  2. Have we met before? Neural correlates of emotional learning in women with social phobia.

    Science.gov (United States)

    Laeger, Inga; Keuper, Kati; Heitmann, Carina; Kugel, Harald; Dobel, Christian; Eden, Annuschka; Arolt, Volker; Zwitserlood, Pienie; Dannlowski, Udo; Zwanzger, Peter

    2014-05-01

    Altered memory processes are thought to be a key mechanism in the etiology of anxiety disorders, but little is known about the neural correlates of fear learning and memory biases in patients with social phobia. The present study therefore examined whether patients with social phobia exhibit different patterns of neural activation when confronted with recently acquired emotional stimuli. Patients with social phobia and a group of healthy controls learned to associate pseudonames with pictures of persons displaying either a fearful or a neutral expression. The next day, participants read the pseudonames in the magnetic resonance imaging scanner. Afterwards, 2 memory tests were carried out. We enrolled 21 patients and 21 controls in our study. There were no group differences for learning performance, and results of the memory tests were mixed. On a neural level, patients showed weaker amygdala activation than controls for the contrast of names previously associated with fearful versus neutral faces. Social phobia severity was negatively related to amygdala activation. Moreover, a detailed psychophysiological interaction analysis revealed an inverse correlation between disorder severity and frontolimbic connectivity for the emotional > neutral pseudonames contrast. Our sample included only women. Our results support the theory of a disturbed cortico limbic interplay, even for recently learned emotional stimuli. We discuss the findings with regard to the vigilance-avoidance theory and contrast them to results indicating an oversensitive limbic system in patients with social phobia.

  3. Reinforcement Learning of Linking and Tracing Contours in Recurrent Neural Networks

    Science.gov (United States)

    Brosch, Tobias; Neumann, Heiko; Roelfsema, Pieter R.

    2015-01-01

    The processing of a visual stimulus can be subdivided into a number of stages. Upon stimulus presentation there is an early phase of feedforward processing where the visual information is propagated from lower to higher visual areas for the extraction of basic and complex stimulus features. This is followed by a later phase where horizontal connections within areas and feedback connections from higher areas back to lower areas come into play. In this later phase, image elements that are behaviorally relevant are grouped by Gestalt grouping rules and are labeled in the cortex with enhanced neuronal activity (object-based attention in psychology). Recent neurophysiological studies revealed that reward-based learning influences these recurrent grouping processes, but it is not well understood how rewards train recurrent circuits for perceptual organization. This paper examines the mechanisms for reward-based learning of new grouping rules. We derive a learning rule that can explain how rewards influence the information flow through feedforward, horizontal and feedback connections. We illustrate the efficiency with two tasks that have been used to study the neuronal correlates of perceptual organization in early visual cortex. The first task is called contour-integration and demands the integration of collinear contour elements into an elongated curve. We show how reward-based learning causes an enhancement of the representation of the to-be-grouped elements at early levels of a recurrent neural network, just as is observed in the visual cortex of monkeys. The second task is curve-tracing where the aim is to determine the endpoint of an elongated curve composed of connected image elements. If trained with the new learning rule, neural networks learn to propagate enhanced activity over the curve, in accordance with neurophysiological data. We close the paper with a number of model predictions that can be tested in future neurophysiological and computational studies

  4. Neural Basis of Brain Dysfunction Produced by Early Sleep Problems

    Directory of Open Access Journals (Sweden)

    Jun Kohyama

    2016-01-01

    Full Text Available There is a wealth of evidence that disrupted sleep and circadian rhythms, which are common in modern society even during the early stages of life, have unfavorable effects on brain function. Altered brain function can cause problem behaviors later in life, such as truancy from or dropping out of school, quitting employment, and committing suicide. In this review, we discuss findings from several large cohort studies together with recent results of a cohort study using the marshmallow test, which was first introduced in the 1960s. This test assessed the ability of four-year-olds to delay gratification and showed how this ability correlated with success later in life. The role of the serotonergic system in sleep and how this role changes with age are also discussed. The serotonergic system is involved in reward processing and interactions with the dorsal striatum, ventral striatum, and the prefrontal cortex are thought to comprise the neural basis for behavioral patterns that are affected by the quantity, quality, and timing of sleep early in life.

  5. Neural Basis of Brain Dysfunction Produced by Early Sleep Problems.

    Science.gov (United States)

    Kohyama, Jun

    2016-01-29

    There is a wealth of evidence that disrupted sleep and circadian rhythms, which are common in modern society even during the early stages of life, have unfavorable effects on brain function. Altered brain function can cause problem behaviors later in life, such as truancy from or dropping out of school, quitting employment, and committing suicide. In this review, we discuss findings from several large cohort studies together with recent results of a cohort study using the marshmallow test, which was first introduced in the 1960s. This test assessed the ability of four-year-olds to delay gratification and showed how this ability correlated with success later in life. The role of the serotonergic system in sleep and how this role changes with age are also discussed. The serotonergic system is involved in reward processing and interactions with the dorsal striatum, ventral striatum, and the prefrontal cortex are thought to comprise the neural basis for behavioral patterns that are affected by the quantity, quality, and timing of sleep early in life.

  6. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

    International Nuclear Information System (INIS)

    Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

    2016-01-01

    There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. Furthermore, the Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.

  7. Distributed Extreme Learning Machine for Nonlinear Learning over Network

    Directory of Open Access Journals (Sweden)

    Songyan Huang

    2015-02-01

    Full Text Available Distributed data collection and analysis over a network are ubiquitous, especially over a wireless sensor network (WSN. To our knowledge, the data model used in most of the distributed algorithms is linear. However, in real applications, the linearity of systems is not always guaranteed. In nonlinear cases, the single hidden layer feedforward neural network (SLFN with radial basis function (RBF hidden neurons has the ability to approximate any continuous functions and, thus, may be used as the nonlinear learning system. However, confined by the communication cost, using the distributed version of the conventional algorithms to train the neural network directly is usually prohibited. Fortunately, based on the theorems provided in the extreme learning machine (ELM literature, we only need to compute the output weights of the SLFN. Computing the output weights itself is a linear learning problem, although the input-output mapping of the overall SLFN is still nonlinear. Using the distributed algorithmto cooperatively compute the output weights of the SLFN, we obtain a distributed extreme learning machine (dELM for nonlinear learning in this paper. This dELM is applied to the regression problem and classification problem to demonstrate its effectiveness and advantages.

  8. Neural basis of feature-based contextual effects on visual search behavior

    Directory of Open Access Journals (Sweden)

    Kelly eShen

    2012-01-01

    Full Text Available Searching for a visual object is known to be adaptable to context, and it is thought to result from the selection of neural representations distributed on a visual salience map, wherein stimulus-driven and goal-directed signals are combined. Here we investigated the neural basis of this adaptability by recording superior colliculus (SC neurons while three female rhesus monkeys (Macaca mulatta searched with saccadic eye movements for a target presented in an array of visual stimuli whose feature composition varied from trial to trial. We found that sensory-motor activity associated with distracters was enhanced or suppressed depending on the search array composition and that it corresponded to the monkey's search strategy, as assessed by the distribution of the occasional errant saccades. This feature-related modulation occurred independently from the saccade goal and facilitated the process of saccade target selection. We also observed feature-related enhancement in the activity associated with distracters that had been the search target during the previous session. Consistent with recurrent processing, both feature-related neuronal modulations occurred more than 60 ms after the onset of the visually evoked responses, and their near coincidence with the time of saccade target selection suggests that they are integral to this process. These results suggest that SC neuronal activity is shaped by the visual context as dictated by both stimulus-driven and goal-directed signals. Given the close proximity of the SC to the motor circuit, our findings suggest a direct link between perception and action and no need for distinct salience and motor maps.

  9. Neural substrates underlying stimulation-enhanced motor skill learning after stroke.

    Science.gov (United States)

    Lefebvre, Stéphanie; Dricot, Laurence; Laloux, Patrice; Gradkowski, Wojciech; Desfontaines, Philippe; Evrard, Frédéric; Peeters, André; Jamart, Jacques; Vandermeeren, Yves

    2015-01-01

    Motor skill learning is one of the key components of motor function recovery after stroke, especially recovery driven by neurorehabilitation. Transcranial direct current stimulation can enhance neurorehabilitation and motor skill learning in stroke patients. However, the neural mechanisms underlying the retention of stimulation-enhanced motor skill learning involving a paretic upper limb have not been resolved. These neural substrates were explored by means of functional magnetic resonance imaging. Nineteen chronic hemiparetic stroke patients participated in a double-blind, cross-over randomized, sham-controlled experiment with two series. Each series consisted of two sessions: (i) an intervention session during which dual transcranial direct current stimulation or sham was applied during motor skill learning with the paretic upper limb; and (ii) an imaging session 1 week later, during which the patients performed the learned motor skill. The motor skill learning task, called the 'circuit game', involves a speed/accuracy trade-off and consists of moving a pointer controlled by a computer mouse along a complex circuit as quickly and accurately as possible. Relative to the sham series, dual transcranial direct current stimulation applied bilaterally over the primary motor cortex during motor skill learning with the paretic upper limb resulted in (i) enhanced online motor skill learning; (ii) enhanced 1-week retention; and (iii) superior transfer of performance improvement to an untrained task. The 1-week retention's enhancement driven by the intervention was associated with a trend towards normalization of the brain activation pattern during performance of the learned motor skill relative to the sham series. A similar trend towards normalization relative to sham was observed during performance of a simple, untrained task without a speed/accuracy constraint, despite a lack of behavioural difference between the dual transcranial direct current stimulation and sham

  10. Modeling the behavioral substrates of associate learning and memory - Adaptive neural models

    Science.gov (United States)

    Lee, Chuen-Chien

    1991-01-01

    Three adaptive single-neuron models based on neural analogies of behavior modification episodes are proposed, which attempt to bridge the gap between psychology and neurophysiology. The proposed models capture the predictive nature of Pavlovian conditioning, which is essential to the theory of adaptive/learning systems. The models learn to anticipate the occurrence of a conditioned response before the presence of a reinforcing stimulus when training is complete. Furthermore, each model can find the most nonredundant and earliest predictor of reinforcement. The behavior of the models accounts for several aspects of basic animal learning phenomena in Pavlovian conditioning beyond previous related models. Computer simulations show how well the models fit empirical data from various animal learning paradigms.

  11. Learning Orthographic Structure With Sequential Generative Neural Networks.

    Science.gov (United States)

    Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

    2016-04-01

    Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. Copyright © 2015 Cognitive Science Society, Inc.

  12. Self-teaching neural network learns difficult reactor control problem

    International Nuclear Information System (INIS)

    Jouse, W.C.

    1989-01-01

    A self-teaching neural network used as an adaptive controller quickly learns to control an unstable reactor configuration. The network models the behavior of a human operator. It is trained by allowing it to operate the reactivity control impulsively. It is punished whenever either the power or fuel temperature stray outside technical limits. Using a simple paradigm, the network constructs an internal representation of the punishment and of the reactor system. The reactor is constrained to small power orbits

  13. Application of radial basis function neural network to predict soil sorption partition coefficient using topological descriptors.

    Science.gov (United States)

    Sabour, Mohammad Reza; Moftakhari Anasori Movahed, Saman

    2017-02-01

    The soil sorption partition coefficient logK oc is an indispensable parameter that can be used in assessing the environmental risk of organic chemicals. In order to predict soil sorption partition coefficient for different and even unknown compounds in a fast and accurate manner, a radial basis function neural network (RBFNN) model was developed. Eight topological descriptors of 800 organic compounds were used as inputs of the model. These 800 organic compounds were chosen from a large and very diverse data set. Generalized Regression Neural Network (GRNN) was utilized as the function in this neural network model due to its capability to adapt very quickly. Hence, it can be used to predict logK oc for new chemicals, as well. Out of total data set, 560 organic compounds were used for training and 240 to test efficiency of the model. The obtained results indicate that the model performance is very well. The correlation coefficients (R2) for training and test sets were 0.995 and 0.933, respectively. The root-mean square errors (RMSE) were 0.2321 for training set and 0.413 for test set. As the results for both training and test set are extremely satisfactory, the proposed neural network model can be employed not only to predict logK oc of known compounds, but also to be adaptive for prediction of this value precisely for new products that enter the market each year. Copyright © 2016 Elsevier Ltd. All rights reserved.

  14. A Sliding Mode Control-based on a RBF Neural Network for Deburring Industry Robotic Systems

    OpenAIRE

    Tao, Yong; Zheng, Jiaqi; Lin, Yuanchang

    2016-01-01

    A sliding mode control method based on radial basis function (RBF) neural network is proposed for the deburring of industry robotic systems. First, a dynamic model for deburring the robot system is established. Then, a conventional SMC scheme is introduced for the joint position tracking of robot manipulators. The RBF neural network based sliding mode control (RBFNN-SMC) has the ability to learn uncertain control actions. In the RBFNN-SMC scheme, the adaptive tuning algorithms for network par...

  15. Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications

    International Nuclear Information System (INIS)

    Reifman, J.; Vitela, J.E.

    1994-01-01

    The method of conjugate gradients is used to expedite the learning process of feedforward multilayer artificial neural networks and to systematically update both the learning parameter and the momentum parameter at each training cycle. The mechanism for the occurrence of premature saturation of the network nodes observed with the back propagation algorithm is described, suggestions are made to eliminate this undesirable phenomenon, and the reason by which this phenomenon is precluded in the method of conjugate gradients is presented. The proposed method is compared with the standard back propagation algorithm in the training of neural networks to classify transient events in neural power plants simulated by the Midland Nuclear Power Plant Unit 2 simulator. The comparison results indicate that the rate of convergence of the proposed method is much greater than the standard back propagation, that it reduces both the number of training cycles and the CPU time, and that it is less sensitive to the choice of initial weights. The advantages of the method are more noticeable and important for problems where the network architecture consists of a large number of nodes, the training database is large, and a tight convergence criterion is desired

  16. Biologically based neural circuit modelling for the study of fear learning and extinction

    Science.gov (United States)

    Nair, Satish S.; Paré, Denis; Vicentic, Aleksandra

    2016-11-01

    The neuronal systems that promote protective defensive behaviours have been studied extensively using Pavlovian conditioning. In this paradigm, an initially neutral-conditioned stimulus is paired with an aversive unconditioned stimulus leading the subjects to display behavioural signs of fear. Decades of research into the neural bases of this simple behavioural paradigm uncovered that the amygdala, a complex structure comprised of several interconnected nuclei, is an essential part of the neural circuits required for the acquisition, consolidation and expression of fear memory. However, emerging evidence from the confluence of electrophysiological, tract tracing, imaging, molecular, optogenetic and chemogenetic methodologies, reveals that fear learning is mediated by multiple connections between several amygdala nuclei and their distributed targets, dynamical changes in plasticity in local circuit elements as well as neuromodulatory mechanisms that promote synaptic plasticity. To uncover these complex relations and analyse multi-modal data sets acquired from these studies, we argue that biologically realistic computational modelling, in conjunction with experiments, offers an opportunity to advance our understanding of the neural circuit mechanisms of fear learning and to address how their dysfunction may lead to maladaptive fear responses in mental disorders.

  17. Neural signals of vicarious extinction learning.

    Science.gov (United States)

    Golkar, Armita; Haaker, Jan; Selbing, Ida; Olsson, Andreas

    2016-10-01

    Social transmission of both threat and safety is ubiquitous, but little is known about the neural circuitry underlying vicarious safety learning. This is surprising given that these processes are critical to flexibly adapt to a changeable environment. To address how the expression of previously learned fears can be modified by the transmission of social information, two conditioned stimuli (CS + s) were paired with shock and the third was not. During extinction, we held constant the amount of direct, non-reinforced, exposure to the CSs (i.e. direct extinction), and critically varied whether another individual-acting as a demonstrator-experienced safety (CS + vic safety) or aversive reinforcement (CS + vic reinf). During extinction, ventromedial prefrontal cortex (vmPFC) responses to the CS + vic reinf increased but decreased to the CS + vic safety This pattern of vmPFC activity was reversed during a subsequent fear reinstatement test, suggesting a temporal shift in the involvement of the vmPFC. Moreover, only the CS + vic reinf association recovered. Our data suggest that vicarious extinction prevents the return of conditioned fear responses, and that this efficacy is reflected by diminished vmPFC involvement during extinction learning. The present findings may have important implications for understanding how social information influences the persistence of fear memories in individuals suffering from emotional disorders. © The Author (2016). Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

  18. An enhanced radial basis function network for short-term electricity price forecasting

    International Nuclear Information System (INIS)

    Lin, Whei-Min; Gow, Hong-Jey; Tsai, Ming-Tang

    2010-01-01

    This paper proposed a price forecasting system for electric market participants to reduce the risk of price volatility. Combining the Radial Basis Function Network (RBFN) and Orthogonal Experimental Design (OED), an Enhanced Radial Basis Function Network (ERBFN) has been proposed for the solving process. The Locational Marginal Price (LMP), system load, transmission flow and temperature of the PJM system were collected and the data clusters were embedded in the Excel Database according to the year, season, workday and weekend. With the OED applied to learning rates in the ERBFN, the forecasting error can be reduced during the training process to improve both accuracy and reliability. This would mean that even the ''spikes'' could be tracked closely. The Back-propagation Neural Network (BPN), Probability Neural Network (PNN), other algorithms, and the proposed ERBFN were all developed and compared to check the performance. Simulation results demonstrated the effectiveness of the proposed ERBFN to provide quality information in a price volatile environment. (author)

  19. Learning to read words in a new language shapes the neural organization of the prior languages.

    Science.gov (United States)

    Mei, Leilei; Xue, Gui; Lu, Zhong-Lin; Chen, Chuansheng; Zhang, Mingxia; He, Qinghua; Wei, Miao; Dong, Qi

    2014-12-01

    Learning a new language entails interactions with one׳s prior language(s). Much research has shown how native language affects the cognitive and neural mechanisms of a new language, but little is known about whether and how learning a new language shapes the neural mechanisms of prior language(s). In two experiments in the current study, we used an artificial language training paradigm in combination with an fMRI to examine (1) the effects of different linguistic components (phonology and semantics) of a new language on the neural process of prior languages (i.e., native and second languages), and (2) whether such effects were modulated by the proficiency level in the new language. Results of Experiment 1 showed that when the training in a new language involved semantics (as opposed to only visual forms and phonology), neural activity during word reading in the native language (Chinese) was reduced in several reading-related regions, including the left pars opercularis, pars triangularis, bilateral inferior temporal gyrus, fusiform gyrus, and inferior occipital gyrus. Results of Experiment 2 replicated the results of Experiment 1 and further found that semantic training also affected neural activity during word reading in the subjects׳ second language (English). Furthermore, we found that the effects of the new language were modulated by the subjects׳ proficiency level in the new language. These results provide critical imaging evidence for the influence of learning to read words in a new language on word reading in native and second languages. Copyright © 2014 Elsevier Ltd. All rights reserved.

  20. The neural basis of unconditional love.

    Science.gov (United States)

    Beauregard, Mario; Courtemanche, Jérôme; Paquette, Vincent; St-Pierre, Evelyne Landry

    2009-05-15

    Functional neuroimaging studies have shown that romantic love and maternal love are mediated by regions specific to each, as well as overlapping regions in the brain's reward system. Nothing is known yet regarding the neural underpinnings of unconditional love. The main goal of this functional magnetic resonance imaging study was to identify the brain regions supporting this form of love. Participants were scanned during a control condition and an experimental condition. In the control condition, participants were instructed to simply look at a series of pictures depicting individuals with intellectual disabilities. In the experimental condition, participants were instructed to feel unconditional love towards the individuals depicted in a series of similar pictures. Significant loci of activation were found, in the experimental condition compared with the control condition, in the middle insula, superior parietal lobule, right periaqueductal gray, right globus pallidus (medial), right caudate nucleus (dorsal head), left ventral tegmental area and left rostro-dorsal anterior cingulate cortex. These results suggest that unconditional love is mediated by a distinct neural network relative to that mediating other emotions. This network contains cerebral structures known to be involved in romantic love or maternal love. Some of these structures represent key components of the brain's reward system.

  1. Identifying beneficial task relations for multi-task learning in deep neural networks

    DEFF Research Database (Denmark)

    Bingel, Joachim; Søgaard, Anders

    2017-01-01

    Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing interest due to some compelling benefits, including its potential to efficiently regularize models and to reduce the need for labeled data. While it has brought significant improvements in a number of NLP...

  2. Reliability analysis of C-130 turboprop engine components using artificial neural network

    Science.gov (United States)

    Qattan, Nizar A.

    In this study, we predict the failure rate of Lockheed C-130 Engine Turbine. More than thirty years of local operational field data were used for failure rate prediction and validation. The Weibull regression model and the Artificial Neural Network model including (feed-forward back-propagation, radial basis neural network, and multilayer perceptron neural network model); will be utilized to perform this study. For this purpose, the thesis will be divided into five major parts. First part deals with Weibull regression model to predict the turbine general failure rate, and the rate of failures that require overhaul maintenance. The second part will cover the Artificial Neural Network (ANN) model utilizing the feed-forward back-propagation algorithm as a learning rule. The MATLAB package will be used in order to build and design a code to simulate the given data, the inputs to the neural network are the independent variables, the output is the general failure rate of the turbine, and the failures which required overhaul maintenance. In the third part we predict the general failure rate of the turbine and the failures which require overhaul maintenance, using radial basis neural network model on MATLAB tool box. In the fourth part we compare the predictions of the feed-forward back-propagation model, with that of Weibull regression model, and radial basis neural network model. The results show that the failure rate predicted by the feed-forward back-propagation artificial neural network model is closer in agreement with radial basis neural network model compared with the actual field-data, than the failure rate predicted by the Weibull model. By the end of the study, we forecast the general failure rate of the Lockheed C-130 Engine Turbine, the failures which required overhaul maintenance and six categorical failures using multilayer perceptron neural network (MLP) model on DTREG commercial software. The results also give an insight into the reliability of the engine

  3. Using c-Jun to identify fear extinction learning-specific patterns of neural activity that are affected by single prolonged stress.

    Science.gov (United States)

    Knox, Dayan; Stanfield, Briana R; Staib, Jennifer M; David, Nina P; DePietro, Thomas; Chamness, Marisa; Schneider, Elizabeth K; Keller, Samantha M; Lawless, Caroline

    2018-04-02

    Neural circuits via which stress leads to disruptions in fear extinction is often explored in animal stress models. Using the single prolonged stress (SPS) model of post traumatic stress disorder and the immediate early gene (IEG) c-Fos as a measure of neural activity, we previously identified patterns of neural activity through which SPS disrupts extinction retention. However, none of these stress effects were specific to fear or extinction learning and memory. C-Jun is another IEG that is sometimes regulated in a different manner to c-Fos and could be used to identify emotional learning/memory specific patterns of neural activity that are sensitive to SPS. Animals were either fear conditioned (CS-fear) or presented with CSs only (CS-only) then subjected to extinction training and testing. C-Jun was then assayed within neural substrates critical for extinction memory. Inhibited c-Jun levels in the hippocampus (Hipp) and enhanced functional connectivity between the ventromedial prefrontal cortex (vmPFC) and basolateral amygdala (BLA) during extinction training was disrupted by SPS in the CS-fear group only. As a result, these effects were specific to emotional learning/memory. SPS also disrupted inhibited Hipp c-Jun levels, enhanced BLA c-Jun levels, and altered functional connectivity among the vmPFC, BLA, and Hipp during extinction testing in SPS rats in the CS-fear and CS-only groups. As a result, these effects were not specific to emotional learning/memory. Our findings suggest that SPS disrupts neural activity specific to extinction memory, but may also disrupt the retention of fear extinction by mechanisms that do not involve emotional learning/memory. Copyright © 2017 Elsevier B.V. All rights reserved.

  4. Psycho-neural Identity as the Basis for Empirical Research and Theorization in Psychology: An Interview with Mario A. Bunge

    Science.gov (United States)

    Virues-Ortega, Javier; Hurtado-Parrado, Camilo; Martin, Toby L.; Julio, Flávia

    2012-10-01

    Mario Bunge is one of the most prolific philosophers of our time. Over the past sixty years he has written extensively about semantics, ontology, epistemology, philosophy of science and ethics. Bunge has been interested in the philosophical and methodological implications of modern psychology and more specifically in the philosophies of the relation between the neural and psychological realms. According to Bunge, functionalism, the philosophical stand of current psychology, has limited explanatory power in that neural processes are not explicitly acknowledged as components or factors of psychological phenomena. In Matter and Mind (2010), Bunge has elaborated in great detail the philosophies of the mind-brain dilemma and the basis of the psychoneural identity hypothesis, which suggests that all psychological processes can be analysed in terms of neural and physical phenomena. This article is the result of a long interview with Dr. Bunge on psychoneural identity and brain-behaviour relations.

  5. Relabeling exchange method (REM) for learning in neural networks

    Science.gov (United States)

    Wu, Wen; Mammone, Richard J.

    1994-02-01

    The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

  6. A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.

    Science.gov (United States)

    Siri, Benoît; Berry, Hugues; Cessac, Bruno; Delord, Bruno; Quoy, Mathias

    2008-12-01

    We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule, including passive forgetting and different timescales, for neuronal activity and learning dynamics. Previous numerical work has reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on neural network evolution. Furthermore, we show that sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.

  7. From phonemes to images : levels of representation in a recurrent neural model of visually-grounded language learning

    NARCIS (Netherlands)

    Gelderloos, L.J.; Chrupala, Grzegorz

    2016-01-01

    We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover

  8. Neural Pattern Similarity in the Left IFG and Fusiform Is Associated with Novel Word Learning

    Directory of Open Access Journals (Sweden)

    Jing Qu

    2017-08-01

    Full Text Available Previous studies have revealed that greater neural pattern similarity across repetitions is associated with better subsequent memory. In this study, we used an artificial language training paradigm and representational similarity analysis to examine whether neural pattern similarity across repetitions before training was associated with post-training behavioral performance. Twenty-four native Chinese speakers were trained to learn a logographic artificial language for 12 days and behavioral performance was recorded using the word naming and picture naming tasks. Participants were scanned while performing a passive viewing task before training, after 4-day training and after 12-day training. Results showed that pattern similarity in the left pars opercularis (PO and fusiform gyrus (FG before training was negatively associated with reaction time (RT in both word naming and picture naming tasks after training. These results suggest that neural pattern similarity is an effective neurofunctional predictor of novel word learning in addition to word memory.

  9. Neural Pattern Similarity in the Left IFG and Fusiform Is Associated with Novel Word Learning

    Science.gov (United States)

    Qu, Jing; Qian, Liu; Chen, Chuansheng; Xue, Gui; Li, Huiling; Xie, Peng; Mei, Leilei

    2017-01-01

    Previous studies have revealed that greater neural pattern similarity across repetitions is associated with better subsequent memory. In this study, we used an artificial language training paradigm and representational similarity analysis to examine whether neural pattern similarity across repetitions before training was associated with post-training behavioral performance. Twenty-four native Chinese speakers were trained to learn a logographic artificial language for 12 days and behavioral performance was recorded using the word naming and picture naming tasks. Participants were scanned while performing a passive viewing task before training, after 4-day training and after 12-day training. Results showed that pattern similarity in the left pars opercularis (PO) and fusiform gyrus (FG) before training was negatively associated with reaction time (RT) in both word naming and picture naming tasks after training. These results suggest that neural pattern similarity is an effective neurofunctional predictor of novel word learning in addition to word memory. PMID:28878640

  10. Optogenetics in the Teaching Laboratory: Using Channelrhodopsin-2 to Study the Neural Basis of Behavior and Synaptic Physiology in "Drosophila"

    Science.gov (United States)

    Pulver, Stefan R.; Hornstein, Nicholas J.; Land, Bruce L.; Johnson, Bruce R.

    2011-01-01

    Here we incorporate recent advances in "Drosophila" neurogenetics and "optogenetics" into neuroscience laboratory exercises. We used the light-activated ion channel channelrhodopsin-2 (ChR2) and tissue-specific genetic expression techniques to study the neural basis of behavior in "Drosophila" larvae. We designed and implemented exercises using…

  11. Concurrent Unimodal Learning Enhances Multisensory Responses of Bi-Directional Crossmodal Learning in Robotic Audio-Visual Tracking

    DEFF Research Database (Denmark)

    Shaikh, Danish; Bodenhagen, Leon; Manoonpong, Poramate

    2018-01-01

    modalities to independently update modality-specific neural weights on a moment-by-moment basis, in response to dynamic changes in noisy sensory stimuli. The circuit is embodied as a non-holonomic robotic agent that must orient a towards a moving audio-visual target. The circuit continuously learns the best...

  12. Application of artificial neural network with extreme learning machine for economic growth estimation

    Science.gov (United States)

    Milačić, Ljubiša; Jović, Srđan; Vujović, Tanja; Miljković, Jovica

    2017-01-01

    The purpose of this research is to develop and apply the artificial neural network (ANN) with extreme learning machine (ELM) to forecast gross domestic product (GDP) growth rate. The economic growth forecasting was analyzed based on agriculture, manufacturing, industry and services value added in GDP. The results were compared with ANN with back propagation (BP) learning approach since BP could be considered as conventional learning methodology. The reliability of the computational models was accessed based on simulation results and using several statistical indicators. Based on results, it was shown that ANN with ELM learning methodology can be applied effectively in applications of GDP forecasting.

  13. Cognitive processes and neural basis of language switching: proposal of a new model.

    Science.gov (United States)

    Moritz-Gasser, Sylvie; Duffau, Hugues

    2009-12-09

    Although studies on bilingualism are abundant, cognitive processes and neural foundations of language switching received less attention. The aim of our study is to provide new insights to this still open question: do dedicated region(s) for language switching exist or is this function underlain by a distributed circuit of interconnected brain areas, part of a more general cognitive system? On the basis of recent behavioral, neuroimaging, and brain stimulation studies, we propose an original 'hodological' model of language switching. This process might be subserved by a large-scale cortico-subcortical network, with an executive system (prefrontal cortex, anterior cingulum, caudate nucleus) controlling a more dedicated language subcircuit, which involves postero-temporal areas, supramarginal and angular gyri, Broca's area, and the superior longitudinal fasciculus.

  14. Three-dimensional neural net for learning visuomotor coordination of a robot arm.

    Science.gov (United States)

    Martinetz, T M; Ritter, H J; Schulten, K J

    1990-01-01

    An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm. Learning occurs by a sequence of trial movements without the need for an external teacher. Using input signals from a pair of cameras, the closed robot arm system is able to reduce its positioning error to about 0.3% of the linear dimensions of its work space. This is achieved by choosing the connectivity of a three-dimensional lattice consisting of the units of the neural net.

  15. Dynamics of neural cryptography.

    Science.gov (United States)

    Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

    2007-05-01

    Synchronization of neural networks has been used for public channel protocols in cryptography. In the case of tree parity machines the dynamics of both bidirectional synchronization and unidirectional learning is driven by attractive and repulsive stochastic forces. Thus it can be described well by a random walk model for the overlap between participating neural networks. For that purpose transition probabilities and scaling laws for the step sizes are derived analytically. Both these calculations as well as numerical simulations show that bidirectional interaction leads to full synchronization on average. In contrast, successful learning is only possible by means of fluctuations. Consequently, synchronization is much faster than learning, which is essential for the security of the neural key-exchange protocol. However, this qualitative difference between bidirectional and unidirectional interaction vanishes if tree parity machines with more than three hidden units are used, so that those neural networks are not suitable for neural cryptography. In addition, the effective number of keys which can be generated by the neural key-exchange protocol is calculated using the entropy of the weight distribution. As this quantity increases exponentially with the system size, brute-force attacks on neural cryptography can easily be made unfeasible.

  16. Dynamics of neural cryptography

    International Nuclear Information System (INIS)

    Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

    2007-01-01

    Synchronization of neural networks has been used for public channel protocols in cryptography. In the case of tree parity machines the dynamics of both bidirectional synchronization and unidirectional learning is driven by attractive and repulsive stochastic forces. Thus it can be described well by a random walk model for the overlap between participating neural networks. For that purpose transition probabilities and scaling laws for the step sizes are derived analytically. Both these calculations as well as numerical simulations show that bidirectional interaction leads to full synchronization on average. In contrast, successful learning is only possible by means of fluctuations. Consequently, synchronization is much faster than learning, which is essential for the security of the neural key-exchange protocol. However, this qualitative difference between bidirectional and unidirectional interaction vanishes if tree parity machines with more than three hidden units are used, so that those neural networks are not suitable for neural cryptography. In addition, the effective number of keys which can be generated by the neural key-exchange protocol is calculated using the entropy of the weight distribution. As this quantity increases exponentially with the system size, brute-force attacks on neural cryptography can easily be made unfeasible

  17. Dynamics of neural cryptography

    Science.gov (United States)

    Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

    2007-05-01

    Synchronization of neural networks has been used for public channel protocols in cryptography. In the case of tree parity machines the dynamics of both bidirectional synchronization and unidirectional learning is driven by attractive and repulsive stochastic forces. Thus it can be described well by a random walk model for the overlap between participating neural networks. For that purpose transition probabilities and scaling laws for the step sizes are derived analytically. Both these calculations as well as numerical simulations show that bidirectional interaction leads to full synchronization on average. In contrast, successful learning is only possible by means of fluctuations. Consequently, synchronization is much faster than learning, which is essential for the security of the neural key-exchange protocol. However, this qualitative difference between bidirectional and unidirectional interaction vanishes if tree parity machines with more than three hidden units are used, so that those neural networks are not suitable for neural cryptography. In addition, the effective number of keys which can be generated by the neural key-exchange protocol is calculated using the entropy of the weight distribution. As this quantity increases exponentially with the system size, brute-force attacks on neural cryptography can easily be made unfeasible.

  18. Neural Basis of Video Gaming: A Systematic Review

    Science.gov (United States)

    Palaus, Marc; Marron, Elena M.; Viejo-Sobera, Raquel; Redolar-Ripoll, Diego

    2017-01-01

    Background: Video gaming is an increasingly popular activity in contemporary society, especially among young people, and video games are increasing in popularity not only as a research tool but also as a field of study. Many studies have focused on the neural and behavioral effects of video games, providing a great deal of video game derived brain correlates in recent decades. There is a great amount of information, obtained through a myriad of methods, providing neural correlates of video games. Objectives: We aim to understand the relationship between the use of video games and their neural correlates, taking into account the whole variety of cognitive factors that they encompass. Methods: A systematic review was conducted using standardized search operators that included the presence of video games and neuro-imaging techniques or references to structural or functional brain changes. Separate categories were made for studies featuring Internet Gaming Disorder and studies focused on the violent content of video games. Results: A total of 116 articles were considered for the final selection. One hundred provided functional data and 22 measured structural brain changes. One-third of the studies covered video game addiction, and 14% focused on video game related violence. Conclusions: Despite the innate heterogeneity of the field of study, it has been possible to establish a series of links between the neural and cognitive aspects, particularly regarding attention, cognitive control, visuospatial skills, cognitive workload, and reward processing. However, many aspects could be improved. The lack of standardization in the different aspects of video game related research, such as the participants' characteristics, the features of each video game genre and the diverse study goals could contribute to discrepancies in many related studies. PMID:28588464

  19. Neural Basis of Video Gaming: A Systematic Review

    Directory of Open Access Journals (Sweden)

    Marc Palaus

    2017-05-01

    Full Text Available Background: Video gaming is an increasingly popular activity in contemporary society, especially among young people, and video games are increasing in popularity not only as a research tool but also as a field of study. Many studies have focused on the neural and behavioral effects of video games, providing a great deal of video game derived brain correlates in recent decades. There is a great amount of information, obtained through a myriad of methods, providing neural correlates of video games.Objectives: We aim to understand the relationship between the use of video games and their neural correlates, taking into account the whole variety of cognitive factors that they encompass.Methods: A systematic review was conducted using standardized search operators that included the presence of video games and neuro-imaging techniques or references to structural or functional brain changes. Separate categories were made for studies featuring Internet Gaming Disorder and studies focused on the violent content of video games.Results: A total of 116 articles were considered for the final selection. One hundred provided functional data and 22 measured structural brain changes. One-third of the studies covered video game addiction, and 14% focused on video game related violence.Conclusions: Despite the innate heterogeneity of the field of study, it has been possible to establish a series of links between the neural and cognitive aspects, particularly regarding attention, cognitive control, visuospatial skills, cognitive workload, and reward processing. However, many aspects could be improved. The lack of standardization in the different aspects of video game related research, such as the participants' characteristics, the features of each video game genre and the diverse study goals could contribute to discrepancies in many related studies.

  20. Neural Basis of Video Gaming: A Systematic Review.

    Science.gov (United States)

    Palaus, Marc; Marron, Elena M; Viejo-Sobera, Raquel; Redolar-Ripoll, Diego

    2017-01-01

    Background: Video gaming is an increasingly popular activity in contemporary society, especially among young people, and video games are increasing in popularity not only as a research tool but also as a field of study. Many studies have focused on the neural and behavioral effects of video games, providing a great deal of video game derived brain correlates in recent decades. There is a great amount of information, obtained through a myriad of methods, providing neural correlates of video games. Objectives: We aim to understand the relationship between the use of video games and their neural correlates, taking into account the whole variety of cognitive factors that they encompass. Methods: A systematic review was conducted using standardized search operators that included the presence of video games and neuro-imaging techniques or references to structural or functional brain changes. Separate categories were made for studies featuring Internet Gaming Disorder and studies focused on the violent content of video games. Results: A total of 116 articles were considered for the final selection. One hundred provided functional data and 22 measured structural brain changes. One-third of the studies covered video game addiction, and 14% focused on video game related violence. Conclusions: Despite the innate heterogeneity of the field of study, it has been possible to establish a series of links between the neural and cognitive aspects, particularly regarding attention, cognitive control, visuospatial skills, cognitive workload, and reward processing. However, many aspects could be improved. The lack of standardization in the different aspects of video game related research, such as the participants' characteristics, the features of each video game genre and the diverse study goals could contribute to discrepancies in many related studies.

  1. A neural fuzzy controller learning by fuzzy error propagation

    Science.gov (United States)

    Nauck, Detlef; Kruse, Rudolf

    1992-01-01

    In this paper, we describe a procedure to integrate techniques for the adaptation of membership functions in a linguistic variable based fuzzy control environment by using neural network learning principles. This is an extension to our work. We solve this problem by defining a fuzzy error that is propagated back through the architecture of our fuzzy controller. According to this fuzzy error and the strength of its antecedent each fuzzy rule determines its amount of error. Depending on the current state of the controlled system and the control action derived from the conclusion, each rule tunes the membership functions of its antecedent and its conclusion. By this we get an unsupervised learning technique that enables a fuzzy controller to adapt to a control task by knowing just about the global state and the fuzzy error.

  2. Neural basis of social status hierarchy across species.

    Science.gov (United States)

    Chiao, Joan Y

    2010-12-01

    Social status hierarchy is a ubiquitous principle of social organization across the animal kingdom. Recent findings in social neuroscience reveal distinct neural networks associated with the recognition and experience of social hierarchy in humans, as well as modulation of these networks by personality and culture. Additionally, allelic variation in the serotonin transporter gene is associated with prevalence of social hierarchy across species and cultures, suggesting the importance of the study of genetic factors underlying social hierarchy. Future studies are needed to determine how genetic and environmental factors shape neural systems involved in the production and maintenance of social hierarchy across ontogeny and phylogeny. Copyright © 2010 Elsevier Ltd. All rights reserved.

  3. Failing to learn from negative prediction errors: Obesity is associated with alterations in a fundamental neural learning mechanism.

    Science.gov (United States)

    Mathar, David; Neumann, Jane; Villringer, Arno; Horstmann, Annette

    2017-10-01

    Prediction errors (PEs) encode the difference between expected and actual action outcomes in the brain via dopaminergic modulation. Integration of these learning signals ensures efficient behavioral adaptation. Obesity has recently been linked to altered dopaminergic fronto-striatal circuits, thus implying impairments in cognitive domains that rely on its integrity. 28 obese and 30 lean human participants performed an implicit stimulus-response learning paradigm inside an fMRI scanner. Computational modeling and psycho-physiological interaction (PPI) analysis was utilized for assessing PE-related learning and associated functional connectivity. We show that human obesity is associated with insufficient incorporation of negative PEs into behavioral adaptation even in a non-food context, suggesting differences in a fundamental neural learning mechanism. Obese subjects were less efficient in using negative PEs to improve implicit learning performance, despite proper coding of PEs in striatum. We further observed lower functional coupling between ventral striatum and supplementary motor area in obese subjects subsequent to negative PEs. Importantly, strength of functional coupling predicted task performance and negative PE utilization. These findings show that obesity is linked to insufficient behavioral adaptation specifically in response to negative PEs, and to associated alterations in function and connectivity within the fronto-striatal system. Recognition of neural differences as a central characteristic of obesity hopefully paves the way to rethink established intervention strategies: Differential behavioral sensitivity to negative and positive PEs should be considered when designing intervention programs. Measures relying on penalization of unwanted behavior may prove less effective in obese subjects than alternative approaches. Copyright © 2017 Elsevier Ltd. All rights reserved.

  4. Neural correlates of contextual cueing are modulated by explicit learning.

    Science.gov (United States)

    Westerberg, Carmen E; Miller, Brennan B; Reber, Paul J; Cohen, Neal J; Paller, Ken A

    2011-10-01

    Contextual cueing refers to the facilitated ability to locate a particular visual element in a scene due to prior exposure to the same scene. This facilitation is thought to reflect implicit learning, as it typically occurs without the observer's knowledge that scenes repeat. Unlike most other implicit learning effects, contextual cueing can be impaired following damage to the medial temporal lobe. Here we investigated neural correlates of contextual cueing and explicit scene memory in two participant groups. Only one group was explicitly instructed about scene repetition. Participants viewed a sequence of complex scenes that depicted a landscape with five abstract geometric objects. Superimposed on each object was a letter T or L rotated left or right by 90°. Participants responded according to the target letter (T) orientation. Responses were highly accurate for all scenes. Response speeds were faster for repeated versus novel scenes. The magnitude of this contextual cueing did not differ between the two groups. Also, in both groups repeated scenes yielded reduced hemodynamic activation compared with novel scenes in several regions involved in visual perception and attention, and reductions in some of these areas were correlated with response-time facilitation. In the group given instructions about scene repetition, recognition memory for scenes was superior and was accompanied by medial temporal and more anterior activation. Thus, strategic factors can promote explicit memorization of visual scene information, which appears to engage additional neural processing beyond what is required for implicit learning of object configurations and target locations in a scene. Copyright © 2011 Elsevier Ltd. All rights reserved.

  5. Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

    Science.gov (United States)

    Kulkarni, Shruti R; Rajendran, Bipin

    2018-07-01

    We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

  6. Neural dynamics of learning sound-action associations.

    Directory of Open Access Journals (Sweden)

    Adam McNamara

    Full Text Available A motor component is pre-requisite to any communicative act as one must inherently move to communicate. To learn to make a communicative act, the brain must be able to dynamically associate arbitrary percepts to the neural substrate underlying the pre-requisite motor activity. We aimed to investigate whether brain regions involved in complex gestures (ventral pre-motor cortex, Brodmann Area 44 were involved in mediating association between novel abstract auditory stimuli and novel gestural movements. In a functional resonance imaging (fMRI study we asked participants to learn associations between previously unrelated novel sounds and meaningless gestures inside the scanner. We use functional connectivity analysis to eliminate the often present confound of 'strategic covert naming' when dealing with BA44 and to rule out effects of non-specific reductions in signal. Brodmann Area 44, a region incorporating Broca's region showed strong, bilateral, negative correlation of BOLD (blood oxygen level dependent response with learning of sound-action associations during data acquisition. Left-inferior-parietal-lobule (l-IPL and bilateral loci in and around visual area V5, right-orbital-frontal-gyrus, right-hippocampus, left-para-hippocampus, right-head-of-caudate, right-insula and left-lingual-gyrus also showed decreases in BOLD response with learning. Concurrent with these decreases in BOLD response, an increasing connectivity between areas of the imaged network as well as the right-middle-frontal-gyrus with rising learning performance was revealed by a psychophysiological interaction (PPI analysis. The increasing connectivity therefore occurs within an increasingly energy efficient network as learning proceeds. Strongest learning related connectivity between regions was found when analysing BA44 and l-IPL seeds. The results clearly show that BA44 and l-IPL is dynamically involved in linking gesture and sound and therefore provides evidence that one of

  7. Comparative quantification of dietary supplemented neural creatine concentrations with (1)H-MRS peak fitting and basis spectrum methods.

    Science.gov (United States)

    Turner, Clare E; Russell, Bruce R; Gant, Nicholas

    2015-11-01

    Magnetic resonance spectroscopy (MRS) is an analytical procedure that can be used to non-invasively measure the concentration of a range of neural metabolites. Creatine is an important neurometabolite with dietary supplementation offering therapeutic potential for neurological disorders with dysfunctional energetic processes. Neural creatine concentrations can be probed using proton MRS and quantified using a range of software packages based on different analytical methods. This experiment examines the differences in quantification performance of two commonly used analysis packages following a creatine supplementation strategy with potential therapeutic application. Human participants followed a seven day dietary supplementation regime in a placebo-controlled, cross-over design interspersed with a five week wash-out period. Spectroscopy data were acquired the day immediately following supplementation and analyzed with two commonly-used software packages which employ vastly different quantification methods. Results demonstrate that neural creatine concentration was augmented following creatine supplementation when analyzed using the peak fitting method of quantification (105.9%±10.1). In contrast, no change in neural creatine levels were detected with supplementation when analysis was conducted using the basis spectrum method of quantification (102.6%±8.6). Results suggest that software packages that employ the peak fitting procedure for spectral quantification are possibly more sensitive to subtle changes in neural creatine concentrations. The relative simplicity of the spectroscopy sequence and the data analysis procedure suggest that peak fitting procedures may be the most effective means of metabolite quantification when detection of subtle alterations in neural metabolites is necessary. The straightforward technique can be used on a clinical magnetic resonance imaging system. Copyright © 2015 Elsevier Inc. All rights reserved.

  8. Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks

    OpenAIRE

    Shen, Li; Lin, Zhouchen; Huang, Qingming

    2015-01-01

    Learning deeper convolutional neural networks becomes a tendency in recent years. However, many empirical evidences suggest that performance improvement cannot be gained by simply stacking more layers. In this paper, we consider the issue from an information theoretical perspective, and propose a novel method Relay Backpropagation, that encourages the propagation of effective information through the network in training stage. By virtue of the method, we achieved the first place in ILSVRC 2015...

  9. Prototype-Incorporated Emotional Neural Network.

    Science.gov (United States)

    Oyedotun, Oyebade K; Khashman, Adnan

    2017-08-15

    Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.

  10. Critical Neural Substrates for Correcting Unexpected Trajectory Errors and Learning from Them

    Science.gov (United States)

    Mutha, Pratik K.; Sainburg, Robert L.; Haaland, Kathleen Y.

    2011-01-01

    Our proficiency at any skill is critically dependent on the ability to monitor our performance, correct errors and adapt subsequent movements so that errors are avoided in the future. In this study, we aimed to dissociate the neural substrates critical for correcting unexpected trajectory errors and learning to adapt future movements based on…

  11. Using repetitive transcranial magnetic stimulation to study the underlying neural mechanisms of human motor learning and memory.

    Science.gov (United States)

    Censor, Nitzan; Cohen, Leonardo G

    2011-01-01

    In the last two decades, there has been a rapid development in the research of the physiological brain mechanisms underlying human motor learning and memory. While conventional memory research performed on animal models uses intracellular recordings, microfusion of protein inhibitors to specific brain areas and direct induction of focal brain lesions, human research has so far utilized predominantly behavioural approaches and indirect measurements of neural activity. Repetitive transcranial magnetic stimulation (rTMS), a safe non-invasive brain stimulation technique, enables the study of the functional role of specific cortical areas by evaluating the behavioural consequences of selective modulation of activity (excitation or inhibition) on memory generation and consolidation, contributing to the understanding of the neural substrates of motor learning. Depending on the parameters of stimulation, rTMS can also facilitate learning processes, presumably through purposeful modulation of excitability in specific brain regions. rTMS has also been used to gain valuable knowledge regarding the timeline of motor memory formation, from initial encoding to stabilization and long-term retention. In this review, we summarize insights gained using rTMS on the physiological and neural mechanisms of human motor learning and memory. We conclude by suggesting possible future research directions, some with direct clinical implications.

  12. Neural network regulation driven by autonomous neural firings

    Science.gov (United States)

    Cho, Myoung Won

    2016-07-01

    Biological neurons naturally fire spontaneously due to the existence of a noisy current. Such autonomous firings may provide a driving force for network formation because synaptic connections can be modified due to neural firings. Here, we study the effect of autonomous firings on network formation. For the temporally asymmetric Hebbian learning, bidirectional connections lose their balance easily and become unidirectional ones. Defining the difference between reciprocal connections as new variables, we could express the learning dynamics as if Ising model spins interact with each other in magnetism. We present a theoretical method to estimate the interaction between the new variables in a neural system. We apply the method to some network systems and find some tendencies of autonomous neural network regulation.

  13. fMRI of Simultaneous Interpretation Reveals the Neural Basis of Extreme Language Control.

    Science.gov (United States)

    Hervais-Adelman, Alexis; Moser-Mercer, Barbara; Michel, Christoph M; Golestani, Narly

    2015-12-01

    We used functional magnetic resonance imaging (fMRI) to examine the neural basis of extreme multilingual language control in a group of 50 multilingual participants. Comparing brain responses arising during simultaneous interpretation (SI) with those arising during simultaneous repetition revealed activation of regions known to be involved in speech perception and production, alongside a network incorporating the caudate nucleus that is known to be implicated in domain-general cognitive control. The similarity between the networks underlying bilingual language control and general executive control supports the notion that the frequently reported bilingual advantage on executive tasks stems from the day-to-day demands of language control in the multilingual brain. We examined neural correlates of the management of simultaneity by correlating brain activity during interpretation with the duration of simultaneous speaking and hearing. This analysis showed significant modulation of the putamen by the duration of simultaneity. Our findings suggest that, during SI, the caudate nucleus is implicated in the overarching selection and control of the lexico-semantic system, while the putamen is implicated in ongoing control of language output. These findings provide the first clear dissociation of specific dorsal striatum structures in polyglot language control, roles that are consistent with previously described involvement of these regions in nonlinguistic executive control. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  14. Statistical Discriminability Estimation for Pattern Classification Based on Neural Incremental Attribute Learning

    DEFF Research Database (Denmark)

    Wang, Ting; Guan, Sheng-Uei; Puthusserypady, Sadasivan

    2014-01-01

    Feature ordering is a significant data preprocessing method in Incremental Attribute Learning (IAL), a novel machine learning approach which gradually trains features according to a given order. Previous research has shown that, similar to feature selection, feature ordering is also important based...... estimation. Moreover, a criterion that summarizes all the produced values of AD is employed with a GA (Genetic Algorithm)-based approach to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. Compared with the feature ordering obtained by other approaches...

  15. Application of artificial neural networks to evaluate weld defects of nuclear components

    International Nuclear Information System (INIS)

    Amin, E.S.

    2007-01-01

    Artificial neural networks (ANNs) are computational representations based on the biological neural architecture of the brain. ANNs have been successfully applied to a wide range of engineering and scientific applications, such as signal, image processing and data analysis. Although Radiographic testing is widely used for welding defects, it is unsuccessful in identifying some welding defects because of the nature of image formation and quality. Neoteric algorithms have been used for the purpose of weld defects identifications in radiographic images to replace the expert knowledge. The application of artificial neural networks in noise detection of radiographic films is used. Radial Basis (RB) and learning vector quantization (LVQ) were applied. The method shows good performance in weld defects recognition and classification problems.

  16. An Intelligent Approach to Educational Data: Performance Comparison of the Multilayer Perceptron and the Radial Basis Function Artificial Neural Networks

    Science.gov (United States)

    Kayri, Murat

    2015-01-01

    The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The…

  17. Construction of Neural Networks for Realization of Localized Deep Learning

    Directory of Open Access Journals (Sweden)

    Charles K. Chui

    2018-05-01

    Full Text Available The subject of deep learning has recently attracted users of machine learning from various disciplines, including: medical diagnosis and bioinformatics, financial market analysis and online advertisement, speech and handwriting recognition, computer vision and natural language processing, time series forecasting, and search engines. However, theoretical development of deep learning is still at its infancy. The objective of this paper is to introduce a deep neural network (also called deep-net approach to localized manifold learning, with each hidden layer endowed with a specific learning task. For the purpose of illustrations, we only focus on deep-nets with three hidden layers, with the first layer for dimensionality reduction, the second layer for bias reduction, and the third layer for variance reduction. A feedback component is also designed to deal with outliers. The main theoretical result in this paper is the order O(m-2s/(2s+d of approximation of the regression function with regularity s, in terms of the number m of sample points, where the (unknown manifold dimension d replaces the dimension D of the sampling (Euclidean space for shallow nets.

  18. Transfer Learning with Convolutional Neural Networks for SAR Ship Recognition

    Science.gov (United States)

    Zhang, Di; Liu, Jia; Heng, Wang; Ren, Kaijun; Song, Junqiang

    2018-03-01

    Ship recognition is the backbone of marine surveillance systems. Recent deep learning methods, e.g. Convolutional Neural Networks (CNNs), have shown high performance for optical images. Learning CNNs, however, requires a number of annotated samples to estimate numerous model parameters, which prevents its application to Synthetic Aperture Radar (SAR) images due to the limited annotated training samples. Transfer learning has been a promising technique for applications with limited data. To this end, a novel SAR ship recognition method based on CNNs with transfer learning has been developed. In this work, we firstly start with a CNNs model that has been trained in advance on Moving and Stationary Target Acquisition and Recognition (MSTAR) database. Next, based on the knowledge gained from this image recognition task, we fine-tune the CNNs on a new task to recognize three types of ships in the OpenSARShip database. The experimental results show that our proposed approach can obviously increase the recognition rate comparing with the result of merely applying CNNs. In addition, compared to existing methods, the proposed method proves to be very competitive and can learn discriminative features directly from training data instead of requiring pre-specification or pre-selection manually.

  19. On-line identification of hybrid systems using an adaptive growing and pruning RBF neural network

    DEFF Research Database (Denmark)

    Alizadeh, Tohid

    2008-01-01

    This paper introduces an adaptive growing and pruning radial basis function (GAP-RBF) neural network for on-line identification of hybrid systems. The main idea is to identify a global nonlinear model that can predict the continuous outputs of hybrid systems. In the proposed approach, GAP......-RBF neural network uses a modified unscented kalman filter (UKF) with forgetting factor scheme as the required on-line learning algorithm. The effectiveness of the resulting identification approach is tested and evaluated on a simulated benchmark hybrid system....

  20. Differential neural substrates of working memory and cognitive skill learning in healthy young volunteers

    International Nuclear Information System (INIS)

    Cho, Sang Soo; Lee, Eun Ju; Yoon, Eun Jin; Kim, Yu Kyeong; Lee, Won Woo; Kim, Sang Eun

    2005-01-01

    It is known that different neural circuits are involved in working memory and cognitive skill learning that represent explicit and implicit memory functions, respectively. In the present study, we investigated the metabolic correlates of working memory and cognitive skill learning with correlation analysis of FDG PET images. Fourteen right-handed healthy subjects (age, 24 ± 2 yr; 5 males and 9 females) underwent brain FDG PET and neuropsychological testing. Two-back task and weather prediction task were used for the evaluation of working memory and cognitive skill learning, respectively, Correlation between regional glucose metabolism and cognitive task performance was examined using SPM99. A significant positive correlation between 2-back task performance and regional glucose metabolism was found in the prefrontal regions and superior temporal gyri bilaterally. In the first term of weather prediction task the task performance correlated positively with glucose metabolism in the bilateral prefrontal areas, left middle temporal and posterior cingulate gyri, and left thalamus. In the second and third terms of the task, the correlation found in the prefrontal areas, superior temporal and anterior cingulate gyri bilaterally, right insula, left parahippocampal gyrus, and right caudate nucleus. We identified the neural substrates that are related with performance of working memory and cognitive skill learning. These results indicate that brain regions associated with the explicit memory system are recruited in early periods of cognitive skill learning, but additional brain regions including caudate nucleus are involved in late periods of cognitive skill learning

  1. Differential neural substrates of working memory and cognitive skill learning in healthy young volunteers

    Energy Technology Data Exchange (ETDEWEB)

    Cho, Sang Soo; Lee, Eun Ju; Yoon, Eun Jin; Kim, Yu Kyeong; Lee, Won Woo; Kim, Sang Eun [Seoul National Univ. College of Medicine, Seoul (Korea, Republic of)

    2005-07-01

    It is known that different neural circuits are involved in working memory and cognitive skill learning that represent explicit and implicit memory functions, respectively. In the present study, we investigated the metabolic correlates of working memory and cognitive skill learning with correlation analysis of FDG PET images. Fourteen right-handed healthy subjects (age, 24 {+-} 2 yr; 5 males and 9 females) underwent brain FDG PET and neuropsychological testing. Two-back task and weather prediction task were used for the evaluation of working memory and cognitive skill learning, respectively, Correlation between regional glucose metabolism and cognitive task performance was examined using SPM99. A significant positive correlation between 2-back task performance and regional glucose metabolism was found in the prefrontal regions and superior temporal gyri bilaterally. In the first term of weather prediction task the task performance correlated positively with glucose metabolism in the bilateral prefrontal areas, left middle temporal and posterior cingulate gyri, and left thalamus. In the second and third terms of the task, the correlation found in the prefrontal areas, superior temporal and anterior cingulate gyri bilaterally, right insula, left parahippocampal gyrus, and right caudate nucleus. We identified the neural substrates that are related with performance of working memory and cognitive skill learning. These results indicate that brain regions associated with the explicit memory system are recruited in early periods of cognitive skill learning, but additional brain regions including caudate nucleus are involved in late periods of cognitive skill learning.

  2. Understanding the Implications of Neural Population Activity on Behavior

    Science.gov (United States)

    Briguglio, John

    Learning how neural activity in the brain leads to the behavior we exhibit is one of the fundamental questions in Neuroscience. In this dissertation, several lines of work are presented to that use principles of neural coding to understand behavior. In one line of work, we formulate the efficient coding hypothesis in a non-traditional manner in order to test human perceptual sensitivity to complex visual textures. We find a striking agreement between how variable a particular texture signal is and how sensitive humans are to its presence. This reveals that the efficient coding hypothesis is still a guiding principle for neural organization beyond the sensory periphery, and that the nature of cortical constraints differs from the peripheral counterpart. In another line of work, we relate frequency discrimination acuity to neural responses from auditory cortex in mice. It has been previously observed that optogenetic manipulation of auditory cortex, in addition to changing neural responses, evokes changes in behavioral frequency discrimination. We are able to account for changes in frequency discrimination acuity on an individual basis by examining the Fisher information from the neural population with and without optogenetic manipulation. In the third line of work, we address the question of what a neural population should encode given that its inputs are responses from another group of neurons. Drawing inspiration from techniques in machine learning, we train Deep Belief Networks on fake retinal data and show the emergence of Garbor-like filters, reminiscent of responses in primary visual cortex. In the last line of work, we model the state of a cortical excitatory-inhibitory network during complex adaptive stimuli. Using a rate model with Wilson-Cowan dynamics, we demonstrate that simple non-linearities in the signal transferred from inhibitory to excitatory neurons can account for real neural recordings taken from auditory cortex. This work establishes and tests

  3. DeepNet: An Ultrafast Neural Learning Code for Seismic Imaging

    International Nuclear Information System (INIS)

    Barhen, J.; Protopopescu, V.; Reister, D.

    1999-01-01

    A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools

  4. Stress Induces a Shift Towards Striatum-Dependent Stimulus-Response Learning via the Mineralocorticoid Receptor

    NARCIS (Netherlands)

    Vogel, S.; Klumpers, F.; Navarro Schröder, T.; Oplaat, K.T.; Krugers, H.J.; Oitzl, M.S.; Joëls, M.; Doeller, C.F.; Fernández, G.

    2017-01-01

    Stress is assumed to cause a shift from flexible 'cognitive' memory to more rigid 'habit' memory. In the spatial memory domain, stress impairs place learning depending on the hippocampus whereas stimulus-response learning based on the striatum appears to be improved. While the neural basis of this

  5. Stress induces a shift towards striatum-dependent stimulus-response learning via the mineralocorticoid receptor

    NARCIS (Netherlands)

    Vogel, S.; Klumpers, F.; Navarro Schröder, T.; Oplaat, K.T.; Krugers, H.J.; Oitzl, M.S.; Joëls, M.; Doeller, C.F.; Fernandez, G.

    2017-01-01

    Stress is assumed to cause a shift from flexible 'cognitive' memory to more rigid 'habit' memory. In the spatial memory domain, stress impairs place learning depending on the hippocampus whereas stimulus-response learning based on the striatum appears to be improved. While the neural basis of this

  6. Stress Induces a Shift Towards Striatum-Dependent Stimulus-Response Learning via the Mineralocorticoid Receptor

    NARCIS (Netherlands)

    Vogel, Susanne; Klumpers, Floris; Schroeder, Tobias Navarro; Oplaat, Krista T.; Krugers, Harm J.; Oitzl, Melly S.; Joels, Marian; Doeller, Christian F.; Fernandez, Guillen

    Stress is assumed to cause a shift from flexible 'cognitive' memory to more rigid 'habit' memory. In the spatial memory domain, stress impairs place learning depending on the hippocampus whereas stimulus-response learning based on the striatum appears to be improved. While the neural basis of this

  7. Multi-step ahead nonlinear identification of Lorenz's chaotic system using radial basis neural network with learning by clustering and particle swarm optimization

    International Nuclear Information System (INIS)

    Guerra, Fabio A.; Coelho, Leandro dos S.

    2008-01-01

    An important problem in engineering is the identification of nonlinear systems, among them radial basis function neural networks (RBF-NN) using Gaussian activation functions models, which have received particular attention due to their potential to approximate nonlinear behavior. Several design methods have been proposed for choosing the centers and spread of Gaussian functions and training the RBF-NN. The selection of RBF-NN parameters such as centers, spreads, and weights can be understood as a system identification problem. This paper presents a hybrid training approach based on clustering methods (k-means and c-means) to tune the centers of Gaussian functions used in the hidden layer of RBF-NNs. This design also uses particle swarm optimization (PSO) for centers (local clustering search method) and spread tuning, and the Penrose-Moore pseudoinverse for the adjustment of RBF-NN weight outputs. Simulations involving this RBF-NN design to identify Lorenz's chaotic system indicate that the performance of the proposed method is superior to that of the conventional RBF-NN trained for k-means and the Penrose-Moore pseudoinverse for multi-step ahead forecasting

  8. Deciphering the Cognitive and Neural Mechanisms Underlying ...

    International Development Research Centre (IDRC) Digital Library (Canada)

    Deciphering the Cognitive and Neural Mechanisms Underlying Auditory Learning. This project seeks to understand the brain mechanisms necessary for people to learn to perceive sounds. Neural circuits and learning. The research team will test people with and without musical training to evaluate their capacity to learn ...

  9. Kernel Temporal Differences for Neural Decoding

    Science.gov (United States)

    Bae, Jihye; Sanchez Giraldo, Luis G.; Pohlmeyer, Eric A.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

    2015-01-01

    We study the feasibility and capability of the kernel temporal difference (KTD)(λ) algorithm for neural decoding. KTD(λ) is an online, kernel-based learning algorithm, which has been introduced to estimate value functions in reinforcement learning. This algorithm combines kernel-based representations with the temporal difference approach to learning. One of our key observations is that by using strictly positive definite kernels, algorithm's convergence can be guaranteed for policy evaluation. The algorithm's nonlinear functional approximation capabilities are shown in both simulations of policy evaluation and neural decoding problems (policy improvement). KTD can handle high-dimensional neural states containing spatial-temporal information at a reasonable computational complexity allowing real-time applications. When the algorithm seeks a proper mapping between a monkey's neural states and desired positions of a computer cursor or a robot arm, in both open-loop and closed-loop experiments, it can effectively learn the neural state to action mapping. Finally, a visualization of the coadaptation process between the decoder and the subject shows the algorithm's capabilities in reinforcement learning brain machine interfaces. PMID:25866504

  10. Dynamic Fault Diagnosis for Semi-Batch Reactor under Closed-Loop Control via Independent Radial Basis Function Neural Network

    OpenAIRE

    Abdelkarim M. Ertiame; D. W. Yu; D. L. Yu; J. B. Gomm

    2015-01-01

    In this paper, a robust fault detection and isolation (FDI) scheme is developed to monitor a multivariable nonlinear chemical process called the Chylla-Haase polymerization reactor, when it is under the cascade PI control. The scheme employs a radial basis function neural network (RBFNN) in an independent mode to model the process dynamics, and using the weighted sum-squared prediction error as the residual. The Recursive Orthogonal Least Squares algorithm (ROLS) is emplo...

  11. Neural principles of memory and a neural theory of analogical insight

    Science.gov (United States)

    Lawson, David I.; Lawson, Anton E.

    1993-12-01

    Grossberg's principles of neural modeling are reviewed and extended to provide a neural level theory to explain how analogies greatly increase the rate of learning and can, in fact, make learning and retention possible. In terms of memory, the key point is that the mind is able to recognize and recall when it is able to match sensory input from new objects, events, or situations with past memory records of similar objects, events, or situations. When a match occurs, an adaptive resonance is set up in which the synaptic strengths of neurons are increased; thus a long term record of the new input is formed in memory. Systems of neurons called outstars and instars are presumably the underlying units that enable this to occur. Analogies can greatly facilitate learning and retention because they activate the outstars (i.e., the cells that are sampling the to-be-learned pattern) and cause the neural activity to grow exponentially by forming feedback loops. This increased activity insures the boost in synaptic strengths of neurons, thus causing storage and retention in long-term memory (i.e., learning).

  12. Neural substrates of approach-avoidance conflict decision-making

    Science.gov (United States)

    Aupperle, Robin L.; Melrose, Andrew J.; Francisco, Alex; Paulus, Martin P.; Stein, Murray B.

    2014-01-01

    Animal approach-avoidance conflict paradigms have been used extensively to operationalize anxiety, quantify the effects of anxiolytic agents, and probe the neural basis of fear and anxiety. Results from human neuroimaging studies support that a frontal-striatal-amygdala neural circuitry is important for approach-avoidance learning. However, the neural basis of decision-making is much less clear in this context. Thus, we combined a recently developed human approach-avoidance paradigm with functional magnetic resonance imaging (fMRI) to identify neural substrates underlying approach-avoidance conflict decision-making. Fifteen healthy adults completed the approach-avoidance conflict (AAC) paradigm during fMRI. Analyses of variance were used to compare conflict to non-conflict (avoid-threat and approach-reward) conditions and to compare level of reward points offered during the decision phase. Trial-by-trial amplitude modulation analyses were used to delineate brain areas underlying decision-making in the context of approach/avoidance behavior. Conflict trials as compared to the non-conflict trials elicited greater activation within bilateral anterior cingulate cortex (ACC), anterior insula, and caudate, as well as right dorsolateral prefrontal cortex. Right caudate and lateral PFC activation was modulated by level of reward offered. Individuals who showed greater caudate activation exhibited less approach behavior. On a trial-by-trial basis, greater right lateral PFC activation related to less approach behavior. Taken together, results suggest that the degree of activation within prefrontal-striatal-insula circuitry determines the degree of approach versus avoidance decision-making. Moreover, the degree of caudate and lateral PFC activation is related to individual differences in approach-avoidance decision-making. Therefore, the AAC paradigm is ideally suited to probe anxiety-related processing differences during approach-avoidance decision-making. PMID:25224633

  13. Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

    Science.gov (United States)

    Khellal, Atmane; Ma, Hongbin; Fei, Qing

    2018-05-09

    The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

  14. Neural Networks

    International Nuclear Information System (INIS)

    Smith, Patrick I.

    2003-01-01

    Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

  15. Multivariate Cross-Classification: Applying machine learning techniques to characterize abstraction in neural representations

    Directory of Open Access Journals (Sweden)

    Jonas eKaplan

    2015-03-01

    Full Text Available Here we highlight an emerging trend in the use of machine learning classifiers to test for abstraction across patterns of neural activity. When a classifier algorithm is trained on data from one cognitive context, and tested on data from another, conclusions can be drawn about the role of a given brain region in representing information that abstracts across those cognitive contexts. We call this kind of analysis Multivariate Cross-Classification (MVCC, and review several domains where it has recently made an impact. MVCC has been important in establishing correspondences among neural patterns across cognitive domains, including motor-perception matching and cross-sensory matching. It has been used to test for similarity between neural patterns evoked by perception and those generated from memory. Other work has used MVCC to investigate the similarity of representations for semantic categories across different kinds of stimulus presentation, and in the presence of different cognitive demands. We use these examples to demonstrate the power of MVCC as a tool for investigating neural abstraction and discuss some important methodological issues related to its application.

  16. Identification of chaotic systems by neural network with hybrid learning algorithm

    International Nuclear Information System (INIS)

    Pan, S.-T.; Lai, C.-C.

    2008-01-01

    Based on the genetic algorithm (GA) and steepest descent method (SDM), this paper proposes a hybrid algorithm for the learning of neural networks to identify chaotic systems. The systems in question are the logistic map and the Duffing equation. Different identification schemes are used to identify both the logistic map and the Duffing equation, respectively. Simulation results show that our hybrid algorithm is more efficient than that of other methods

  17. A Meta-Analysis Suggests Different Neural Correlates for Implicit and Explicit Learning.

    Science.gov (United States)

    Loonis, Roman F; Brincat, Scott L; Antzoulatos, Evan G; Miller, Earl K

    2017-10-11

    A meta-analysis of non-human primates performing three different tasks (Object-Match, Category-Match, and Category-Saccade associations) revealed signatures of explicit and implicit learning. Performance improved equally following correct and error trials in the Match (explicit) tasks, but it improved more after correct trials in the Saccade (implicit) task, a signature of explicit versus implicit learning. Likewise, error-related negativity, a marker for error processing, was greater in the Match (explicit) tasks. All tasks showed an increase in alpha/beta (10-30 Hz) synchrony after correct choices. However, only the implicit task showed an increase in theta (3-7 Hz) synchrony after correct choices that decreased with learning. In contrast, in the explicit tasks, alpha/beta synchrony increased with learning and decreased thereafter. Our results suggest that explicit versus implicit learning engages different neural mechanisms that rely on different patterns of oscillatory synchrony. Copyright © 2017 Elsevier Inc. All rights reserved.

  18. Developmental song learning as a model to understand neural mechanisms that limit and promote the ability to learn.

    Science.gov (United States)

    London, Sarah E

    2017-11-20

    Songbirds famously learn their vocalizations. Some species can learn continuously, others seasonally, and still others just once. The zebra finch (Taeniopygia guttata) learns to sing during a single developmental "Critical Period," a restricted phase during which a specific experience has profound and permanent effects on brain function and behavioral patterns. The zebra finch can therefore provide fundamental insight into features that promote and limit the ability to acquire complex learned behaviors. For example, what properties permit the brain to come "on-line" for learning? How does experience become encoded to prevent future learning? What features define the brain in receptive compared to closed learning states? This piece will focus on epigenomic, genomic, and molecular levels of analysis that operate on the timescales of development and complex behavioral learning. Existing data will be discussed as they relate to Critical Period learning, and strategies for future studies to more directly address these questions will be considered. Birdsong learning is a powerful model for advancing knowledge of the biological intersections of maturation and experience. Lessons from its study not only have implications for understanding developmental song learning, but also broader questions of learning potential and the enduring effects of early life experience on neural systems and behavior. Copyright © 2017. Published by Elsevier B.V.

  19. The neural basis of predicting the outcomes of planned actions

    Directory of Open Access Journals (Sweden)

    Andrew eJahn

    2011-11-01

    Full Text Available A key feature of human intelligence is the ability to predict the outcomes of one’s own actions prior to executing them. Action values are thought to be represented in part in the dorsal and ventral medial prefrontal cortex, yet current studies have focused on the value of executed actions rather than the anticipated value of a planned action. Thus, little is known about the neural basis of how individuals think (or fail to think about their actions and the potential consequences before they act. We scanned individuals with fMRI while they thought about performing actions that they knew would likely be correct or incorrect. Here we show that merely imagining an error, as opposed to imagining a correct outcome, increases activity in the dorsal anterior cingulate cortex, independently of subsequent actions. This activity overlaps with regions that respond to actual error commission. The findings show a distinct network that signals the prospective outcomes of one’s planned actions. A number of clinical disorders such as schizophrenia and drug abuse involve a failure to take the potential consequences of an action into account prior to acting. Our results thus suggest how dysfunctions of the medial prefrontal cortex may contribute to such failures.

  20. Age-related difference in the effective neural connectivity associated with probabilistic category learning

    International Nuclear Information System (INIS)

    Yoon, Eun Jin; Cho, Sang Soo; Kim, Hee Jung; Bang, Seong Ae; Park, Hyun Soo; Kim, Yu Kyeong; Kim, Sang Eun

    2007-01-01

    Although it is well known that explicit memory is affected by the deleterious changes in brain with aging, but effect of aging in implicit memory such as probabilistic category learning (PCL) is not clear. To identify the effect of aging on the neural interaction for successful PCL, we investigated the neural substrates of PCL and the age-related changes of the neural network between these brain regions. 23 young (age, 252 y; 11 males) and 14 elderly (673 y; 7 males) healthy subjects underwent FDG PET during a resting state and 150-trial weather prediction (WP) task. Correlations between the WP hit rates and regional glucose metabolism were assessed using SPM2 (P diff (37) = 142.47, P<0.005), Systematic comparisons of each path revealed that frontal crosscallosal and the frontal to parahippocampal connection were most responsible for the model differences (P<0.05). For the successful PCL, the elderly recruits the basal ganglia implicit memory system but MTL recruitment differs from the young. The inadequate MTL correlation pattern in the elderly is may be caused by the changes of the neural pathway related with explicit memory. These neural changes can explain the decreased performance of PCL in elderly subjects

  1. Neural circuitry of abdominal pain-related fear learning and reinstatement in irritable bowel syndrome.

    Science.gov (United States)

    Icenhour, A; Langhorst, J; Benson, S; Schlamann, M; Hampel, S; Engler, H; Forsting, M; Elsenbruch, S

    2015-01-01

    Altered pain anticipation likely contributes to disturbed central pain processing in chronic pain conditions like irritable bowel syndrome (IBS), but the learning processes shaping the expectation of pain remain poorly understood. We assessed the neural circuitry mediating the formation, extinction, and reactivation of abdominal pain-related memories in IBS patients compared to healthy controls (HC) in a differential fear conditioning paradigm. During fear acquisition, predictive visual cues (CS(+)) were paired with rectal distensions (US), while control cues (CS(-)) were presented unpaired. During extinction, only CSs were presented. Subsequently, memory reactivation was assessed with a reinstatement procedure involving unexpected USs. Using functional magnetic resonance imaging, group differences in neural activation to CS(+) vs CS(-) were analyzed, along with skin conductance responses (SCR), CS valence, CS-US contingency, state anxiety, salivary cortisol, and alpha-amylase activity. The contribution of anxiety symptoms was addressed in covariance analyses. Fear acquisition was altered in IBS, as indicated by more accurate contingency awareness, greater CS-related valence change, and enhanced CS(+)-induced differential activation of prefrontal cortex and amygdala. IBS patients further revealed enhanced differential cingulate activation during extinction and greater differential hippocampal activation during reinstatement. Anxiety affected neural responses during memory formation and reinstatement. Abdominal pain-related fear learning and memory processes are altered in IBS, mediated by amygdala, cingulate cortex, prefrontal areas, and hippocampus. Enhanced reinstatement may contribute to hypervigilance and central pain amplification, especially in anxious patients. Preventing a 'relapse' of learned fear utilizing extinction-based interventions may be a promising treatment goal in IBS. © 2014 John Wiley & Sons Ltd.

  2. Neural Correlates of Success and Failure Signals During Neurofeedback Learning.

    Science.gov (United States)

    Radua, Joaquim; Stoica, Teodora; Scheinost, Dustin; Pittenger, Christopher; Hampson, Michelle

    2018-05-15

    Feedback-driven learning, observed across phylogeny and of clear adaptive value, is frequently operationalized in simple operant conditioning paradigms, but it can be much more complex, driven by abstract representations of success and failure. This study investigates the neural processes involved in processing success and failure during feedback learning, which are not well understood. Data analyzed were acquired during a multisession neurofeedback experiment in which ten participants were presented with, and instructed to modulate, the activity of their orbitofrontal cortex with the aim of decreasing their anxiety. We assessed the regional blood-oxygenation-level-dependent response to the individualized neurofeedback signals of success and failure across twelve functional runs acquired in two different magnetic resonance sessions in each of ten individuals. Neurofeedback signals of failure correlated early during learning with deactivation in the precuneus/posterior cingulate and neurofeedback signals of success correlated later during learning with deactivation in the medial prefrontal/anterior cingulate cortex. The intensity of the latter deactivations predicted the efficacy of the neurofeedback intervention in the reduction of anxiety. These findings indicate a role for regulation of the default mode network during feedback learning, and suggest a higher sensitivity to signals of failure during the early feedback learning and to signals of success subsequently. Copyright © 2016 IBRO. Published by Elsevier Ltd. All rights reserved.

  3. Noise-driven manifestation of learning in mature neural networks

    International Nuclear Information System (INIS)

    Monterola, Christopher; Saloma, Caesar

    2002-01-01

    We show that the generalization capability of a mature thresholding neural network to process above-threshold disturbances in a noise-free environment is extended to subthreshold disturbances by ambient noise without retraining. The ability to benefit from noise is intrinsic and does not have to be learned separately. Nonlinear dependence of sensitivity with noise strength is significantly narrower than in individual threshold systems. Noise has a minimal effect on network performance for above-threshold signals. We resolve two seemingly contradictory responses of trained networks to noise--their ability to benefit from its presence and their robustness against noisy strong disturbances

  4. The neural basis of body form and body action agnosia.

    Science.gov (United States)

    Moro, Valentina; Urgesi, Cosimo; Pernigo, Simone; Lanteri, Paola; Pazzaglia, Mariella; Aglioti, Salvatore Maria

    2008-10-23

    Visual analysis of faces and nonfacial body stimuli brings about neural activity in different cortical areas. Moreover, processing body form and body action relies on distinct neural substrates. Although brain lesion studies show specific face processing deficits, neuropsychological evidence for defective recognition of nonfacial body parts is lacking. By combining psychophysics studies with lesion-mapping techniques, we found that lesions of ventromedial, occipitotemporal areas induce face and body recognition deficits while lesions involving extrastriate body area seem causatively associated with impaired recognition of body but not of face and object stimuli. We also found that body form and body action recognition deficits can be double dissociated and are causatively associated with lesions to extrastriate body area and ventral premotor cortex, respectively. Our study reports two category-specific visual deficits, called body form and body action agnosia, and highlights their neural underpinnings.

  5. Linking Neural and Symbolic Representation and Processing of Conceptual Structures

    Directory of Open Access Journals (Sweden)

    Frank van der Velde

    2017-08-01

    Full Text Available We compare and discuss representations in two cognitive architectures aimed at representing and processing complex conceptual (sentence-like structures. First is the Neural Blackboard Architecture (NBA, which aims to account for representation and processing of complex and combinatorial conceptual structures in the brain. Second is IDyOT (Information Dynamics of Thinking, which derives sentence-like structures by learning statistical sequential regularities over a suitable corpus. Although IDyOT is designed at a level more abstract than the neural, so it is a model of cognitive function, rather than neural processing, there are strong similarities between the composite structures developed in IDyOT and the NBA. We hypothesize that these similarities form the basis of a combined architecture in which the individual strengths of each architecture are integrated. We outline and discuss the characteristics of this combined architecture, emphasizing the representation and processing of conceptual structures.

  6. Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

    Science.gov (United States)

    Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

    2017-04-10

    This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

  7. A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.

    Science.gov (United States)

    Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa

    2007-05-01

    We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.

  8. Introduction to neural networks

    International Nuclear Information System (INIS)

    Pavlopoulos, P.

    1996-01-01

    This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix

  9. Application of different entropy formalisms in a neural network for novel word learning

    Science.gov (United States)

    Khordad, R.; Rastegar Sedehi, H. R.

    2015-12-01

    In this paper novel word learning in adults is studied. For this goal, four entropy formalisms are employed to include some degree of non-locality in a neural network. The entropy formalisms are Tsallis, Landsberg-Vedral, Kaniadakis, and Abe entropies. First, we have analytically obtained non-extensive cost functions for the all entropies. Then, we have used a generalization of the gradient descent dynamics as a learning rule in a simple perceptron. The Langevin equations are numerically solved and the error function (learning curve) is obtained versus time for different values of the parameters. The influence of index q and number of neuron N on learning is investigated for the all entropies. It is found that learning is a decreasing function of time for the all entropies. The rate of learning for the Landsberg-Vedral entropy is slower than other entropies. The variation of learning with time for the Landsberg-Vedral entropy is not appreciable when the number of neurons increases. It is said that entropy formalism can be used as a means for studying the learning.

  10. A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

    Directory of Open Access Journals (Sweden)

    Alireza Alemi

    2015-08-01

    Full Text Available Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the

  11. A Neural Network Model to Learn Multiple Tasks under Dynamic Environments

    Science.gov (United States)

    Tsumori, Kenji; Ozawa, Seiichi

    When environments are dynamically changed for agents, the knowledge acquired in an environment might be useless in future. In such dynamic environments, agents should be able to not only acquire new knowledge but also modify old knowledge in learning. However, modifying all knowledge acquired before is not efficient because the knowledge once acquired may be useful again when similar environment reappears and some knowledge can be shared among different environments. To learn efficiently in such environments, we propose a neural network model that consists of the following modules: resource allocating network, long-term & short-term memory, and environment change detector. We evaluate the model under a class of dynamic environments where multiple function approximation tasks are sequentially given. The experimental results demonstrate that the proposed model possesses stable incremental learning, accurate environmental change detection, proper association and recall of old knowledge, and efficient knowledge transfer.

  12. A Tsallis’ statistics based neural network model for novel word learning

    Science.gov (United States)

    Hadzibeganovic, Tarik; Cannas, Sergio A.

    2009-03-01

    We invoke the Tsallis entropy formalism, a nonextensive entropy measure, to include some degree of non-locality in a neural network that is used for simulation of novel word learning in adults. A generalization of the gradient descent dynamics, realized via nonextensive cost functions, is used as a learning rule in a simple perceptron. The model is first investigated for general properties, and then tested against the empirical data, gathered from simple memorization experiments involving two populations of linguistically different subjects. Numerical solutions of the model equations corresponded to the measured performance states of human learners. In particular, we found that the memorization tasks were executed with rather small but population-specific amounts of nonextensivity, quantified by the entropic index q. Our findings raise the possibility of using entropic nonextensivity as a means of characterizing the degree of complexity of learning in both natural and artificial systems.

  13. Superior Generalization Capability of Hardware-Learing Algorithm Developed for Self-Learning Neuron-MOS Neural Networks

    Science.gov (United States)

    Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro

    1995-02-01

    We have investigated the learning performance of the hardware backpropagation (HBP) algorithm, a hardware-oriented learning algorithm developed for the self-learning architecture of neural networks constructed using neuron MOS (metal-oxide-semiconductor) transistors. The solution to finding a mirror symmetry axis in a 4×4 binary pixel array was tested by computer simulation based on the HBP algorithm. Despite the inherent restrictions imposed on the hardware-learning algorithm, HBP exhibits equivalent learning performance to that of the original backpropagation (BP) algorithm when all the pertinent parameters are optimized. Very importantly, we have found that HBP has a superior generalization capability over BP; namely, HBP exhibits higher performance in solving problems that the network has not yet learnt.

  14. Habituation in non-neural organisms: evidence from slime moulds

    OpenAIRE

    Boisseau, Romain P.; Vogel, David; Dussutour, Audrey

    2016-01-01

    Learning, defined as a change in behaviour evoked by experience, has hitherto been investigated almost exclusively in multicellular neural organisms. Evidence for learning in non-neural multicellular organisms is scant, and only a few unequivocal reports of learning have been described in single-celled organisms. Here we demonstrate habituation, an unmistakable form of learning, in the non-neural organism Physarum polycephalum. In our experiment, using chemotaxis as the behavioural output and...

  15. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Directory of Open Access Journals (Sweden)

    Yoonsik Shim

    2016-10-01

    Full Text Available We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP. The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  16. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Science.gov (United States)

    Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

    2016-10-01

    We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  17. Neural basis of music imagery and the effect of musical expertise.

    Science.gov (United States)

    Herholz, Sibylle C; Lappe, Claudia; Knief, Arne; Pantev, Christo

    2008-12-01

    Although the influence of long-term musical training on the processing of heard music has been the subject of many studies, the neural basis of music imagery and the effect of musical expertise remain insufficiently understood. By means of magnetoencephalography (MEG) we compared musicians and nonmusicians in a musical imagery task with familiar melodies. Subjects listened to the beginnings of the melodies, continued them in their imagination and then heard a tone which was either a correct or an incorrect further continuation of the melody. Only in musicians was the imagery of these melodies strong enough to elicit an early preattentive brain response to unexpected incorrect continuations of the imagined melodies; this response, the imagery mismatch negativity (iMMN), peaked approximately 175 ms after tone onset and was right-lateralized. In contrast to previous studies the iMMN was not based on a heard but on a purely imagined memory trace. Our results suggest that in trained musicians imagery and perception rely on similar neuronal correlates, and that the musicians' intense musical training has modified this network to achieve a superior ability for imagery and preattentive processing of music.

  18. Chaotic diagonal recurrent neural network

    International Nuclear Information System (INIS)

    Wang Xing-Yuan; Zhang Yi

    2012-01-01

    We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)

  19. Application of a neural network for reflectance spectrum classification

    Science.gov (United States)

    Yang, Gefei; Gartley, Michael

    2017-05-01

    Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

  20. The neural basis of intuitive and counterintuitive moral judgment

    Science.gov (United States)

    Wiech, Katja; Shackel, Nicholas; Farias, Miguel; Savulescu, Julian; Tracey, Irene

    2012-01-01

    Neuroimaging studies on moral decision-making have thus far largely focused on differences between moral judgments with opposing utilitarian (well-being maximizing) and deontological (duty-based) content. However, these studies have investigated moral dilemmas involving extreme situations, and did not control for two distinct dimensions of moral judgment: whether or not it is intuitive (immediately compelling to most people) and whether it is utilitarian or deontological in content. By contrasting dilemmas where utilitarian judgments are counterintuitive with dilemmas in which they are intuitive, we were able to use functional magnetic resonance imaging to identify the neural correlates of intuitive and counterintuitive judgments across a range of moral situations. Irrespective of content (utilitarian/deontological), counterintuitive moral judgments were associated with greater difficulty and with activation in the rostral anterior cingulate cortex, suggesting that such judgments may involve emotional conflict; intuitive judgments were linked to activation in the visual and premotor cortex. In addition, we obtained evidence that neural differences in moral judgment in such dilemmas are largely due to whether they are intuitive and not, as previously assumed, to differences between utilitarian and deontological judgments. Our findings therefore do not support theories that have generally associated utilitarian and deontological judgments with distinct neural systems. PMID:21421730

  1. Where's the Noise? Key Features of Spontaneous Activity and Neural Variability Arise through Learning in a Deterministic Network.

    Directory of Open Access Journals (Sweden)

    Christoph Hartmann

    2015-12-01

    Full Text Available Even in the absence of sensory stimulation the brain is spontaneously active. This background "noise" seems to be the dominant cause of the notoriously high trial-to-trial variability of neural recordings. Recent experimental observations have extended our knowledge of trial-to-trial variability and spontaneous activity in several directions: 1. Trial-to-trial variability systematically decreases following the onset of a sensory stimulus or the start of a motor act. 2. Spontaneous activity states in sensory cortex outline the region of evoked sensory responses. 3. Across development, spontaneous activity aligns itself with typical evoked activity patterns. 4. The spontaneous brain activity prior to the presentation of an ambiguous stimulus predicts how the stimulus will be interpreted. At present it is unclear how these observations relate to each other and how they arise in cortical circuits. Here we demonstrate that all of these phenomena can be accounted for by a deterministic self-organizing recurrent neural network model (SORN, which learns a predictive model of its sensory environment. The SORN comprises recurrently coupled populations of excitatory and inhibitory threshold units and learns via a combination of spike-timing dependent plasticity (STDP and homeostatic plasticity mechanisms. Similar to balanced network architectures, units in the network show irregular activity and variable responses to inputs. Additionally, however, the SORN exhibits sequence learning abilities matching recent findings from visual cortex and the network's spontaneous activity reproduces the experimental findings mentioned above. Intriguingly, the network's behaviour is reminiscent of sampling-based probabilistic inference, suggesting that correlates of sampling-based inference can develop from the interaction of STDP and homeostasis in deterministic networks. We conclude that key observations on spontaneous brain activity and the variability of neural

  2. The Molecular Basis of Neural Memory. Part 7: Neural Intelligence (NI versus Artificial Intelligence (AI

    Directory of Open Access Journals (Sweden)

    Gerard Marx

    2017-07-01

    Full Text Available The link of memory to intelligence is incontestable, though the development of electronic artifacts with memory has confounded cognitive and computer scientists’ conception of memory and its relevance to “intelligence”. We propose two categories of “Intelligence”: (1 Logical (objective — mathematics, numbers, pattern recognition, games, programmable in binary format. (2 Emotive (subjective — sensations, feelings, perceptions, goals desires, sociability, sex, food, love. The 1st has been reduced to computational algorithms of which we are well versed, witness global technology and the internet. The 2nd relates to the mysterious process whereby (psychic emotive states are achieved by neural beings sensing, comprehending, remembering and dealing with their surroundings. Many theories and philosophies have been forwarded to rationalize this process, but as neuroscientists, we remain dissatisfied. Our own musings on universal neural memory, suggest a tripartite mechanism involving neurons interacting with their surroundings, notably the neural extracellular matrix (nECM with dopants [trace metals and neurotransmitters (NTs]. In particular, the NTs are the molecular encoders of emotive states. We have developed a chemographic representation of such a molecular code.To quote Longuet-Higgins, “Perhaps it is time for the term ‘artificial intelligence’ to be replaced by something more modest and less provisional”. We suggest “artifact intelligence” (ARTI or “machine intelligence” (MI, neither of which imply emulation of emotive neural processes, but simply refer to the ‘demotive’ (lacking emotive quality capability of electronic artifacts that employ a recall function, to calculate algorithms.

  3. Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks.

    Science.gov (United States)

    Le, Nguyen-Quoc-Khanh; Ho, Quang-Thai; Ou, Yu-Yen

    2018-06-13

    Deep learning has been increasingly used to solve a number of problems with state-of-the-art performance in a wide variety of fields. In biology, deep learning can be applied to reduce feature extraction time and achieve high levels of performance. In our present work, we apply deep learning via two-dimensional convolutional neural networks and position-specific scoring matrices to classify Rab protein molecules, which are main regulators in membrane trafficking for transferring proteins and other macromolecules throughout the cell. The functional loss of specific Rab molecular functions has been implicated in a variety of human diseases, e.g., choroideremia, intellectual disabilities, cancer. Therefore, creating a precise model for classifying Rabs is crucial in helping biologists understand the molecular functions of Rabs and design drug targets according to such specific human disease information. We constructed a robust deep neural network for classifying Rabs that achieved an accuracy of 99%, 99.5%, 96.3%, and 97.6% for each of four specific molecular functions. Our approach demonstrates superior performance to traditional artificial neural networks. Therefore, from our proposed study, we provide both an effective tool for classifying Rab proteins and a basis for further research that can improve the performance of biological modeling using deep neural networks. Copyright © 2018 Elsevier Inc. All rights reserved.

  4. An H(∞) control approach to robust learning of feedforward neural networks.

    Science.gov (United States)

    Jing, Xingjian

    2011-09-01

    A novel H(∞) robust control approach is proposed in this study to deal with the learning problems of feedforward neural networks (FNNs). The analysis and design of a desired weight update law for the FNN is transformed into a robust controller design problem for a discrete dynamic system in terms of the estimation error. The drawbacks of some existing learning algorithms can therefore be revealed, especially for the case that the output data is fast changing with respect to the input or the output data is corrupted by noise. Based on this approach, the optimal learning parameters can be found by utilizing the linear matrix inequality (LMI) optimization techniques to achieve a predefined H(∞) "noise" attenuation level. Several existing BP-type algorithms are shown to be special cases of the new H(∞)-learning algorithm. Theoretical analysis and several examples are provided to show the advantages of the new method. Copyright © 2011 Elsevier Ltd. All rights reserved.

  5. Neural networks for aircraft control

    Science.gov (United States)

    Linse, Dennis

    1990-01-01

    Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

  6. Diagnosis of mechanical pumping system using neural networks and system parameters analysis

    International Nuclear Information System (INIS)

    Tsai, Tai Ming; Wang, Wei Hui

    2009-01-01

    Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input- output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions were artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended

  7. Diagnosis of mechanical pumping system using neural networks and system parameters analysis

    Energy Technology Data Exchange (ETDEWEB)

    Tsai, Tai Ming; Wang, Wei Hui [National Taiwan Ocean University, Keelung (China)

    2009-01-15

    Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input- output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions were artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended

  8. A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

    DEFF Research Database (Denmark)

    Sturm, Bob L.; Kereliuk, Corey; Pikrakis, Aggelos

    2014-01-01

    Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look...

  9. Hardware Acceleration of Adaptive Neural Algorithms.

    Energy Technology Data Exchange (ETDEWEB)

    James, Conrad D. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

    2017-11-01

    As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - world conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.

  10. Wood Modification at High Temperature and Pressurized Steam: a Relational Model of Mechanical Properties Based on a Neural Network

    Directory of Open Access Journals (Sweden)

    Hong Yang

    2015-07-01

    Full Text Available Thermally modified wood has high dimensional stability and biological durability.But if the process parameters of thermal modification are not appropriate, then there will be a decline in the physical properties of wood.A neural network algorithm was employed in this study to establish the relationship between the process parameters of high-temperature and high-pressure thermal modification and the mechanical properties of the wood. Three important parameters: temperature, relative humidity, and treatment time, were considered as the inputs to the neural network. Back propagation (BP neural network and radial basis function (RBF neural network models for prediction were built and compared. The comparison showed that the RBF neural network model had advantages in network structure, convergence speed, and generalization capacity. On this basis, the inverse model, reflecting the relationship between the process parameters and the mechanical properties of wood, was established. Given the desired mechanical properties of the wood, the thermal modification process parameters could be inversely optimized and predicted. The results indicated that the model has good learning ability and generalization capacity. This is of great importance for the theoretical and applicational studies of the thermal modification of wood.

  11. Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

    Science.gov (United States)

    Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

    2017-03-01

    Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

  12. Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

    Science.gov (United States)

    Li, Siqi; Jiang, Huiyan; Pang, Wenbo

    2017-05-01

    Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. A neural network model for credit risk evaluation.

    Science.gov (United States)

    Khashman, Adnan

    2009-08-01

    Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.

  14. Evolvable Neural Software System

    Science.gov (United States)

    Curtis, Steven A.

    2009-01-01

    The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.

  15. Learning Control of Fixed-Wing Unmanned Aerial Vehicles Using Fuzzy Neural Networks

    Directory of Open Access Journals (Sweden)

    Erdal Kayacan

    2017-01-01

    Full Text Available A learning control strategy is preferred for the control and guidance of a fixed-wing unmanned aerial vehicle to deal with lack of modeling and flight uncertainties. For learning the plant model as well as changing working conditions online, a fuzzy neural network (FNN is used in parallel with a conventional P (proportional controller. Among the learning algorithms in the literature, a derivative-free one, sliding mode control (SMC theory-based learning algorithm, is preferred as it has been proved to be computationally efficient in real-time applications. Its proven robustness and finite time converging nature make the learning algorithm appropriate for controlling an unmanned aerial vehicle as the computational power is always limited in unmanned aerial vehicles (UAVs. The parameter update rules and stability conditions of the learning are derived, and the proof of the stability of the learning algorithm is shown by using a candidate Lyapunov function. Intensive simulations are performed to illustrate the applicability of the proposed controller which includes the tracking of a three-dimensional trajectory by the UAV subject to time-varying wind conditions. The simulation results show the efficiency of the proposed control algorithm, especially in real-time control systems because of its computational efficiency.

  16. Neural coding of basic reward terms of animal learning theory, game theory, microeconomics and behavioural ecology.

    Science.gov (United States)

    Schultz, Wolfram

    2004-04-01

    Neurons in a small number of brain structures detect rewards and reward-predicting stimuli and are active during the expectation of predictable food and liquid rewards. These neurons code the reward information according to basic terms of various behavioural theories that seek to explain reward-directed learning, approach behaviour and decision-making. The involved brain structures include groups of dopamine neurons, the striatum including the nucleus accumbens, the orbitofrontal cortex and the amygdala. The reward information is fed to brain structures involved in decision-making and organisation of behaviour, such as the dorsolateral prefrontal cortex and possibly the parietal cortex. The neural coding of basic reward terms derived from formal theories puts the neurophysiological investigation of reward mechanisms on firm conceptual grounds and provides neural correlates for the function of rewards in learning, approach behaviour and decision-making.

  17. Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data.

    Science.gov (United States)

    Koutsoukas, Alexios; Monaghan, Keith J; Li, Xiaoli; Huan, Jun

    2017-06-28

    In recent years, research in artificial neural networks has resurged, now under the deep-learning umbrella, and grown extremely popular. Recently reported success of DL techniques in crowd-sourced QSAR and predictive toxicology competitions has showcased these methods as powerful tools in drug-discovery and toxicology research. The aim of this work was dual, first large number of hyper-parameter configurations were explored to investigate how they affect the performance of DNNs and could act as starting points when tuning DNNs and second their performance was compared to popular methods widely employed in the field of cheminformatics namely Naïve Bayes, k-nearest neighbor, random forest and support vector machines. Moreover, robustness of machine learning methods to different levels of artificially introduced noise was assessed. The open-source Caffe deep-learning framework and modern NVidia GPU units were utilized to carry out this study, allowing large number of DNN configurations to be explored. We show that feed-forward deep neural networks are capable of achieving strong classification performance and outperform shallow methods across diverse activity classes when optimized. Hyper-parameters that were found to play critical role are the activation function, dropout regularization, number hidden layers and number of neurons. When compared to the rest methods, tuned DNNs were found to statistically outperform, with p value <0.01 based on Wilcoxon statistical test. DNN achieved on average MCC units of 0.149 higher than NB, 0.092 than kNN, 0.052 than SVM with linear kernel, 0.021 than RF and finally 0.009 higher than SVM with radial basis function kernel. When exploring robustness to noise, non-linear methods were found to perform well when dealing with low levels of noise, lower than or equal to 20%, however when dealing with higher levels of noise, higher than 30%, the Naïve Bayes method was found to perform well and even outperform at the highest level of

  18. Shindigs, brunches, and rodeos: the neural basis of event words.

    Science.gov (United States)

    Bedny, Marina; Dravida, Swethasri; Saxe, Rebecca

    2014-09-01

    Events (e.g., "running" or "eating") constitute a basic type within human cognition and human language. We asked whether thinking about events, as compared to other conceptual categories, depends on partially independent neural circuits. Indirect evidence for this hypothesis comes from previous studies showing elevated posterior temporal responses to verbs, which typically label events. Neural responses to verbs could, however, be driven either by their grammatical or by their semantic properties. In the present experiment, we separated the effects of grammatical class (verb vs. noun) and semantic category (event vs. object) by measuring neural responses to event nouns (e.g., "the hurricane"). Participants rated the semantic relatedness of event nouns, as well as of two categories of object nouns-animals (e.g., "the alligator") and plants (e.g., "the acorn")-and three categories of verbs-manner of motion (e.g., "to roll"), emission (e.g., "to sparkle"), and perception (e.g., "to gaze"). As has previously been observed, we found larger responses to verbs than to object nouns in the left posterior middle (LMTG) and superior (LSTG) temporal gyri. Crucially, we also found that the LMTG responds more to event than to object nouns. These data suggest that part of the posterior lateral temporal response to verbs is driven by their semantic properties. By contrast, a more superior region, at the junction of the temporal and parietal cortices, responded more to verbs than to all nouns, irrespective of their semantic category. We concluded that the neural mechanisms engaged when thinking about event and object categories are partially dissociable.

  19. Structural reliability calculation method based on the dual neural network and direct integration method.

    Science.gov (United States)

    Li, Haibin; He, Yun; Nie, Xiaobo

    2018-01-01

    Structural reliability analysis under uncertainty is paid wide attention by engineers and scholars due to reflecting the structural characteristics and the bearing actual situation. The direct integration method, started from the definition of reliability theory, is easy to be understood, but there are still mathematics difficulties in the calculation of multiple integrals. Therefore, a dual neural network method is proposed for calculating multiple integrals in this paper. Dual neural network consists of two neural networks. The neural network A is used to learn the integrand function, and the neural network B is used to simulate the original function. According to the derivative relationships between the network output and the network input, the neural network B is derived from the neural network A. On this basis, the performance function of normalization is employed in the proposed method to overcome the difficulty of multiple integrations and to improve the accuracy for reliability calculations. The comparisons between the proposed method and Monte Carlo simulation method, Hasofer-Lind method, the mean value first-order second moment method have demonstrated that the proposed method is an efficient and accurate reliability method for structural reliability problems.

  20. Introduction to Concepts in Artificial Neural Networks

    Science.gov (United States)

    Niebur, Dagmar

    1995-01-01

    This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.

  1. Neural networks and applications tutorial

    Science.gov (United States)

    Guyon, I.

    1991-09-01

    The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

  2. BELM: Bayesian extreme learning machine.

    Science.gov (United States)

    Soria-Olivas, Emilio; Gómez-Sanchis, Juan; Martín, José D; Vila-Francés, Joan; Martínez, Marcelino; Magdalena, José R; Serrano, Antonio J

    2011-03-01

    The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities. Bayesian ELM is benchmarked against classical ELM in several artificial and real datasets that are widely used for the evaluation of machine learning algorithms. Achieved results show that the proposed approach produces a competitive accuracy with some additional advantages, namely, automatic production of CIs, reduction of probability of model overfitting, and use of a priori knowledge.

  3. Neural architecture design based on extreme learning machine.

    Science.gov (United States)

    Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

    2013-12-01

    Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

  4. A Telescopic Binary Learning Machine for Training Neural Networks.

    Science.gov (United States)

    Brunato, Mauro; Battiti, Roberto

    2017-03-01

    This paper proposes a new algorithm based on multiscale stochastic local search with binary representation for training neural networks [binary learning machine (BLM)]. We study the effects of neighborhood evaluation strategies, the effect of the number of bits per weight and that of the maximum weight range used for mapping binary strings to real values. Following this preliminary investigation, we propose a telescopic multiscale version of local search, where the number of bits is increased in an adaptive manner, leading to a faster search and to local minima of better quality. An analysis related to adapting the number of bits in a dynamic way is presented. The control on the number of bits, which happens in a natural manner in the proposed method, is effective to increase the generalization performance. The learning dynamics are discussed and validated on a highly nonlinear artificial problem and on real-world tasks in many application domains; BLM is finally applied to a problem requiring either feedforward or recurrent architectures for feedback control.

  5. QCD-Aware Neural Networks for Jet Physics

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering history of sequential recombination jet algorithms is like the parsing of a sentence. Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based neural network topology varies on an event-by-event basis. Our experiments highlight the flexibility of our method for building task-specific jet embeddings and show that recursive architectures are significantly more accurate and data efficient than previous image-based networks. We extend the analogy from individual jets (sentences) to full events (paragraphs), and show for the first time an event-level classifier operating...

  6. The neural basis of speech sound discrimination from infancy to adulthood

    OpenAIRE

    Partanen, Eino

    2013-01-01

    Rapid processing of speech is facilitated by neural representations of native language phonemes. However, some disorders and developmental conditions, such as developmental dyslexia, can hamper the development of these neural memory traces, leading to language delays and poor academic achievement. While the early identification of such deficits is paramount so that interventions can be started as early as possible, there is currently no systematically used ecologically valid paradigm for the ...

  7. Neural oscillatory mechanisms during novel grammar learning underlying language analytical abilities.

    Science.gov (United States)

    Kepinska, Olga; Pereda, Ernesto; Caspers, Johanneke; Schiller, Niels O

    2017-12-01

    The goal of the present study was to investigate the initial phases of novel grammar learning on a neural level, concentrating on mechanisms responsible for individual variability between learners. Two groups of participants, one with high and one with average language analytical abilities, performed an Artificial Grammar Learning (AGL) task consisting of learning and test phases. During the task, EEG signals from 32 cap-mounted electrodes were recorded and epochs corresponding to the learning phases were analysed. We investigated spectral power modulations over time, and functional connectivity patterns by means of a bivariate, frequency-specific index of phase synchronization termed Phase Locking Value (PLV). Behavioural data showed learning effects in both groups, with a steeper learning curve and higher ultimate attainment for the highly skilled learners. Moreover, we established that cortical connectivity patterns and profiles of spectral power modulations over time differentiated L2 learners with various levels of language analytical abilities. Over the course of the task, the learning process seemed to be driven by whole-brain functional connectivity between neuronal assemblies achieved by means of communication in the beta band frequency. On a shorter time-scale, increasing proficiency on the AGL task appeared to be supported by stronger local synchronisation within the right hemisphere regions. Finally, we observed that the highly skilled learners might have exerted less mental effort, or reduced attention for the task at hand once the learning was achieved, as evidenced by the higher alpha band power. Copyright © 2017 Elsevier Inc. All rights reserved.

  8. Consciousness and neural plasticity

    DEFF Research Database (Denmark)

    changes or to abandon the strong identity thesis altogether. Were one to pursue a theory according to which consciousness is not an epiphenomenon to brain processes, consciousness may in fact affect its own neural basis. The neural correlate of consciousness is often seen as a stable structure, that is...

  9. Neural Basis of Acquired Amusia and Its Recovery after Stroke.

    Science.gov (United States)

    Sihvonen, Aleksi J; Ripollés, Pablo; Leo, Vera; Rodríguez-Fornells, Antoni; Soinila, Seppo; Särkämö, Teppo

    2016-08-24

    Although acquired amusia is a relatively common disorder after stroke, its precise neuroanatomical basis is still unknown. To evaluate which brain regions form the neural substrate for acquired amusia and its recovery, we performed a voxel-based lesion-symptom mapping (VLSM) and morphometry (VBM) study with 77 human stroke subjects. Structural MRIs were acquired at acute and 6 month poststroke stages. Amusia and aphasia were behaviorally assessed at acute and 3 month poststroke stages using the Scale and Rhythm subtests of the Montreal Battery of Evaluation of Amusia (MBEA) and language tests. VLSM analyses indicated that amusia was associated with a lesion area comprising the superior temporal gyrus, Heschl's gyrus, insula, and striatum in the right hemisphere, clearly different from the lesion pattern associated with aphasia. Parametric analyses of MBEA Pitch and Rhythm scores showed extensive lesion overlap in the right striatum, as well as in the right Heschl's gyrus and superior temporal gyrus. Lesions associated with Rhythm scores extended more superiorly and posterolaterally. VBM analysis of volume changes from the acute to the 6 month stage showed a clear decrease in gray matter volume in the right superior and middle temporal gyri in nonrecovered amusic patients compared with nonamusic patients. This increased atrophy was more evident in anterior temporal areas in rhythm amusia and in posterior temporal and temporoparietal areas in pitch amusia. Overall, the results implicate right temporal and subcortical regions as the crucial neural substrate for acquired amusia and highlight the importance of different temporal lobe regions for the recovery of amusia after stroke. Lesion studies are essential in uncovering the brain regions causally linked to a given behavior or skill. For music perception ability, previous lesion studies of amusia have been methodologically limited in both spatial accuracy and time domain as well as by small sample sizes, providing

  10. Modeling of biologically motivated self-learning equivalent-convolutional recurrent-multilayer neural structures (BLM_SL_EC_RMNS) for image fragments clustering and recognition

    Science.gov (United States)

    Krasilenko, Vladimir G.; Lazarev, Alexander A.; Nikitovich, Diana V.

    2018-03-01

    The biologically-motivated self-learning equivalence-convolutional recurrent-multilayer neural structures (BLM_SL_EC_RMNS) for fragments images clustering and recognition will be discussed. We shall consider these neural structures and their spatial-invariant equivalental models (SIEMs) based on proposed equivalent two-dimensional functions of image similarity and the corresponding matrix-matrix (or tensor) procedures using as basic operations of continuous logic and nonlinear processing. These SIEMs can simply describe the signals processing during the all training and recognition stages and they are suitable for unipolar-coding multilevel signals. The clustering efficiency in such models and their implementation depends on the discriminant properties of neural elements of hidden layers. Therefore, the main models and architecture parameters and characteristics depends on the applied types of non-linear processing and function used for image comparison or for adaptive-equivalent weighing of input patterns. We show that these SL_EC_RMNSs have several advantages, such as the self-study and self-identification of features and signs of the similarity of fragments, ability to clustering and recognize of image fragments with best efficiency and strong mutual correlation. The proposed combined with learning-recognition clustering method of fragments with regard to their structural features is suitable not only for binary, but also color images and combines self-learning and the formation of weight clustered matrix-patterns. Its model is constructed and designed on the basis of recursively continuous logic and nonlinear processing algorithms and to k-average method or method the winner takes all (WTA). The experimental results confirmed that fragments with a large numbers of elements may be clustered. For the first time the possibility of generalization of these models for space invariant case is shown. The experiment for an images of different dimensions (a reference

  11. Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise.

    Science.gov (United States)

    Vuković, Najdan; Miljković, Zoran

    2015-03-01

    Feedforward neural networks (FFNN) are among the most used neural networks for modeling of various nonlinear problems in engineering. In sequential and especially real time processing all neural networks models fail when faced with outliers. Outliers are found across a wide range of engineering problems. Recent research results in the field have shown that to avoid overfitting or divergence of the model, new approach is needed especially if FFNN is to run sequentially or in real time. To accommodate limitations of FFNN when training data contains a certain number of outliers, this paper presents new learning algorithm based on improvement of conventional extended Kalman filter (EKF). Extended Kalman filter robust to outliers (EKF-OR) is probabilistic generative model in which measurement noise covariance is not constant; the sequence of noise measurement covariance is modeled as stochastic process over the set of symmetric positive-definite matrices in which prior is modeled as inverse Wishart distribution. In each iteration EKF-OR simultaneously estimates noise estimates and current best estimate of FFNN parameters. Bayesian framework enables one to mathematically derive expressions, while analytical intractability of the Bayes' update step is solved by using structured variational approximation. All mathematical expressions in the paper are derived using the first principles. Extensive experimental study shows that FFNN trained with developed learning algorithm, achieves low prediction error and good generalization quality regardless of outliers' presence in training data. Copyright © 2014 Elsevier Ltd. All rights reserved.

  12. The shared neural basis of empathy and facial imitation accuracy.

    Science.gov (United States)

    Braadbaart, L; de Grauw, H; Perrett, D I; Waiter, G D; Williams, J H G

    2014-01-01

    Empathy involves experiencing emotion vicariously, and understanding the reasons for those emotions. It may be served partly by a motor simulation function, and therefore share a neural basis with imitation (as opposed to mimicry), as both involve sensorimotor representations of intentions based on perceptions of others' actions. We recently showed a correlation between imitation accuracy and Empathy Quotient (EQ) using a facial imitation task and hypothesised that this relationship would be mediated by the human mirror neuron system. During functional Magnetic Resonance Imaging (fMRI), 20 adults observed novel 'blends' of facial emotional expressions. According to instruction, they either imitated (i.e. matched) the expressions or executed alternative, pre-prescribed mismatched actions as control. Outside the scanner we replicated the association between imitation accuracy and EQ. During fMRI, activity was greater during mismatch compared to imitation, particularly in the bilateral insula. Activity during imitation correlated with EQ in somatosensory cortex, intraparietal sulcus and premotor cortex. Imitation accuracy correlated with activity in insula and areas serving motor control. Overlapping voxels for the accuracy and EQ correlations occurred in premotor cortex. We suggest that both empathy and facial imitation rely on formation of action plans (or a simulation of others' intentions) in the premotor cortex, in connection with representations of emotional expressions based in the somatosensory cortex. In addition, the insula may play a key role in the social regulation of facial expression. © 2013.

  13. Neural Basis of Action Understanding: Evidence from Sign Language Aphasia.

    Science.gov (United States)

    Rogalsky, Corianne; Raphel, Kristin; Tomkovicz, Vivian; O'Grady, Lucinda; Damasio, Hanna; Bellugi, Ursula; Hickok, Gregory

    2013-01-01

    The neural basis of action understanding is a hotly debated issue. The mirror neuron account holds that motor simulation in fronto-parietal circuits is critical to action understanding including speech comprehension, while others emphasize the ventral stream in the temporal lobe. Evidence from speech strongly supports the ventral stream account, but on the other hand, evidence from manual gesture comprehension (e.g., in limb apraxia) has led to contradictory findings. Here we present a lesion analysis of sign language comprehension. Sign language is an excellent model for studying mirror system function in that it bridges the gap between the visual-manual system in which mirror neurons are best characterized and language systems which have represented a theoretical target of mirror neuron research. Twenty-one life long deaf signers with focal cortical lesions performed two tasks: one involving the comprehension of individual signs and the other involving comprehension of signed sentences (commands). Participants' lesions, as indicated on MRI or CT scans, were mapped onto a template brain to explore the relationship between lesion location and sign comprehension measures. Single sign comprehension was not significantly affected by left hemisphere damage. Sentence sign comprehension impairments were associated with left temporal-parietal damage. We found that damage to mirror system related regions in the left frontal lobe were not associated with deficits on either of these comprehension tasks. We conclude that the mirror system is not critically involved in action understanding.

  14. Social Interaction Affects Neural Outcomes of Sign Language Learning As a Foreign Language in Adults.

    Science.gov (United States)

    Yusa, Noriaki; Kim, Jungho; Koizumi, Masatoshi; Sugiura, Motoaki; Kawashima, Ryuta

    2017-01-01

    Children naturally acquire a language in social contexts where they interact with their caregivers. Indeed, research shows that social interaction facilitates lexical and phonological development at the early stages of child language acquisition. It is not clear, however, whether the relationship between social interaction and learning applies to adult second language acquisition of syntactic rules. Does learning second language syntactic rules through social interactions with a native speaker or without such interactions impact behavior and the brain? The current study aims to answer this question. Adult Japanese participants learned a new foreign language, Japanese sign language (JSL), either through a native deaf signer or via DVDs. Neural correlates of acquiring new linguistic knowledge were investigated using functional magnetic resonance imaging (fMRI). The participants in each group were indistinguishable in terms of their behavioral data after the instruction. The fMRI data, however, revealed significant differences in the neural activities between two groups. Significant activations in the left inferior frontal gyrus (IFG) were found for the participants who learned JSL through interactions with the native signer. In contrast, no cortical activation change in the left IFG was found for the group who experienced the same visual input for the same duration via the DVD presentation. Given that the left IFG is involved in the syntactic processing of language, spoken or signed, learning through social interactions resulted in an fMRI signature typical of native speakers: activation of the left IFG. Thus, broadly speaking, availability of communicative interaction is necessary for second language acquisition and this results in observed changes in the brain.

  15. Hyperresponsiveness of the Neural Fear Network During Fear Conditioning and Extinction Learning in Male Cocaine Users

    NARCIS (Netherlands)

    Kaag, A.M.; Levar, N.; Woutersen, K.; Homberg, J.R.; Brink, W. van den; Reneman, L.; Wingen, G. van

    2016-01-01

    OBJECTIVE: The authors investigated whether cocaine use disorder is associated with abnormalities in the neural underpinnings of aversive conditioning and extinction learning, as these processes may play an important role in the development and persistence of drug abuse. METHOD: Forty male regular

  16. Neural correlates of reward-based spatial learning in persons with cocaine dependence.

    Science.gov (United States)

    Tau, Gregory Z; Marsh, Rachel; Wang, Zhishun; Torres-Sanchez, Tania; Graniello, Barbara; Hao, Xuejun; Xu, Dongrong; Packard, Mark G; Duan, Yunsuo; Kangarlu, Alayar; Martinez, Diana; Peterson, Bradley S

    2014-02-01

    Dysfunctional learning systems are thought to be central to the pathogenesis of and impair recovery from addictions. The functioning of the brain circuits for episodic memory or learning that support goal-directed behavior has not been studied previously in persons with cocaine dependence (CD). Thirteen abstinent CD and 13 healthy participants underwent MRI scanning while performing a task that requires the use of spatial cues to navigate a virtual-reality environment and find monetary rewards, allowing the functional assessment of the brain systems for spatial learning, a form of episodic memory. Whereas both groups performed similarly on the reward-based spatial learning task, we identified disturbances in brain regions involved in learning and reward in CD participants. In particular, CD was associated with impaired functioning of medial temporal lobe (MTL), a brain region that is crucial for spatial learning (and episodic memory) with concomitant recruitment of striatum (which normally participates in stimulus-response, or habit, learning), and prefrontal cortex. CD was also associated with enhanced sensitivity of the ventral striatum to unexpected rewards but not to expected rewards earned during spatial learning. We provide evidence that spatial learning in CD is characterized by disturbances in functioning of an MTL-based system for episodic memory and a striatum-based system for stimulus-response learning and reward. We have found additional abnormalities in distributed cortical regions. Consistent with findings from animal studies, we provide the first evidence in humans describing the disruptive effects of cocaine on the coordinated functioning of multiple neural systems for learning and memory.

  17. A Neural Basis for the Acquired Capability for Suicide

    Directory of Open Access Journals (Sweden)

    Gopikrishna Deshpande

    2016-08-01

    Full Text Available The high rate of fatal suicidal behavior in men is an urgent issue as highlighted in the public eye via news sources and media outlets. In this study, we have attempted to address this issue and understand the neural substrates underlying the gender differences in the rate of fatal suicidal behavior. The Interpersonal-Psychological Theory of Suicide (IPTS has proposed an explanation for the seemingly paradoxical relationship between gender and suicidal behavior, i.e. greater non-fatal suicide attempts by women but higher number of deaths by suicide in men. This theory states that possessing suicidal desire (due to conditions such as depression alone is not sufficient for a lethal suicide attempt. It is imperative for an individual to have acquired the capability for suicide (ACS along with suicidal desire in order to die by suicide. Therefore, higher levels of ACS in men may explain why men are more likely to die by suicide than women, despite being less likely to experience suicidal ideation or depression. In this study, we used activation likelihood estimation meta-analysis to investigate a potential ACS network that involves neural substrates underlying emotional stoicism, sensation seeking, pain tolerance, and fearlessness of death along with a potential depression network that involves neural substrates that underlie clinical depression. Brain regions commonly found in ACS and depression networks for males and females were further used as seeds to obtain regions functionally and structurally connected to them. We found that the male-specific networks were more widespread and diverse than the female-specific ones. Also, while the former involved motor regions such as the premotor cortex and cerebellum, the latter was dominated by limbic regions. This may support the fact that suicidal desire generally leads to fatal/decisive action in males while in females, it manifests as depression, ideation and generally non-fatal actions. The proposed

  18. Advantages of comparative studies in songbirds to understand the neural basis of sensorimotor integration.

    Science.gov (United States)

    Murphy, Karagh; James, Logan S; Sakata, Jon T; Prather, Jonathan F

    2017-08-01

    Sensorimotor integration is the process through which the nervous system creates a link between motor commands and associated sensory feedback. This process allows for the acquisition and refinement of many behaviors, including learned communication behaviors such as speech and birdsong. Consequently, it is important to understand fundamental mechanisms of sensorimotor integration, and comparative analyses of this process can provide vital insight. Songbirds offer a powerful comparative model system to study how the nervous system links motor and sensory information for learning and control. This is because the acquisition, maintenance, and control of birdsong critically depend on sensory feedback. Furthermore, there is an incredible diversity of song organizations across songbird species, ranging from songs with simple, stereotyped sequences to songs with complex sequencing of vocal gestures, as well as a wide diversity of song repertoire sizes. Despite this diversity, the neural circuitry for song learning, control, and maintenance remains highly similar across species. Here, we highlight the utility of songbirds for the analysis of sensorimotor integration and the insights about mechanisms of sensorimotor integration gained by comparing different songbird species. Key conclusions from this comparative analysis are that variation in song sequence complexity seems to covary with the strength of feedback signals in sensorimotor circuits and that sensorimotor circuits contain distinct representations of elements in the vocal repertoire, possibly enabling evolutionary variation in repertoire sizes. We conclude our review by highlighting important areas of research that could benefit from increased comparative focus, with particular emphasis on the integration of new technologies. Copyright © 2017 the American Physiological Society.

  19. Cocaine self-administration abolishes associative neural encoding in the nucleus accumbens necessary for higher-order learning.

    Science.gov (United States)

    Saddoris, Michael P; Carelli, Regina M

    2014-01-15

    Cocaine use is often associated with diminished cognitive function, persisting even after abstinence from the drug. Likely targets for these changes are the core and shell of the nucleus accumbens (NAc), which are critical for mediating the rewarding aspects of drugs of abuse as well as supporting associative learning. To understand this deficit, we recorded neural activity in the NAc of rats with a history of cocaine self-administration or control subjects while they learned Pavlovian first- and second-order associations. Rats were trained for 2 weeks to self-administer intravenous cocaine or water. Later, rats learned a first-order Pavlovian discrimination where a conditioned stimulus (CS)+ predicted food, and a control (CS-) did not. Rats then learned a second-order association where, absent any food reinforcement, a novel cued (SOC+) predicted the CS+ and another (SOC-) predicted the CS-. Electrophysiological recordings were taken during performance of these tasks in the NAc core and shell. Both control subjects and cocaine-experienced rats learned the first-order association, but only control subjects learned the second-order association. Neural recordings indicated that core and shell neurons encoded task-relevant information that correlated with behavioral performance, whereas this type of encoding was abolished in cocaine-experienced rats. The NAc core and shell perform complementary roles in supporting normal associative learning, functions that are impaired after cocaine experience. This impoverished encoding of motivational behavior, even after abstinence from the drug, might provide a key mechanism to understand why addiction remains a chronically relapsing disorder despite repeated attempts at sobriety. Copyright © 2014 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.

  20. Gradient Learning in Spiking Neural Networks by Dynamic Perturbation of Conductances

    International Nuclear Information System (INIS)

    Fiete, Ila R.; Seung, H. Sebastian

    2006-01-01

    We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic perturbation of the membrane conductances of the neurons. It is compatible with recurrent networks of conductance-based model neurons with dynamic synapses. The method can be interpreted as a biologically plausible synaptic learning rule, if the dynamic perturbations are generated by a special class of 'empiric' synapses driven by random spike trains from an external source

  1. Nonlinear Model Predictive Control Based on a Self-Organizing Recurrent Neural Network.

    Science.gov (United States)

    Han, Hong-Gui; Zhang, Lu; Hou, Ying; Qiao, Jun-Fei

    2016-02-01

    A nonlinear model predictive control (NMPC) scheme is developed in this paper based on a self-organizing recurrent radial basis function (SR-RBF) neural network, whose structure and parameters are adjusted concurrently in the training process. The proposed SR-RBF neural network is represented in a general nonlinear form for predicting the future dynamic behaviors of nonlinear systems. To improve the modeling accuracy, a spiking-based growing and pruning algorithm and an adaptive learning algorithm are developed to tune the structure and parameters of the SR-RBF neural network, respectively. Meanwhile, for the control problem, an improved gradient method is utilized for the solution of the optimization problem in NMPC. The stability of the resulting control system is proved based on the Lyapunov stability theory. Finally, the proposed SR-RBF neural network-based NMPC (SR-RBF-NMPC) is used to control the dissolved oxygen (DO) concentration in a wastewater treatment process (WWTP). Comparisons with other existing methods demonstrate that the SR-RBF-NMPC can achieve a considerably better model fitting for WWTP and a better control performance for DO concentration.

  2. Neural networks involved in learning lexical-semantic and syntactic information in a second language.

    Science.gov (United States)

    Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

    2014-01-01

    The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

  3. A Model to Explain the Emergence of Reward Expectancy neurons using Reinforcement Learning and Neural Network

    OpenAIRE

    Shinya, Ishii; Munetaka, Shidara; Katsunari, Shibata

    2006-01-01

    In an experiment of multi-trial task to obtain a reward, reward expectancy neurons,###which responded only in the non-reward trials that are necessary to advance###toward the reward, have been observed in the anterior cingulate cortex of monkeys.###In this paper, to explain the emergence of the reward expectancy neuron in###terms of reinforcement learning theory, a model that consists of a recurrent neural###network trained based on reinforcement learning is proposed. The analysis of the###hi...

  4. A Neural Circuit for Acoustic Navigation combining Heterosynaptic and Non-synaptic Plasticity that learns Stable Trajectories

    DEFF Research Database (Denmark)

    Shaikh, Danish; Manoonpong, Poramate

    2017-01-01

    controllers be resolved in a manner that generates consistent and stable robot trajectories? We propose a neural circuit that minimises this conflict by learning sensorimotor mappings as neuronal transfer functions between the perceived sound direction and wheel velocities of a simulated non-holonomic mobile...

  5. Reinforcement learning signals in the human striatum distinguish learners from nonlearners during reward-based decision making.

    Science.gov (United States)

    Schönberg, Tom; Daw, Nathaniel D; Joel, Daphna; O'Doherty, John P

    2007-11-21

    The computational framework of reinforcement learning has been used to forward our understanding of the neural mechanisms underlying reward learning and decision-making behavior. It is known that humans vary widely in their performance in decision-making tasks. Here, we used a simple four-armed bandit task in which subjects are almost evenly split into two groups on the basis of their performance: those who do learn to favor choice of the optimal action and those who do not. Using models of reinforcement learning we sought to determine the neural basis of these intrinsic differences in performance by scanning both groups with functional magnetic resonance imaging. We scanned 29 subjects while they performed the reward-based decision-making task. Our results suggest that these two groups differ markedly in the degree to which reinforcement learning signals in the striatum are engaged during task performance. While the learners showed robust prediction error signals in both the ventral and dorsal striatum during learning, the nonlearner group showed a marked absence of such signals. Moreover, the magnitude of prediction error signals in a region of dorsal striatum correlated significantly with a measure of behavioral performance across all subjects. These findings support a crucial role of prediction error signals, likely originating from dopaminergic midbrain neurons, in enabling learning of action selection preferences on the basis of obtained rewards. Thus, spontaneously observed individual differences in decision making performance demonstrate the suggested dependence of this type of learning on the functional integrity of the dopaminergic striatal system in humans.

  6. Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function

    Science.gov (United States)

    Rodríguez-Quiñonez, J. C.; Sergiyenko, O.; Hernandez-Balbuena, D.; Rivas-Lopez, M.; Flores-Fuentes, W.; Basaca-Preciado, L. C.

    2014-12-01

    Many laser scanners depend on their mechanical construction to guarantee their measurements accuracy, however, the current computational technologies allow us to improve these measurements by mathematical methods implemented in neural networks. In this article we are going to introduce the current laser scanner technologies, give a description of our 3D laser scanner and adjust their measurement error by a previously trained feed forward back propagation (FFBP) neural network with a Widrow-Hoff weight/bias learning function. A comparative analysis with other learning functions such as the Kohonen algorithm and gradient descendent with momentum algorithm is presented. Finally, computational simulations are conducted to verify the performance and method uncertainty in the proposed system.

  7. Designing an artificial neural network using radial basis function to model exergetic efficiency of nanofluids in mini double pipe heat exchanger

    Science.gov (United States)

    Ghasemi, Nahid; Aghayari, Reza; Maddah, Heydar

    2018-06-01

    The present study aims at predicting and optimizing exergetic efficiency of TiO2-Al2O3/water nanofluid at different Reynolds numbers, volume fractions and twisted ratios using Artificial Neural Networks (ANN) and experimental data. Central Composite Design (CCD) and cascade Radial Basis Function (RBF) were used to display the significant levels of the analyzed factors on the exergetic efficiency. The size of TiO2-Al2O3/water nanocomposite was 20-70 nm. The parameters of ANN model were adapted by a training algorithm of radial basis function (RBF) with a wide range of experimental data set. Total mean square error and correlation coefficient were used to evaluate the results which the best result was obtained from double layer perceptron neural network with 30 neurons in which total Mean Square Error(MSE) and correlation coefficient (R2) were equal to 0.002 and 0.999, respectively. This indicated successful prediction of the network. Moreover, the proposed equation for predicting exergetic efficiency was extremely successful. According to the optimal curves, the optimum designing parameters of double pipe heat exchanger with inner twisted tape and nanofluid under the constrains of exergetic efficiency 0.937 are found to be Reynolds number 2500, twisted ratio 2.5 and volume fraction( v/v%) 0.05.

  8. Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

    Science.gov (United States)

    Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L

    2016-07-01

    Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text

  9. Rhesus monkey neural stem cell transplantation promotes neural regeneration in rats with hippocampal lesions

    Directory of Open Access Journals (Sweden)

    Li-juan Ye

    2016-01-01

    Full Text Available Rhesus monkey neural stem cells are capable of differentiating into neurons and glial cells. Therefore, neural stem cell transplantation can be used to promote functional recovery of the nervous system. Rhesus monkey neural stem cells (1 × 105 cells/μL were injected into bilateral hippocampi of rats with hippocampal lesions. Confocal laser scanning microscopy demonstrated that green fluorescent protein-labeled transplanted cells survived and grew well. Transplanted cells were detected at the lesion site, but also in the nerve fiber-rich region of the cerebral cortex and corpus callosum. Some transplanted cells differentiated into neurons and glial cells clustering along the ventricular wall, and integrated into the recipient brain. Behavioral tests revealed that spatial learning and memory ability improved, indicating that rhesus monkey neural stem cells noticeably improve spatial learning and memory abilities in rats with hippocampal lesions.

  10. Neural stem cell sex dimorphism in aromatase (CYP19 expression: a basis for differential neural fate

    Directory of Open Access Journals (Sweden)

    Jay Waldron

    2010-11-01

    Full Text Available Jay Waldron1, Althea McCourty1, Laurent Lecanu1,21The Research Institute of the McGill University Health Centre, Montreal, Canada; 2Department of Medicine, McGill University, Quebec, CanadaPurpose: Neural stem cell (NSC transplantation and pharmacologic activation of endogenous neurogenesis are two approaches that trigger a great deal of interest as brain repair strategies. However, the success rate of clinical attempts using stem cells to restore neurologic functions altered either after traumatic brain injury or as a consequence of neurodegenerative disease remains rather disappointing. This suggests that factors affecting the fate of grafted NSCs are largely understudied and remain to be characterized. We recently reported that aging differentially affects the neurogenic properties of male and female NSCs. Although the sex steroids androgens and estrogens participate in the regulation of neurogenesis, to our knowledge, research on how gender-based differences affect the capacity of NSCs to differentiate and condition their neural fate is lacking. In the present study, we explored further the role of cell sex as a determining factor of the neural fate followed by differentiating NSCs and its relationship with a potential differential expression of aromatase (CYP19, the testosterone-metabolizing enzyme.Results: Using NSCs isolated from the subventricular zone of three-month-old male and female Long-Evans rats and maintained as neurospheres, we showed that differentiation triggered by retinoic acid resulted in a neural phenotype that depends on cell sex. Differentiated male NSCs mainly expressed markers of neuronal fate, including ßIII-tubulin, microtubule associated protein 2, growth-associated protein 43, and doublecortin. In contrast, female NSCs essentially expressed the astrocyte marker glial fibrillary acidic protein. Quantification of the expression of aromatase showed a very low level of expression in undifferentiated female NSCs

  11. How we learn to make decisions: rapid propagation of reinforcement learning prediction errors in humans.

    Science.gov (United States)

    Krigolson, Olav E; Hassall, Cameron D; Handy, Todd C

    2014-03-01

    Our ability to make decisions is predicated upon our knowledge of the outcomes of the actions available to us. Reinforcement learning theory posits that actions followed by a reward or punishment acquire value through the computation of prediction errors-discrepancies between the predicted and the actual reward. A multitude of neuroimaging studies have demonstrated that rewards and punishments evoke neural responses that appear to reflect reinforcement learning prediction errors [e.g., Krigolson, O. E., Pierce, L. J., Holroyd, C. B., & Tanaka, J. W. Learning to become an expert: Reinforcement learning and the acquisition of perceptual expertise. Journal of Cognitive Neuroscience, 21, 1833-1840, 2009; Bayer, H. M., & Glimcher, P. W. Midbrain dopamine neurons encode a quantitative reward prediction error signal. Neuron, 47, 129-141, 2005; O'Doherty, J. P. Reward representations and reward-related learning in the human brain: Insights from neuroimaging. Current Opinion in Neurobiology, 14, 769-776, 2004; Holroyd, C. B., & Coles, M. G. H. The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity. Psychological Review, 109, 679-709, 2002]. Here, we used the brain ERP technique to demonstrate that not only do rewards elicit a neural response akin to a prediction error but also that this signal rapidly diminished and propagated to the time of choice presentation with learning. Specifically, in a simple, learnable gambling task, we show that novel rewards elicited a feedback error-related negativity that rapidly decreased in amplitude with learning. Furthermore, we demonstrate the existence of a reward positivity at choice presentation, a previously unreported ERP component that has a similar timing and topography as the feedback error-related negativity that increased in amplitude with learning. The pattern of results we observed mirrored the output of a computational model that we implemented to compute reward

  12. Simplification of neural network model for predicting local power distributions of BWR fuel bundle using learning algorithm with forgetting

    International Nuclear Information System (INIS)

    Tanabe, Akira; Yamamoto, Toru; Shinfuku, Kimihiro; Nakamae, Takuji; Nishide, Fusayo.

    1995-01-01

    Previously a two-layered neural network model was developed to predict the relation between fissile enrichment of each fuel rod and local power distribution in a BWR fuel bundle. This model was obtained intuitively based on 33 patterns of training signals after an intensive survey of the models. Recently, a learning algorithm with forgetting was reported to simplify neural network models. It is an interesting subject what kind of model will be obtained if this algorithm is applied to the complex three-layered model which learns the same training signals. A three-layered model which is expanded to have direct connections between the 1st and the 3rd layer elements has been constructed and the learning method of normal back propagation was applied first to this model. The forgetting algorithm was then added to this learning process. The connections concerned with the 2nd layer elements disappeared and the 2nd layer has become unnecessary. It took a longer computing time by an order to learn the same training signals than the simple back propagation, but the two-layered model was obtained autonomously from the expanded three-layered model. (author)

  13. Fault diagnosis and performance evaluation for high current LIA based on radial basis function neural network

    International Nuclear Information System (INIS)

    Yang Xinglin; Wang Huacen; Chen Nan; Dai Wenhua; Li Jin

    2006-01-01

    High current linear induction accelerator (LIA) is a complicated experimental physics device. It is difficult to evaluate and predict its performance. this paper presents a method which combines wavelet packet transform and radial basis function (RBF) neural network to build fault diagnosis and performance evaluation in order to improve reliability of high current LIA. The signal characteristics vectors which are extracted based on energy parameters of wavelet packet transform can well present the temporal and steady features of pulsed power signal, and reduce data dimensions effectively. The fault diagnosis system for accelerating cell and the trend classification system for the beam current based on RBF networks can perform fault diagnosis and evaluation, and provide predictive information for precise maintenance of high current LIA. (authors)

  14. The neural basis of non-verbal communication-enhanced processing of perceived give-me gestures in 9-month-old girls.

    Science.gov (United States)

    Bakker, Marta; Kaduk, Katharina; Elsner, Claudia; Juvrud, Joshua; Gustaf Gredebäck

    2015-01-01

    This study investigated the neural basis of non-verbal communication. Event-related potentials were recorded while 29 nine-month-old infants were presented with a give-me gesture (experimental condition) and the same hand shape but rotated 90°, resulting in a non-communicative hand configuration (control condition). We found different responses in amplitude between the two conditions, captured in the P400 ERP component. Moreover, the size of this effect was modulated by participants' sex, with girls generally demonstrating a larger relative difference between the two conditions than boys.

  15. A machine learning approach for efficient uncertainty quantification using multiscale methods

    Science.gov (United States)

    Chan, Shing; Elsheikh, Ahmed H.

    2018-02-01

    Several multiscale methods account for sub-grid scale features using coarse scale basis functions. For example, in the Multiscale Finite Volume method the coarse scale basis functions are obtained by solving a set of local problems over dual-grid cells. We introduce a data-driven approach for the estimation of these coarse scale basis functions. Specifically, we employ a neural network predictor fitted using a set of solution samples from which it learns to generate subsequent basis functions at a lower computational cost than solving the local problems. The computational advantage of this approach is realized for uncertainty quantification tasks where a large number of realizations has to be evaluated. We attribute the ability to learn these basis functions to the modularity of the local problems and the redundancy of the permeability patches between samples. The proposed method is evaluated on elliptic problems yielding very promising results.

  16. Differential neural network configuration during human path integration

    Science.gov (United States)

    Arnold, Aiden E. G. F; Burles, Ford; Bray, Signe; Levy, Richard M.; Iaria, Giuseppe

    2014-01-01

    Path integration is a fundamental skill for navigation in both humans and animals. Despite recent advances in unraveling the neural basis of path integration in animal models, relatively little is known about how path integration operates at a neural level in humans. Previous attempts to characterize the neural mechanisms used by humans to visually path integrate have suggested a central role of the hippocampus in allowing accurate performance, broadly resembling results from animal data. However, in recent years both the central role of the hippocampus and the perspective that animals and humans share similar neural mechanisms for path integration has come into question. The present study uses a data driven analysis to investigate the neural systems engaged during visual path integration in humans, allowing for an unbiased estimate of neural activity across the entire brain. Our results suggest that humans employ common task control, attention and spatial working memory systems across a frontoparietal network during path integration. However, individuals differed in how these systems are configured into functional networks. High performing individuals were found to more broadly express spatial working memory systems in prefrontal cortex, while low performing individuals engaged an allocentric memory system based primarily in the medial occipito-temporal region. These findings suggest that visual path integration in humans over short distances can operate through a spatial working memory system engaging primarily the prefrontal cortex and that the differential configuration of memory systems recruited by task control networks may help explain individual biases in spatial learning strategies. PMID:24808849

  17. System Identification Using Multilayer Differential Neural Networks: A New Result

    Directory of Open Access Journals (Sweden)

    J. Humberto Pérez-Cruz

    2012-01-01

    Full Text Available In previous works, a learning law with a dead zone function was developed for multilayer differential neural networks. This scheme requires strictly a priori knowledge of an upper bound for the unmodeled dynamics. In this paper, the learning law is modified in such a way that this condition is relaxed. By this modification, the tuning process is simpler and the dead-zone function is not required anymore. On the basis of this modification and by using a Lyapunov-like analysis, a stronger result is here demonstrated: the exponential convergence of the identification error to a bounded zone. Besides, a value for upper bound of such zone is provided. The workability of this approach is tested by a simulation example.

  18. Individual differences in sensitivity to reward and punishment and neural activity during reward and avoidance learning.

    Science.gov (United States)

    Kim, Sang Hee; Yoon, HeungSik; Kim, Hackjin; Hamann, Stephan

    2015-09-01

    In this functional neuroimaging study, we investigated neural activations during the process of learning to gain monetary rewards and to avoid monetary loss, and how these activations are modulated by individual differences in reward and punishment sensitivity. Healthy young volunteers performed a reinforcement learning task where they chose one of two fractal stimuli associated with monetary gain (reward trials) or avoidance of monetary loss (avoidance trials). Trait sensitivity to reward and punishment was assessed using the behavioral inhibition/activation scales (BIS/BAS). Functional neuroimaging results showed activation of the striatum during the anticipation and reception periods of reward trials. During avoidance trials, activation of the dorsal striatum and prefrontal regions was found. As expected, individual differences in reward sensitivity were positively associated with activation in the left and right ventral striatum during reward reception. Individual differences in sensitivity to punishment were negatively associated with activation in the left dorsal striatum during avoidance anticipation and also with activation in the right lateral orbitofrontal cortex during receiving monetary loss. These results suggest that learning to attain reward and learning to avoid loss are dependent on separable sets of neural regions whose activity is modulated by trait sensitivity to reward or punishment. © The Author (2015). Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

  19. Recurrent fuzzy neural network by using feedback error learning approaches for LFC in interconnected power system

    International Nuclear Information System (INIS)

    Sabahi, Kamel; Teshnehlab, Mohammad; Shoorhedeli, Mahdi Aliyari

    2009-01-01

    In this study, a new adaptive controller based on modified feedback error learning (FEL) approaches is proposed for load frequency control (LFC) problem. The FEL strategy consists of intelligent and conventional controllers in feedforward and feedback paths, respectively. In this strategy, a conventional feedback controller (CFC), i.e. proportional, integral and derivative (PID) controller, is essential to guarantee global asymptotic stability of the overall system; and an intelligent feedforward controller (INFC) is adopted to learn the inverse of the controlled system. Therefore, when the INFC learns the inverse of controlled system, the tracking of reference signal is done properly. Generally, the CFC is designed at nominal operating conditions of the system and, therefore, fails to provide the best control performance as well as global stability over a wide range of changes in the operating conditions of the system. So, in this study a supervised controller (SC), a lookup table based controller, is addressed for tuning of the CFC. During abrupt changes of the power system parameters, the SC adjusts the PID parameters according to these operating conditions. Moreover, for improving the performance of overall system, a recurrent fuzzy neural network (RFNN) is adopted in INFC instead of the conventional neural network, which was used in past studies. The proposed FEL controller has been compared with the conventional feedback error learning controller (CFEL) and the PID controller through some performance indices

  20. Oscillations, neural computations and learning during wake and sleep.

    Science.gov (United States)

    Penagos, Hector; Varela, Carmen; Wilson, Matthew A

    2017-06-01

    Learning and memory theories consider sleep and the reactivation of waking hippocampal neural patterns to be crucial for the long-term consolidation of memories. Here we propose that precisely coordinated representations across brain regions allow the inference and evaluation of causal relationships to train an internal generative model of the world. This training starts during wakefulness and strongly benefits from sleep because its recurring nested oscillations may reflect compositional operations that facilitate a hierarchical processing of information, potentially including behavioral policy evaluations. This suggests that an important function of sleep activity is to provide conditions conducive to general inference, prediction and insight, which contribute to a more robust internal model that underlies generalization and adaptive behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

  1. Learning and retrieval behavior in recurrent neural networks with pre-synaptic dependent homeostatic plasticity

    Science.gov (United States)

    Mizusaki, Beatriz E. P.; Agnes, Everton J.; Erichsen, Rubem; Brunnet, Leonardo G.

    2017-08-01

    The plastic character of brain synapses is considered to be one of the foundations for the formation of memories. There are numerous kinds of such phenomenon currently described in the literature, but their role in the development of information pathways in neural networks with recurrent architectures is still not completely clear. In this paper we study the role of an activity-based process, called pre-synaptic dependent homeostatic scaling, in the organization of networks that yield precise-timed spiking patterns. It encodes spatio-temporal information in the synaptic weights as it associates a learned input with a specific response. We introduce a correlation measure to evaluate the precision of the spiking patterns and explore the effects of different inhibitory interactions and learning parameters. We find that large learning periods are important in order to improve the network learning capacity and discuss this ability in the presence of distinct inhibitory currents.

  2. Probabilistic neural network algorithm for using radon emanations as an earthquake precursor

    International Nuclear Information System (INIS)

    Gupta, Dhawal; Shahani, D.T.

    2014-01-01

    The investigation throughout the world in past two decades provides evidence which indicate that significance variation of radon and other soil gases occur in association with major geophysical events such as earthquake. The traditional statistical algorithm includes regression to remove the effect of the meteorological parameters from the raw radon and anomalies are calculated either taking the periodicity in seasonal variations or periodicity computed using Fast Fourier Transform. In case of neural networks the regression step is avoided. A neural network model can be found which can learn the behavior of radon with respect to meteorological parameter in order that changing emission patterns may be adapted to by the model on its own. The output of this neural model is the estimated radon values. This estimated radon value is used to decide whether anomalous behavior of radon has occurred and a valid precursor may be identified. The neural network model developed using Radial Basis function network gave a prediction rate of 87.7%. The same was accompanied by huge false alarms. The present paper deals with improved neural network algorithm using Probabilistic Neural Networks that requires neither an explicit step of regression nor use of any specific period. This neural network model reduces the false alarms to zero and gave same prediction rate as RBF networks. (author)

  3. Towards an Irritable Bowel Syndrome Control System Based on Artificial Neural Networks

    Science.gov (United States)

    Podolski, Ina; Rettberg, Achim

    To solve health problems with medical applications that use complex algorithms is a trend nowadays. It could also be a chance to help patients with critical problems caused from nerve irritations to overcome them and provide a better living situation. In this paper a system for monitoring and controlling the nerves from the intestine is described on a theoretical basis. The presented system could be applied to the irritable bowel syndrome. For control a neural network is used. The advantages for using a neural network for the control of irritable bowel syndrome are the adaptation and learning. These two aspects are important because the syndrome behavior varies from patient to patient and have also concerning the time a lot of variations with respect to each patient. The developed neural network is implemented and can be simulated. Therefore, it can be shown how the network monitor and control the nerves for individual input parameters.

  4. Drive Control Scheme of Electric Power Assisted Wheelchair Based on Neural Network Learning of Human Wheelchair Operation Characteristics

    Science.gov (United States)

    Tanohata, Naoki; Seki, Hirokazu

    This paper describes a novel drive control scheme of electric power assisted wheelchairs based on neural network learning of human wheelchair operation characteristics. “Electric power assisted wheelchair” which enhances the drive force of the operator by employing electric motors is expected to be widely used as a mobility support system for elderly and disabled people. However, some handicapped people with paralysis of the muscles of one side of the body cannot maneuver the wheelchair as desired because of the difference in the right and left input force. Therefore, this study proposes a neural network learning system of such human wheelchair operation characteristics and a drive control scheme with variable distribution and assistance ratios. Some driving experiments will be performed to confirm the effectiveness of the proposed control system.

  5. Neural systems underlying aversive conditioning in humans with primary and secondary reinforcers

    Directory of Open Access Journals (Sweden)

    Mauricio R Delgado

    2011-05-01

    Full Text Available Money is a secondary reinforcer commonly used across a range of disciplines in experimental paradigms investigating reward learning and decision-making. The effectiveness of monetary reinforcers during aversive learning and its neural basis, however, remains a topic of debate. Specifically, it is unclear if the initial acquisition of aversive representations of monetary losses depends on similar neural systems as more traditional aversive conditioning that involves primary reinforcers. This study contrasts the efficacy of a biologically defined primary reinforcer (shock and a socially defined secondary reinforcer (money during aversive learning and its associated neural circuitry. During a two-part experiment, participants first played a gambling game where wins and losses were based on performance to gain an experimental bank. Participants were then exposed to two separate aversive conditioning sessions. In one session, a primary reinforcer (mild shock served as an unconditioned stimulus (US and was paired with one of two colored squares, the conditioned stimuli (CS+ and CS-, respectively. In another session, a secondary reinforcer (loss of money served as the US and was paired with one of two different CS. Skin conductance responses were greater for CS+ compared to CS- trials irrespective of type of reinforcer. Neuroimaging results revealed that the striatum, a region typically linked with reward-related processing, was found to be involved in the acquisition of aversive conditioned response irrespective of reinforcer type. In contrast, the amygdala was involved during aversive conditioning with primary reinforcers, as suggested by both an exploratory fMRI analysis and a follow-up case study with a patient with bilateral amygdala damage. Taken together, these results suggest that learning about potential monetary losses may depend on reinforcement learning related systems, rather than on typical structures involved in more biologically based

  6. Neural mechanisms of hypnosis and meditation.

    Science.gov (United States)

    De Benedittis, Giuseppe

    2015-12-01

    Hypnosis has been an elusive concept for science for a long time. However, the explosive advances in neuroscience in the last few decades have provided a "bridge of understanding" between classical neurophysiological studies and psychophysiological studies. These studies have shed new light on the neural basis of the hypnotic experience. Furthermore, an ambitious new area of research is focusing on mapping the core processes of psychotherapy and the neurobiology/underlying them. Hypnosis research offers powerful techniques to isolate psychological processes in ways that allow their neural bases to be mapped. The Hypnotic Brain can serve as a way to tap neurocognitive questions and our cognitive assays can in turn shed new light on the neural bases of hypnosis. This cross-talk should enhance research and clinical applications. An increasing body of evidence provides insight in the neural mechanisms of the Meditative Brain. Discrete meditative styles are likely to target different neurodynamic patterns. Recent findings emphasize increased attentional resources activating the attentional and salience networks with coherent perception. Cognitive and emotional equanimity gives rise to an eudaimonic state, made of calm, resilience and stability, readiness to express compassion and empathy, a main goal of Buddhist practices. Structural changes in gray matter of key areas of the brain involved in learning processes suggest that these skills can be learned through practice. Hypnosis and Meditation represent two important, historical and influential landmarks of Western and Eastern civilization and culture respectively. Neuroscience has beginning to provide a better understanding of the mechanisms of both Hypnotic and Meditative Brain, outlining similarities but also differences between the two states and processes. It is important not to view either the Eastern or the Western system as superior to the other. Cross-fertilization of the ancient Eastern meditation techniques

  7. Adolescent-specific patterns of behavior and neural activity during social reinforcement learning.

    Science.gov (United States)

    Jones, Rebecca M; Somerville, Leah H; Li, Jian; Ruberry, Erika J; Powers, Alisa; Mehta, Natasha; Dyke, Jonathan; Casey, B J

    2014-06-01

    Humans are sophisticated social beings. Social cues from others are exceptionally salient, particularly during adolescence. Understanding how adolescents interpret and learn from variable social signals can provide insight into the observed shift in social sensitivity during this period. The present study tested 120 participants between the ages of 8 and 25 years on a social reinforcement learning task where the probability of receiving positive social feedback was parametrically manipulated. Seventy-eight of these participants completed the task during fMRI scanning. Modeling trial-by-trial learning, children and adults showed higher positive learning rates than did adolescents, suggesting that adolescents demonstrated less differentiation in their reaction times for peers who provided more positive feedback. Forming expectations about receiving positive social reinforcement correlated with neural activity within the medial prefrontal cortex and ventral striatum across age. Adolescents, unlike children and adults, showed greater insular activity during positive prediction error learning and increased activity in the supplementary motor cortex and the putamen when receiving positive social feedback regardless of the expected outcome, suggesting that peer approval may motivate adolescents toward action. While different amounts of positive social reinforcement enhanced learning in children and adults, all positive social reinforcement equally motivated adolescents. Together, these findings indicate that sensitivity to peer approval during adolescence goes beyond simple reinforcement theory accounts and suggest possible explanations for how peers may motivate adolescent behavior.

  8. Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

    Science.gov (United States)

    Cheng, Phillip M; Malhi, Harshawn S

    2017-04-01

    The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

  9. Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship

    Science.gov (United States)

    Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.

    2010-01-01

    The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…

  10. Sharpened cortical tuning and enhanced cortico-cortical communication contribute to the long-term neural mechanisms of visual motion perceptual learning.

    Science.gov (United States)

    Chen, Nihong; Bi, Taiyong; Zhou, Tiangang; Li, Sheng; Liu, Zili; Fang, Fang

    2015-07-15

    Much has been debated about whether the neural plasticity mediating perceptual learning takes place at the sensory or decision-making stage in the brain. To investigate this, we trained human subjects in a visual motion direction discrimination task. Behavioral performance and BOLD signals were measured before, immediately after, and two weeks after training. Parallel to subjects' long-lasting behavioral improvement, the neural selectivity in V3A and the effective connectivity from V3A to IPS (intraparietal sulcus, a motion decision-making area) exhibited a persistent increase for the trained direction. Moreover, the improvement was well explained by a linear combination of the selectivity and connectivity increases. These findings suggest that the long-term neural mechanisms of motion perceptual learning are implemented by sharpening cortical tuning to trained stimuli at the sensory processing stage, as well as by optimizing the connections between sensory and decision-making areas in the brain. Copyright © 2015 Elsevier Inc. All rights reserved.

  11. Dopamine prediction errors in reward learning and addiction: from theory to neural circuitry

    Science.gov (United States)

    Keiflin, Ronald; Janak, Patricia H.

    2015-01-01

    Summary Midbrain dopamine (DA) neurons are proposed to signal reward prediction error (RPE), a fundamental parameter in associative learning models. This RPE hypothesis provides a compelling theoretical framework for understanding DA function in reward learning and addiction. New studies support a causal role for DA-mediated RPE activity in promoting learning about natural reward; however, this question has not been explicitly tested in the context of drug addiction. In this review, we integrate theoretical models with experimental findings on the activity of DA systems, and on the causal role of specific neuronal projections and cell types, to provide a circuit-based framework for probing DA-RPE function in addiction. By examining error-encoding DA neurons in the neural network in which they are embedded, hypotheses regarding circuit-level adaptations that possibly contribute to pathological error-signaling and addiction can be formulated and tested. PMID:26494275

  12. Dopamine Prediction Errors in Reward Learning and Addiction: From Theory to Neural Circuitry.

    Science.gov (United States)

    Keiflin, Ronald; Janak, Patricia H

    2015-10-21

    Midbrain dopamine (DA) neurons are proposed to signal reward prediction error (RPE), a fundamental parameter in associative learning models. This RPE hypothesis provides a compelling theoretical framework for understanding DA function in reward learning and addiction. New studies support a causal role for DA-mediated RPE activity in promoting learning about natural reward; however, this question has not been explicitly tested in the context of drug addiction. In this review, we integrate theoretical models with experimental findings on the activity of DA systems, and on the causal role of specific neuronal projections and cell types, to provide a circuit-based framework for probing DA-RPE function in addiction. By examining error-encoding DA neurons in the neural network in which they are embedded, hypotheses regarding circuit-level adaptations that possibly contribute to pathological error signaling and addiction can be formulated and tested. Copyright © 2015 Elsevier Inc. All rights reserved.

  13. Learning to Grasp Unknown Objects Based on 3D Edge Information

    DEFF Research Database (Denmark)

    Bodenhagen, Leon; Kraft, Dirk; Popovic, Mila

    2010-01-01

    In this work we refine an initial grasping behavior based on 3D edge information by learning. Based on a set of autonomously generated evaluated grasps and relations between the semi-global 3D edges, a prediction function is learned that computes a likelihood for the success of a grasp using either...... an offline or an online learning scheme. Both methods are implemented using a hybrid artificial neural network containing standard nodes with a sigmoid activation function and nodes with a radial basis function. We show that a significant performance improvement can be achieved....

  14. Neural basis of quasi-rational decision making.

    Science.gov (United States)

    Lee, Daeyeol

    2006-04-01

    Standard economic theories conceive homo economicus as a rational decision maker capable of maximizing utility. In reality, however, people tend to approximate optimal decision-making strategies through a collection of heuristic routines. Some of these routines are driven by emotional processes, and others are adjusted iteratively through experience. In addition, routines specialized for social decision making, such as inference about the mental states of other decision makers, might share their origins and neural mechanisms with the ability to simulate or imagine outcomes expected from alternative actions that an individual can take. A recent surge of collaborations across economics, psychology and neuroscience has provided new insights into how such multiple elements of decision making interact in the brain.

  15. Cooperative learning neural network output feedback control of uncertain nonlinear multi-agent systems under directed topologies

    Science.gov (United States)

    Wang, W.; Wang, D.; Peng, Z. H.

    2017-09-01

    Without assuming that the communication topologies among the neural network (NN) weights are to be undirected and the states of each agent are measurable, the cooperative learning NN output feedback control is addressed for uncertain nonlinear multi-agent systems with identical structures in strict-feedback form. By establishing directed communication topologies among NN weights to share their learned knowledge, NNs with cooperative learning laws are employed to identify the uncertainties. By designing NN-based κ-filter observers to estimate the unmeasurable states, a new cooperative learning output feedback control scheme is proposed to guarantee that the system outputs can track nonidentical reference signals with bounded tracking errors. A simulation example is given to demonstrate the effectiveness of the theoretical results.

  16. The Last Planner System Style of Planning: Its Basis in Learning Theory

    Directory of Open Access Journals (Sweden)

    Bo Terje Kalsaas

    2012-07-01

    Full Text Available The objective of this article is to contribute to creating a better understanding of the Last Planner System (LPS – which is associated with Lean Construction – in the light of the learning processes at the basis of knowledge development, and of change and innovation. Founded on a theoretical discussion, three research questions are asked, namely: In what ways can the LPS be expected to alter the learning arenas compared to conventional project management in construction; according to learning theory, what are the main challenges associated with implementing the LPS; and, finally, what kind of learning can be linked to an implemented LPS that functions as intended? The implementation of the LPS is shown to require substantial changes to the technical-organisational learning arena. In order for the implementation to be successful, the work identity has to alter on the individual level so that an overlap occurs with the new work practices prescribed by the LPS. The LPS has an inbuilt experiential learning cycle, and provides a good starting point for single-loop learning, as well as for simple forms of double-loop learning (“routinized learning capability”. However, it is argued that the LPS understood as experiential learning has clear limitations with regard to “evolutionary learning capability”. This is amplified by the context project organisation provides. In terms of theoretical implications, this article promotes an understanding of the planning process informed by the theory describing it as an experiential learning cycle. The conceptualisation which separates the LPS from conventional production control theory is critiqued. Finally, it is argued that an understanding of the LPS grounded in learning theory will improve the possibilities for successful implementation and maximise the learning effects.

  17. The Neural Basis of Typewriting: A Functional MRI Study.

    Science.gov (United States)

    Higashiyama, Yuichi; Takeda, Katsuhiko; Someya, Yoshiaki; Kuroiwa, Yoshiyuki; Tanaka, Fumiaki

    2015-01-01

    To investigate the neural substrate of typewriting Japanese words and to detect the difference between the neural substrate of typewriting and handwriting, we conducted a functional magnetic resonance imaging (fMRI) study in 16 healthy volunteers. All subjects were skillful touch typists and performed five tasks: a typing task, a writing task, a reading task, and two control tasks. Three brain regions were activated during both the typing and the writing tasks: the left superior parietal lobule, the left supramarginal gyrus, and the left premotor cortex close to Exner's area. Although typing and writing involved common brain regions, direct comparison between the typing and the writing task revealed greater left posteromedial intraparietal cortex activation in the typing task. In addition, activity in the left premotor cortex was more rostral in the typing task than in the writing task. These findings suggest that, although the brain circuits involved in Japanese typewriting are almost the same as those involved in handwriting, there are brain regions that are specific for typewriting.

  18. The neural basis of suppression and amblyopia in strabismus.

    Science.gov (United States)

    Sengpiel, F; Blakemore, C

    1996-01-01

    The neurophysiological consequences of artificial strabismus in cats and monkeys have been studied for 30 years. However, until very recently no clear picture has emerged of neural deficits that might account for the powerful interocular suppression that strabismic humans experience, nor for the severe amblyopia that is often associated with convergent strabismus. Here we review the effects of squint on the integrative capacities of the primary visual cortex and propose a hypothesis about the relationship between suppression and amblyopia. Most neurons in the visual cortex of normal cats and monkeys can be excited through either eye and show strong facilitation during binocular stimulation with contours of similar orientation in the two eyes. But in strabismic animals, cortical neurons tend to fall into two populations of monocularly excitable cells and exhibit suppressive binocular interactions that share key properties with perceptual suppression in strabismic humans. Such interocular suppression, if prolonged and asymmetric (with input from the squinting eye habitually suppressed by that from the fixating eye), might lead to neural defects in the representation of the deviating eye and hence to amblyopia.

  19. The Neural Basis of Typewriting: A Functional MRI Study.

    Directory of Open Access Journals (Sweden)

    Yuichi Higashiyama

    Full Text Available To investigate the neural substrate of typewriting Japanese words and to detect the difference between the neural substrate of typewriting and handwriting, we conducted a functional magnetic resonance imaging (fMRI study in 16 healthy volunteers. All subjects were skillful touch typists and performed five tasks: a typing task, a writing task, a reading task, and two control tasks. Three brain regions were activated during both the typing and the writing tasks: the left superior parietal lobule, the left supramarginal gyrus, and the left premotor cortex close to Exner's area. Although typing and writing involved common brain regions, direct comparison between the typing and the writing task revealed greater left posteromedial intraparietal cortex activation in the typing task. In addition, activity in the left premotor cortex was more rostral in the typing task than in the writing task. These findings suggest that, although the brain circuits involved in Japanese typewriting are almost the same as those involved in handwriting, there are brain regions that are specific for typewriting.

  20. Neural networks, nativism, and the plausibility of constructivism.

    Science.gov (United States)

    Quartz, S R

    1993-09-01

    Recent interest in PDP (parallel distributed processing) models is due in part to the widely held belief that they challenge many of the assumptions of classical cognitive science. In the domain of language acquisition, for example, there has been much interest in the claim that PDP models might undermine nativism. Related arguments based on PDP learning have also been given against Fodor's anti-constructivist position--a position that has contributed to the widespread dismissal of constructivism. A limitation of many of the claims regarding PDP learning, however, is that the principles underlying this learning have not been rigorously characterized. In this paper, I examine PDP models from within the framework of Valiant's PAC (probably approximately correct) model of learning, now the dominant model in machine learning, and which applies naturally to neural network learning. From this perspective, I evaluate the implications of PDP models for nativism and Fodor's influential anti-constructivist position. In particular, I demonstrate that, contrary to a number of claims, PDP models are nativist in a robust sense. I also demonstrate that PDP models actually serve as a good illustration of Fodor's anti-constructivist position. While these results may at first suggest that neural network models in general are incapable of the sort of concept acquisition that is required to refute Fodor's anti-constructivist position, I suggest that there is an alternative form of neural network learning that demonstrates the plausibility of constructivism. This alternative form of learning is a natural interpretation of the constructivist position in terms of neural network learning, as it employs learning algorithms that incorporate the addition of structure in addition to weight modification schemes. By demonstrating that there is a natural and plausible interpretation of constructivism in terms of neural network learning, the position that nativism is the only plausible model of

  1. Deep learning with convolutional neural networks for EEG decoding and visualization.

    Science.gov (United States)

    Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

    2017-11-01

    Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

  2. Deep learning with convolutional neural networks for EEG decoding and visualization

    Science.gov (United States)

    Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

    2017-01-01

    Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

  3. Learning, memory, and the role of neural network architecture.

    Directory of Open Access Journals (Sweden)

    Ann M Hermundstad

    2011-06-01

    Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

  4. DCS-Neural-Network Program for Aircraft Control and Testing

    Science.gov (United States)

    Jorgensen, Charles C.

    2006-01-01

    A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

  5. Algebraic and adaptive learning in neural control systems

    Science.gov (United States)

    Ferrari, Silvia

    A systematic approach is developed for designing adaptive and reconfigurable nonlinear control systems that are applicable to plants modeled by ordinary differential equations. The nonlinear controller comprising a network of neural networks is taught using a two-phase learning procedure realized through novel techniques for initialization, on-line training, and adaptive critic design. A critical observation is that the gradients of the functions defined by the neural networks must equal corresponding linear gain matrices at chosen operating points. On-line training is based on a dual heuristic adaptive critic architecture that improves control for large, coupled motions by accounting for actual plant dynamics and nonlinear effects. An action network computes the optimal control law; a critic network predicts the derivative of the cost-to-go with respect to the state. Both networks are algebraically initialized based on prior knowledge of satisfactory pointwise linear controllers and continue to adapt on line during full-scale simulations of the plant. On-line training takes place sequentially over discrete periods of time and involves several numerical procedures. A backpropagating algorithm called Resilient Backpropagation is modified and successfully implemented to meet these objectives, without excessive computational expense. This adaptive controller is as conservative as the linear designs and as effective as a global nonlinear controller. The method is successfully implemented for the full-envelope control of a six-degree-of-freedom aircraft simulation. The results show that the on-line adaptation brings about improved performance with respect to the initialization phase during aircraft maneuvers that involve large-angle and coupled dynamics, and parameter variations.

  6. Memory and learning in a class of neural network models

    International Nuclear Information System (INIS)

    Wallace, D.J.

    1986-01-01

    The author discusses memory and learning properties of the neural network model now identified with Hopfield's work. The model, how it attempts to abstract some key features of the nervous system, and the sense in which learning and memory are identified in the model are described. A brief report is presented on the important role of phase transitions in the model and their implications for memory capacity. The results of numerical simulations obtained using the ICL Distributed Array Processors at Edinburgh are presented. A summary is presented on how the fraction of images which are perfectly stored, depends on the number of nodes and the number of nominal images which one attempts to store using the prescription in Hopfield's paper. Results are presented on the second phase transition in the model, which corresponds to almost total loss of storage capacity as the number of nominal images is increased. Results are given on the performance of a new iterative algorithm for exact storage of up to N images in an N node model

  7. Convolutional neural network with transfer learning for rice type classification

    Science.gov (United States)

    Patel, Vaibhav Amit; Joshi, Manjunath V.

    2018-04-01

    Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

  8. Language Learning Enhanced by Massive Multiple Online Role-Playing Games (MMORPGs) and the Underlying Behavioral and Neural Mechanisms

    OpenAIRE

    Zhang, Yongjun; Song, Hongwen; Liu, Xiaoming; Tang, Dinghong; Chen, Yue-e; Zhang, Xiaochu

    2017-01-01

    Massive Multiple Online Role-Playing Games (MMORPGs) have increased in popularity among children, juveniles, and adults since MMORPGs’ appearance in this digital age. MMORPGs can be applied to enhancing language learning, which is drawing researchers’ attention from different fields and many studies have validated MMORPGs’ positive effect on language learning. However, there are few studies on the underlying behavioral or neural mechanism of such effect. This paper reviews the educational app...

  9. A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

    Science.gov (United States)

    Li, Yongcheng; Sun, Rong; Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

    2016-01-01

    We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

  10. A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

    Directory of Open Access Journals (Sweden)

    Yongcheng Li

    Full Text Available We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning. Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

  11. Neural basis of limb ownership in individuals with body integrity identity disorder.

    Directory of Open Access Journals (Sweden)

    Milenna T van Dijk

    Full Text Available Our body feels like it is ours. However, individuals with body integrity identity disorder (BIID lack this feeling of ownership for distinct limbs and desire amputation of perfectly healthy body parts. This extremely rare condition provides us with an opportunity to study the neural basis underlying the feeling of limb ownership, since these individuals have a feeling of disownership for a limb in the absence of apparent brain damage. Here we directly compared brain activation between limbs that do and do not feel as part of the body using functional MRI during separate tactile stimulation and motor execution experiments. In comparison to matched controls, individuals with BIID showed heightened responsivity of a large somatosensory network including the parietal cortex and right insula during tactile stimulation, regardless of whether the stimulated leg felt owned or alienated. Importantly, activity in the ventral premotor cortex depended on the feeling of ownership and was reduced during stimulation of the alienated compared to the owned leg. In contrast, no significant differences between groups were observed during the performance of motor actions. These results suggest that altered somatosensory processing in the premotor cortex is associated with the feeling of disownership in BIID, which may be related to altered integration of somatosensory and proprioceptive information.

  12. Neural basis of limb ownership in individuals with body integrity identity disorder.

    Science.gov (United States)

    van Dijk, Milenna T; van Wingen, Guido A; van Lammeren, Anouk; Blom, Rianne M; de Kwaasteniet, Bart P; Scholte, H Steven; Denys, Damiaan

    2013-01-01

    Our body feels like it is ours. However, individuals with body integrity identity disorder (BIID) lack this feeling of ownership for distinct limbs and desire amputation of perfectly healthy body parts. This extremely rare condition provides us with an opportunity to study the neural basis underlying the feeling of limb ownership, since these individuals have a feeling of disownership for a limb in the absence of apparent brain damage. Here we directly compared brain activation between limbs that do and do not feel as part of the body using functional MRI during separate tactile stimulation and motor execution experiments. In comparison to matched controls, individuals with BIID showed heightened responsivity of a large somatosensory network including the parietal cortex and right insula during tactile stimulation, regardless of whether the stimulated leg felt owned or alienated. Importantly, activity in the ventral premotor cortex depended on the feeling of ownership and was reduced during stimulation of the alienated compared to the owned leg. In contrast, no significant differences between groups were observed during the performance of motor actions. These results suggest that altered somatosensory processing in the premotor cortex is associated with the feeling of disownership in BIID, which may be related to altered integration of somatosensory and proprioceptive information.

  13. Cost-Sensitive Radial Basis Function Neural Network Classifier for Software Defect Prediction.

    Science.gov (United States)

    Kumudha, P; Venkatesan, R

    Effective prediction of software modules, those that are prone to defects, will enable software developers to achieve efficient allocation of resources and to concentrate on quality assurance activities. The process of software development life cycle basically includes design, analysis, implementation, testing, and release phases. Generally, software testing is a critical task in the software development process wherein it is to save time and budget by detecting defects at the earliest and deliver a product without defects to the customers. This testing phase should be carefully operated in an effective manner to release a defect-free (bug-free) software product to the customers. In order to improve the software testing process, fault prediction methods identify the software parts that are more noted to be defect-prone. This paper proposes a prediction approach based on conventional radial basis function neural network (RBFNN) and the novel adaptive dimensional biogeography based optimization (ADBBO) model. The developed ADBBO based RBFNN model is tested with five publicly available datasets from the NASA data program repository. The computed results prove the effectiveness of the proposed ADBBO-RBFNN classifier approach with respect to the considered metrics in comparison with that of the early predictors available in the literature for the same datasets.

  14. Do Convolutional Neural Networks Learn Class Hierarchy?

    Science.gov (United States)

    Bilal, Alsallakh; Jourabloo, Amin; Ye, Mao; Liu, Xiaoming; Ren, Liu

    2018-01-01

    Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.

  15. A connectionist model of category learning by individuals with high-functioning autism spectrum disorder.

    Science.gov (United States)

    Dovgopoly, Alexander; Mercado, Eduardo

    2013-06-01

    Individuals with autism spectrum disorder (ASD) show atypical patterns of learning and generalization. We explored the possible impacts of autism-related neural abnormalities on perceptual category learning using a neural network model of visual cortical processing. When applied to experiments in which children or adults were trained to classify complex two-dimensional images, the model can account for atypical patterns of perceptual generalization. This is only possible, however, when individual differences in learning are taken into account. In particular, analyses performed with a self-organizing map suggested that individuals with high-functioning ASD show two distinct generalization patterns: one that is comparable to typical patterns, and a second in which there is almost no generalization. The model leads to novel predictions about how individuals will generalize when trained with simplified input sets and can explain why some researchers have failed to detect learning or generalization deficits in prior studies of category learning by individuals with autism. On the basis of these simulations, we propose that deficits in basic neural plasticity mechanisms may be sufficient to account for the atypical patterns of perceptual category learning and generalization associated with autism, but they do not account for why only a subset of individuals with autism would show such deficits. If variations in performance across subgroups reflect heterogeneous neural abnormalities, then future behavioral and neuroimaging studies of individuals with ASD will need to account for such disparities.

  16. The neural basis of loss aversion in decision-making under risk.

    Science.gov (United States)

    Tom, Sabrina M; Fox, Craig R; Trepel, Christopher; Poldrack, Russell A

    2007-01-26

    People typically exhibit greater sensitivity to losses than to equivalent gains when making decisions. We investigated neural correlates of loss aversion while individuals decided whether to accept or reject gambles that offered a 50/50 chance of gaining or losing money. A broad set of areas (including midbrain dopaminergic regions and their targets) showed increasing activity as potential gains increased. Potential losses were represented by decreasing activity in several of these same gain-sensitive areas. Finally, individual differences in behavioral loss aversion were predicted by a measure of neural loss aversion in several regions, including the ventral striatum and prefrontal cortex.

  17. HIERtalker: A default hierarchy of high order neural networks that learns to read English aloud

    Energy Technology Data Exchange (ETDEWEB)

    An, Z.G.; Mniszewski, S.M.; Lee, Y.C.; Papcun, G.; Doolen, G.D.

    1988-01-01

    A new learning algorithm based on a default hierarchy of high order neural networks has been developed that is able to generalize as well as handle exceptions. It learns the ''building blocks'' or clusters of symbols in a stream that appear repeatedly and convey certain messages. The default hierarchy prevents a combinatoric explosion of rules. A simulator of such a hierarchy, HIERtalker, has been applied to the conversion of English words to phonemes. Achieved accuracy is 99% for trained words and ranges from 76% to 96% for sets of new words. 8 refs., 4 figs., 1 tab.

  18. Neural network error correction for solving coupled ordinary differential equations

    Science.gov (United States)

    Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

    1992-01-01

    A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

  19. Comment on 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study'.

    Science.gov (United States)

    Valdes, Gilmer; Interian, Yannet

    2018-03-15

    The application of machine learning (ML) presents tremendous opportunities for the field of oncology, thus we read 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study' with great interest. In this article, the authors used state of the art techniques: a pre-trained convolutional neural network (VGG-16 CNN), transfer learning, data augmentation, drop out and early stopping, all of which are directly responsible for the success and the excitement that these algorithms have created in other fields. We believe that the use of these techniques can offer tremendous opportunities in the field of Medical Physics and as such we would like to praise the authors for their pioneering application to the field of Radiation Oncology. That being said, given that the field of Medical Physics has unique characteristics that differentiate us from those fields where these techniques have been applied successfully, we would like to raise some points for future discussion and follow up studies that could help the community understand the limitations and nuances of deep learning techniques.

  20. Habituation in non-neural organisms: evidence from slime moulds.

    Science.gov (United States)

    Boisseau, Romain P; Vogel, David; Dussutour, Audrey

    2016-04-27

    Learning, defined as a change in behaviour evoked by experience, has hitherto been investigated almost exclusively in multicellular neural organisms. Evidence for learning in non-neural multicellular organisms is scant, and only a few unequivocal reports of learning have been described in single-celled organisms. Here we demonstrate habituation, an unmistakable form of learning, in the non-neural organism Physarum polycephalum In our experiment, using chemotaxis as the behavioural output and quinine or caffeine as the stimulus, we showed that P. polycephalum learnt to ignore quinine or caffeine when the stimuli were repeated, but responded again when the stimulus was withheld for a certain time. Our results meet the principle criteria that have been used to demonstrate habituation: responsiveness decline and spontaneous recovery. To distinguish habituation from sensory adaptation or motor fatigue, we also show stimulus specificity. Our results point to the diversity of organisms lacking neurons, which likely display a hitherto unrecognized capacity for learning, and suggest that slime moulds may be an ideal model system in which to investigate fundamental mechanisms underlying learning processes. Besides, documenting learning in non-neural organisms such as slime moulds is centrally important to a comprehensive, phylogenetic understanding of when and where in the tree of life the earliest manifestations of learning evolved. © 2016 The Author(s).