Experimental Demonstrations of Optical Neural Computers

OpenAIRE

Hsu, Ken; Brady, David; Psaltis, Demetri

1988-01-01

We describe two experiments in optical neural computing. In the first a closed optical feedback loop is used to implement auto-associative image recall. In the second a perceptron-like learning algorithm is implemented with photorefractive holography.

Computational chaos in massively parallel neural networks

Science.gov (United States)

Barhen, Jacob; Gulati, Sandeep

1989-01-01

A fundamental issue which directly impacts the scalability of current theoretical neural network models to massively parallel embodiments, in both software as well as hardware, is the inherent and unavoidable concurrent asynchronicity of emerging fine-grained computational ensembles and the possible emergence of chaotic manifestations. Previous analyses attributed dynamical instability to the topology of the interconnection matrix, to parasitic components or to propagation delays. However, researchers have observed the existence of emergent computational chaos in a concurrently asynchronous framework, independent of the network topology. Researcher present a methodology enabling the effective asynchronous operation of large-scale neural networks. Necessary and sufficient conditions guaranteeing concurrent asynchronous convergence are established in terms of contracting operators. Lyapunov exponents are computed formally to characterize the underlying nonlinear dynamics. Simulation results are presented to illustrate network convergence to the correct results, even in the presence of large delays.

Brains--Computers--Machines: Neural Engineering in Science Classrooms

Science.gov (United States)

Chudler, Eric H.; Bergsman, Kristen Clapper

2016-01-01

Neural engineering is an emerging field of high relevance to students, teachers, and the general public. This feature presents online resources that educators and scientists can use to introduce students to neural engineering and to integrate core ideas from the life sciences, physical sciences, social sciences, computer science, and engineering…

Optoelectronic Computer Architecture Development for Image Reconstruction

National Research Council Canada - National Science Library

Forber, Richard

1996-01-01

.... Specifically, we collaborated with UCSD and ERIM on the development of an optically augmented electronic computer for high speed inverse transform calculations to enable real time image reconstruction...

Efficient universal computing architectures for decoding neural activity.

Directory of Open Access Journals (Sweden)

Benjamin I Rapoport

Full Text Available The ability to decode neural activity into meaningful control signals for prosthetic devices is critical to the development of clinically useful brain- machine interfaces (BMIs. Such systems require input from tens to hundreds of brain-implanted recording electrodes in order to deliver robust and accurate performance; in serving that primary function they should also minimize power dissipation in order to avoid damaging neural tissue; and they should transmit data wirelessly in order to minimize the risk of infection associated with chronic, transcutaneous implants. Electronic architectures for brain- machine interfaces must therefore minimize size and power consumption, while maximizing the ability to compress data to be transmitted over limited-bandwidth wireless channels. Here we present a system of extremely low computational complexity, designed for real-time decoding of neural signals, and suited for highly scalable implantable systems. Our programmable architecture is an explicit implementation of a universal computing machine emulating the dynamics of a network of integrate-and-fire neurons; it requires no arithmetic operations except for counting, and decodes neural signals using only computationally inexpensive logic operations. The simplicity of this architecture does not compromise its ability to compress raw neural data by factors greater than [Formula: see text]. We describe a set of decoding algorithms based on this computational architecture, one designed to operate within an implanted system, minimizing its power consumption and data transmission bandwidth; and a complementary set of algorithms for learning, programming the decoder, and postprocessing the decoded output, designed to operate in an external, nonimplanted unit. The implementation of the implantable portion is estimated to require fewer than 5000 operations per second. A proof-of-concept, 32-channel field-programmable gate array (FPGA implementation of this portion

Neural computing thermal comfort index for HVAC systems

International Nuclear Information System (INIS)

Atthajariyakul, S.; Leephakpreeda, T.

2005-01-01

The primary purpose of a heating, ventilating and air conditioning (HVAC) system within a building is to make occupants comfortable. Without real time determination of human thermal comfort, it is not feasible for the HVAC system to yield controlled conditions of the air for human comfort all the time. This paper presents a practical approach to determine human thermal comfort quantitatively via neural computing. The neural network model allows real time determination of the thermal comfort index, where it is not practical to compute the conventional predicted mean vote (PMV) index itself in real time. The feed forward neural network model is proposed as an explicit function of the relation of the PMV index to accessible variables, i.e. the air temperature, wet bulb temperature, globe temperature, air velocity, clothing insulation and human activity. An experiment in an air conditioned office room was done to demonstrate the effectiveness of the proposed methodology. The results show good agreement between the thermal comfort index calculated from the neural network model in real time and those calculated from the conventional PMV model

The super-Turing computational power of plastic recurrent neural networks.

Science.gov (United States)

Cabessa, Jérémie; Siegelmann, Hava T

2014-12-01

We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power--as the static analog neural networks--irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

Computational neural network regression model for Host based Intrusion Detection System

Directory of Open Access Journals (Sweden)

Sunil Kumar Gautam

2016-09-01

Full Text Available The current scenario of information gathering and storing in secure system is a challenging task due to increasing cyber-attacks. There exists computational neural network techniques designed for intrusion detection system, which provide security to single machine and entire network's machine. In this paper, we have used two types of computational neural network models, namely, Generalized Regression Neural Network (GRNN model and Multilayer Perceptron Neural Network (MPNN model for Host based Intrusion Detection System using log files that are generated by a single personal computer. The simulation results show correctly classified percentage of normal and abnormal (intrusion class using confusion matrix. On the basis of results and discussion, we found that the Host based Intrusion Systems Model (HISM significantly improved the detection accuracy while retaining minimum false alarm rate.

Connecting Neural Coding to Number Cognition: A Computational Account

Science.gov (United States)

Prather, Richard W.

2012-01-01

The current study presents a series of computational simulations that demonstrate how the neural coding of numerical magnitude may influence number cognition and development. This includes behavioral phenomena cataloged in cognitive literature such as the development of numerical estimation and operational momentum. Though neural research has…

Inherently stochastic spiking neurons for probabilistic neural computation

KAUST Repository

Al-Shedivat, Maruan

2015-04-01

Neuromorphic engineering aims to design hardware that efficiently mimics neural circuitry and provides the means for emulating and studying neural systems. In this paper, we propose a new memristor-based neuron circuit that uniquely complements the scope of neuron implementations and follows the stochastic spike response model (SRM), which plays a cornerstone role in spike-based probabilistic algorithms. We demonstrate that the switching of the memristor is akin to the stochastic firing of the SRM. Our analysis and simulations show that the proposed neuron circuit satisfies a neural computability condition that enables probabilistic neural sampling and spike-based Bayesian learning and inference. Our findings constitute an important step towards memristive, scalable and efficient stochastic neuromorphic platforms. © 2015 IEEE.

Neural Computations in a Dynamical System with Multiple Time Scales.

Science.gov (United States)

Mi, Yuanyuan; Lin, Xiaohan; Wu, Si

2016-01-01

Neural systems display rich short-term dynamics at various levels, e.g., spike-frequency adaptation (SFA) at the single-neuron level, and short-term facilitation (STF) and depression (STD) at the synapse level. These dynamical features typically cover a broad range of time scales and exhibit large diversity in different brain regions. It remains unclear what is the computational benefit for the brain to have such variability in short-term dynamics. In this study, we propose that the brain can exploit such dynamical features to implement multiple seemingly contradictory computations in a single neural circuit. To demonstrate this idea, we use continuous attractor neural network (CANN) as a working model and include STF, SFA and STD with increasing time constants in its dynamics. Three computational tasks are considered, which are persistent activity, adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, and hence cannot be implemented by a single dynamical feature or any combination with similar time constants. However, with properly coordinated STF, SFA and STD, we show that the network is able to implement the three computational tasks concurrently. We hope this study will shed light on the understanding of how the brain orchestrates its rich dynamics at various levels to realize diverse cognitive functions.

Neural decoding of collective wisdom with multi-brain computing.

Science.gov (United States)

Eckstein, Miguel P; Das, Koel; Pham, Binh T; Peterson, Matthew F; Abbey, Craig K; Sy, Jocelyn L; Giesbrecht, Barry

2012-01-02

Group decisions and even aggregation of multiple opinions lead to greater decision accuracy, a phenomenon known as collective wisdom. Little is known about the neural basis of collective wisdom and whether its benefits arise in late decision stages or in early sensory coding. Here, we use electroencephalography and multi-brain computing with twenty humans making perceptual decisions to show that combining neural activity across brains increases decision accuracy paralleling the improvements shown by aggregating the observers' opinions. Although the largest gains result from an optimal linear combination of neural decision variables across brains, a simpler neural majority decision rule, ubiquitous in human behavior, results in substantial benefits. In contrast, an extreme neural response rule, akin to a group following the most extreme opinion, results in the least improvement with group size. Analyses controlling for number of electrodes and time-points while increasing number of brains demonstrate unique benefits arising from integrating neural activity across different brains. The benefits of multi-brain integration are present in neural activity as early as 200 ms after stimulus presentation in lateral occipital sites and no additional benefits arise in decision related neural activity. Sensory-related neural activity can predict collective choices reached by aggregating individual opinions, voting results, and decision confidence as accurately as neural activity related to decision components. Estimation of the potential for the collective to execute fast decisions by combining information across numerous brains, a strategy prevalent in many animals, shows large time-savings. Together, the findings suggest that for perceptual decisions the neural activity supporting collective wisdom and decisions arises in early sensory stages and that many properties of collective cognition are explainable by the neural coding of information across multiple brains. Finally

Partnering through Staff Rotation in a Multi-Branch Academic Library: One Example at the UCSD Libraries

Science.gov (United States)

Goodson, Kymberly Anne

2006-01-01

The article describes a partnership between two of the libraries at the University of California, San Diego (UCSD) through which two staff in one library worked part-time at the other during the summer of 2006 in order to maximize staffing efficiency among the units, as well as to realize professional development-related goals for the staff…

Content validity of CASA-Q cough domains and UCSD-SOBQ for use in patients with Idiopathic Pulmonary Fibrosis.

Science.gov (United States)

Gries, Katharine Suzanne; Esser, Dirk; Wiklund, Ingela

2013-09-16

The study objective was to assess the content validity of the Cough and Sputum Assessment Questionnaire (CASA-Q) cough domains and the UCSD Shortness of Breath Questionnaire (SOBQ) for use in patients with Idiopathic Pulmonary Fibrosis (IPF). Cross-sectional, qualitative study with cognitive interviews in patients with IPF. Study outcomes included relevance, comprehension of item meaning, understanding of the instructions, recall period, response options, and concept saturation. Interviews were conducted with 18 IPF patients. The mean age was 68.9 years (SD 11.9), 77.8% were male, and 88.9% were Caucasian. The intended meaning of the CASA-Q cough domain items was clearly understood by most of the participants (89-100%). All participants understood the CASA-Q instructions; the correct recall period was reported by 89% of the patients, and the response options were understood by 76%. The intended meaning of the UCSD-SOBQ items was relevant and clearly understood by all participants. Participants understood the instructions (83%) and all patients understood the response options (100%). The reported recall period varied based on the type of activity performed. No concepts were missing, suggesting that saturation was demonstrated for both measures. This study provides evidence for content validity for the CASA-Q cough domains and the UCSD-SOBQ for patients with IPF. Items of both questionnaires were understood and perceived as relevant to measure the key symptoms of IPF. The results of this study support the use of these instruments in IPF clinical trials as well as further studies of their psychometric properties.

Hybrid computing using a neural network with dynamic external memory.

Science.gov (United States)

Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago; Agapiou, John; Badia, Adrià Puigdomènech; Hermann, Karl Moritz; Zwols, Yori; Ostrovski, Georg; Cain, Adam; King, Helen; Summerfield, Christopher; Blunsom, Phil; Kavukcuoglu, Koray; Hassabis, Demis

2016-10-27

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

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.

Exploratory analysis of normative performance on the UCSD Performance-Based Skills Assessment-Brief.

Science.gov (United States)

Vella, Lea; Patterson, Thomas L; Harvey, Philip D; McClure, Margaret McNamara; Mausbach, Brent T; Taylor, Michael J; Twamley, Elizabeth W

2017-10-01

The UCSD Performance-Based Skills Assessment (UPSA) is a performance-based measure of functional capacity. The brief, two-domain (finance and communication ability) version of the assessment (UPSA-B) is now widely used in both clinical research and treatment trials. To date, research has not examined possible demographic-UPSA-B relationships within a non-psychiatric population. We aimed to produce and describe preliminary normative scores for the UPSA-B over a full range of ages and educational attainment. The finance and communication subscales of the UPSA were administered to 190 healthy participants in the context of three separate studies. These data were combined to examine the effects of age, sex, and educational attainment on the UPSA-B domain and total scores. Fractional polynomial regression was used to compute demographically-corrected T-scores for the UPSA-B total score, and percentile rank conversion was used for the two subscales. Age and education both had significant non-linear effects on the UPSA-B total score. The finance subscale was significantly related to both gender and years of education, whereas the communication subscale was not significantly related to any of the demographic characteristics. Demographically corrected T-scores and percentile ranks for UPSA-B scores are now available for use in clinical research. Published by Elsevier B.V.

Integrated Markov-neural reliability computation method: A case for multiple automated guided vehicle system

International Nuclear Information System (INIS)

Fazlollahtabar, Hamed; Saidi-Mehrabad, Mohammad; Balakrishnan, Jaydeep

2015-01-01

This paper proposes an integrated Markovian and back propagation neural network approaches to compute reliability of a system. While states of failure occurrences are significant elements for accurate reliability computation, Markovian based reliability assessment method is designed. Due to drawbacks shown by Markovian model for steady state reliability computations and neural network for initial training pattern, integration being called Markov-neural is developed and evaluated. To show efficiency of the proposed approach comparative analyses are performed. Also, for managerial implication purpose an application case for multiple automated guided vehicles (AGVs) in manufacturing networks is conducted. - Highlights: • Integrated Markovian and back propagation neural network approach to compute reliability. • Markovian based reliability assessment method. • Managerial implication is shown in an application case for multiple automated guided vehicles (AGVs) in manufacturing networks

Advanced neural network-based computational schemes for robust fault diagnosis

CERN Document Server

Mrugalski, Marcin

2014-01-01

The present book is devoted to problems of adaptation of artificial neural networks to robust fault diagnosis schemes. It presents neural networks-based modelling and estimation techniques used for designing robust fault diagnosis schemes for non-linear dynamic systems. A part of the book focuses on fundamental issues such as architectures of dynamic neural networks, methods for designing of neural networks and fault diagnosis schemes as well as the importance of robustness. The book is of a tutorial value and can be perceived as a good starting point for the new-comers to this field. The book is also devoted to advanced schemes of description of neural model uncertainty. In particular, the methods of computation of neural networks uncertainty with robust parameter estimation are presented. Moreover, a novel approach for system identification with the state-space GMDH neural network is delivered. All the concepts described in this book are illustrated by both simple academic illustrative examples and practica...

Computationally efficient model predictive control algorithms a neural network approach

CERN Document Server

Ławryńczuk, Maciej

2014-01-01

This book thoroughly discusses computationally efficient (suboptimal) Model Predictive Control (MPC) techniques based on neural models. The subjects treated include: ·         A few types of suboptimal MPC algorithms in which a linear approximation of the model or of the predicted trajectory is successively calculated on-line and used for prediction. ·         Implementation details of the MPC algorithms for feedforward perceptron neural models, neural Hammerstein models, neural Wiener models and state-space neural models. ·         The MPC algorithms based on neural multi-models (inspired by the idea of predictive control). ·         The MPC algorithms with neural approximation with no on-line linearization. ·         The MPC algorithms with guaranteed stability and robustness. ·         Cooperation between the MPC algorithms and set-point optimization. Thanks to linearization (or neural approximation), the presented suboptimal algorithms do not require d...

Advances in neural networks computational and theoretical issues

CERN Document Server

Esposito, Anna; Morabito, Francesco

2015-01-01

This book collects research works that exploit neural networks and machine learning techniques from a multidisciplinary perspective. Subjects covered include theoretical, methodological and computational topics which are grouped together into chapters devoted to the discussion of novelties and innovations related to the field of Artificial Neural Networks as well as the use of neural networks for applications, pattern recognition, signal processing, and special topics such as the detection and recognition of multimodal emotional expressions and daily cognitive functions, and  bio-inspired memristor-based networks.  Providing insights into the latest research interest from a pool of international experts coming from different research fields, the volume becomes valuable to all those with any interest in a holistic approach to implement believable, autonomous, adaptive, and context-aware Information Communication Technologies.

Advances in neural networks computational intelligence for ICT

CERN Document Server

Esposito, Anna; Morabito, Francesco; Pasero, Eros

2016-01-01

This carefully edited book is putting emphasis on computational and artificial intelligent methods for learning and their relative applications in robotics, embedded systems, and ICT interfaces for psychological and neurological diseases. The book is a follow-up of the scientific workshop on Neural Networks (WIRN 2015) held in Vietri sul Mare, Italy, from the 20th to the 22nd of May 2015. The workshop, at its 27th edition became a traditional scientific event that brought together scientists from many countries, and several scientific disciplines. Each chapter is an extended version of the original contribution presented at the workshop, and together with the reviewers’ peer revisions it also benefits from the live discussion during the presentation. The content of book is organized in the following sections. 1. Introduction, 2. Machine Learning, 3. Artificial Neural Networks: Algorithms and models, 4. Intelligent Cyberphysical and Embedded System, 5. Computational Intelligence Methods for Biomedical ICT in...

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks

Science.gov (United States)

Pyle, Ryan; Rosenbaum, Robert

2017-01-01

Randomly connected networks of excitatory and inhibitory spiking neurons provide a parsimonious model of neural variability, but are notoriously unreliable for performing computations. We show that this difficulty is overcome by incorporating the well-documented dependence of connection probability on distance. Spatially extended spiking networks exhibit symmetry-breaking bifurcations and generate spatiotemporal patterns that can be trained to perform dynamical computations under a reservoir computing framework.

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks.

Science.gov (United States)

Pyle, Ryan; Rosenbaum, Robert

2017-01-06

Randomly connected networks of excitatory and inhibitory spiking neurons provide a parsimonious model of neural variability, but are notoriously unreliable for performing computations. We show that this difficulty is overcome by incorporating the well-documented dependence of connection probability on distance. Spatially extended spiking networks exhibit symmetry-breaking bifurcations and generate spatiotemporal patterns that can be trained to perform dynamical computations under a reservoir computing framework.

Review On Applications Of Neural Network To Computer Vision

Science.gov (United States)

Li, Wei; Nasrabadi, Nasser M.

1989-03-01

Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.

Fusion of neural computing and PLS techniques for load estimation

Energy Technology Data Exchange (ETDEWEB)

Lu, M.; Xue, H.; Cheng, X. [Northwestern Polytechnical Univ., Xi' an (China); Zhang, W. [Xi' an Inst. of Post and Telecommunication, Xi' an (China)

2007-07-01

A method to predict the electric load of a power system in real time was presented. The method is based on neurocomputing and partial least squares (PLS). Short-term load forecasts for power systems are generally determined by conventional statistical methods and Computational Intelligence (CI) techniques such as neural computing. However, statistical modeling methods often require the input of questionable distributional assumptions, and neural computing is weak, particularly in determining topology. In order to overcome the problems associated with conventional techniques, the authors developed a CI hybrid model based on neural computation and PLS techniques. The theoretical foundation for the designed CI hybrid model was presented along with its application in a power system. The hybrid model is suitable for nonlinear modeling and latent structure extracting. It can automatically determine the optimal topology to maximize the generalization. The CI hybrid model provides faster convergence and better prediction results compared to the abductive networks model because it incorporates a load conversion technique as well as new transfer functions. In order to demonstrate the effectiveness of the hybrid model, load forecasting was performed on a data set obtained from the Puget Sound Power and Light Company. Compared with the abductive networks model, the CI hybrid model reduced the forecast error by 32.37 per cent on workday, and by an average of 27.18 per cent on the weekend. It was concluded that the CI hybrid model has a more powerful predictive ability. 7 refs., 1 tab., 3 figs.

Biological neural networks as model systems for designing future parallel processing computers

Science.gov (United States)

Ross, Muriel D.

1991-01-01

One of the more interesting debates of the present day centers on whether human intelligence can be simulated by computer. The author works under the premise that neurons individually are not smart at all. Rather, they are physical units which are impinged upon continuously by other matter that influences the direction of voltage shifts across the units membranes. It is only the action of a great many neurons, billions in the case of the human nervous system, that intelligent behavior emerges. What is required to understand even the simplest neural system is painstaking analysis, bit by bit, of the architecture and the physiological functioning of its various parts. The biological neural network studied, the vestibular utricular and saccular maculas of the inner ear, are among the most simple of the mammalian neural networks to understand and model. While there is still a long way to go to understand even this most simple neural network in sufficient detail for extrapolation to computers and robots, a start was made. Moreover, the insights obtained and the technologies developed help advance the understanding of the more complex neural networks that underlie human intelligence.

UCSD's Institute of Engineering in Medicine: fostering collaboration through research and education.

Science.gov (United States)

Chien, Shu

2012-07-01

The University of California, San Diego (UCSD) was established in 1961 as a new research university that emphasizes innovation, excellence, and interdisciplinary research and education. It has a School of Medicine (SOM) and the Jacobs School of Engineering (JSOE) in close proximity, and both schools have national rankings among the top 15. In 1991, with the support of the Whitaker Foundation, the Whitaker Institute of Biomedical Engineering was formed to foster collaborations in research and education. In 2008, the university extended the collaboration further by establishing the Institute of Engineering in Medicine (IEM), with the mission of accelerating the discoveries of novel science and technology to enhance health care through teamwork between engineering and medicine, and facilitating the translation of innovative technologies for delivery to the public through clinical application and commercialization.

Instrumentation for Scientific Computing in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics.

Science.gov (United States)

1987-10-01

include Security Classification) Instrumentation for scientific computing in neural networks, information science, artificial intelligence, and...instrumentation grant to purchase equipment for support of research in neural networks, information science, artificail intellignece , and applied mathematics...in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics Contract AFOSR 86-0282 Principal Investigator: Stephen

THE COMPUTATIONAL INTELLIGENCE TECHNIQUES FOR PREDICTIONS - ARTIFICIAL NEURAL NETWORKS

OpenAIRE

Mary Violeta Bar

2014-01-01

The computational intelligence techniques are used in problems which can not be solved by traditional techniques when there is insufficient data to develop a model problem or when they have errors.Computational intelligence, as he called Bezdek (Bezdek, 1992) aims at modeling of biological intelligence. Artificial Neural Networks( ANNs) have been applied to an increasing number of real world problems of considerable complexity. Their most important advantage is solving problems that are too c...

Computational Models and Emergent Properties of Respiratory Neural Networks

Science.gov (United States)

Lindsey, Bruce G.; Rybak, Ilya A.; Smith, Jeffrey C.

2012-01-01

Computational models of the neural control system for breathing in mammals provide a theoretical and computational framework bringing together experimental data obtained from different animal preparations under various experimental conditions. Many of these models were developed in parallel and iteratively with experimental studies and provided predictions guiding new experiments. This data-driven modeling approach has advanced our understanding of respiratory network architecture and neural mechanisms underlying generation of the respiratory rhythm and pattern, including their functional reorganization under different physiological conditions. Models reviewed here vary in neurobiological details and computational complexity and span multiple spatiotemporal scales of respiratory control mechanisms. Recent models describe interacting populations of respiratory neurons spatially distributed within the Bötzinger and pre-Bötzinger complexes and rostral ventrolateral medulla that contain core circuits of the respiratory central pattern generator (CPG). Network interactions within these circuits along with intrinsic rhythmogenic properties of neurons form a hierarchy of multiple rhythm generation mechanisms. The functional expression of these mechanisms is controlled by input drives from other brainstem components, including the retrotrapezoid nucleus and pons, which regulate the dynamic behavior of the core circuitry. The emerging view is that the brainstem respiratory network has rhythmogenic capabilities at multiple levels of circuit organization. This allows flexible, state-dependent expression of different neural pattern-generation mechanisms under various physiological conditions, enabling a wide repertoire of respiratory behaviors. Some models consider control of the respiratory CPG by pulmonary feedback and network reconfiguration during defensive behaviors such as cough. Future directions in modeling of the respiratory CPG are considered. PMID:23687564

Container-code recognition system based on computer vision and deep neural networks

Science.gov (United States)

Liu, Yi; Li, Tianjian; Jiang, Li; Liang, Xiaoyao

2018-04-01

Automatic container-code recognition system becomes a crucial requirement for ship transportation industry in recent years. In this paper, an automatic container-code recognition system based on computer vision and deep neural networks is proposed. The system consists of two modules, detection module and recognition module. The detection module applies both algorithms based on computer vision and neural networks, and generates a better detection result through combination to avoid the drawbacks of the two methods. The combined detection results are also collected for online training of the neural networks. The recognition module exploits both character segmentation and end-to-end recognition, and outputs the recognition result which passes the verification. When the recognition module generates false recognition, the result will be corrected and collected for online training of the end-to-end recognition sub-module. By combining several algorithms, the system is able to deal with more situations, and the online training mechanism can improve the performance of the neural networks at runtime. The proposed system is able to achieve 93% of overall recognition accuracy.

Computational neuroanatomy: ontology-based representation of neural components and connectivity.

Science.gov (United States)

Rubin, Daniel L; Talos, Ion-Florin; Halle, Michael; Musen, Mark A; Kikinis, Ron

2009-02-05

A critical challenge in neuroscience is organizing, managing, and accessing the explosion in neuroscientific knowledge, particularly anatomic knowledge. We believe that explicit knowledge-based approaches to make neuroscientific knowledge computationally accessible will be helpful in tackling this challenge and will enable a variety of applications exploiting this knowledge, such as surgical planning. We developed ontology-based models of neuroanatomy to enable symbolic lookup, logical inference and mathematical modeling of neural systems. We built a prototype model of the motor system that integrates descriptive anatomic and qualitative functional neuroanatomical knowledge. In addition to modeling normal neuroanatomy, our approach provides an explicit representation of abnormal neural connectivity in disease states, such as common movement disorders. The ontology-based representation encodes both structural and functional aspects of neuroanatomy. The ontology-based models can be evaluated computationally, enabling development of automated computer reasoning applications. Neuroanatomical knowledge can be represented in machine-accessible format using ontologies. Computational neuroanatomical approaches such as described in this work could become a key tool in translational informatics, leading to decision support applications that inform and guide surgical planning and personalized care for neurological disease in the future.

From biological neural networks to thinking machines: Transitioning biological organizational principles to computer technology

Science.gov (United States)

Ross, Muriel D.

1991-01-01

The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.

Task III: UCSD/DIII-D/Textor FY-97-98 Accomplishments

International Nuclear Information System (INIS)

Boedo, J.A.

2000-01-01

OAK (B204) Task III: UCSD/DIII-D/Textor FY-97-98 Accomplishments. A comprehensive report on the physics of pump limiters and particularly, the characterization of ALT-II, was published in Nuclear Fusion, bringing the project to a closure. The performance of the toroidal pump limiter was characterized under full auxiliary heating of 7 MW of NBI and ICRH and full pumping, as stated in the project milestones. Relevant highlights are: (1) Pumping with ALT-II allows for density control. (2) The achieved exhaust efficiency is 4% during NBI operation and near 2% during OH or ICRH operation. (3) We have shown that an exhaust efficiency of 2% is sufficient to satisfy the ash removal requirements of fusion reactors. (4) The plasma particle efflux and the pumped flux both increase with density and heating power. (5) The particle confinement time is less than the energy confinement time by a factor of 4. In summary, pumped belt limiters could provide the density control and ash exhaust requirements of fusion reactors

Human Inspired Self-developmental Model of Neural Network (HIM): Introducing Content/Form Computing

Science.gov (United States)

Krajíček, Jiří

This paper presents cross-disciplinary research between medical/psychological evidence on human abilities and informatics needs to update current models in computer science to support alternative methods for computation and communication. In [10] we have already proposed hypothesis introducing concept of human information model (HIM) as cooperative system. Here we continue on HIM design in detail. In our design, first we introduce Content/Form computing system which is new principle of present methods in evolutionary computing (genetic algorithms, genetic programming). Then we apply this system on HIM (type of artificial neural network) model as basic network self-developmental paradigm. Main inspiration of our natural/human design comes from well known concept of artificial neural networks, medical/psychological evidence and Sheldrake theory of "Nature as Alive" [22].

Neural Computations in a Dynamical System with Multiple Time Scales

Directory of Open Access Journals (Sweden)

Yuanyuan Mi

2016-09-01

Full Text Available Neural systems display rich short-term dynamics at various levels, e.g., spike-frequencyadaptation (SFA at single neurons, and short-term facilitation (STF and depression (STDat neuronal synapses. These dynamical features typically covers a broad range of time scalesand exhibit large diversity in different brain regions. It remains unclear what the computationalbenefit for the brain to have such variability in short-term dynamics is. In this study, we proposethat the brain can exploit such dynamical features to implement multiple seemingly contradictorycomputations in a single neural circuit. To demonstrate this idea, we use continuous attractorneural network (CANN as a working model and include STF, SFA and STD with increasing timeconstants in their dynamics. Three computational tasks are considered, which are persistent activity,adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, andhence cannot be implemented by a single dynamical feature or any combination with similar timeconstants. However, with properly coordinated STF, SFA and STD, we show that the network isable to implement the three computational tasks concurrently. We hope this study will shed lighton the understanding of how the brain orchestrates its rich dynamics at various levels to realizediverse cognitive functions.

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.

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.

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

Optics in neural computation

Science.gov (United States)

Levene, Michael John

In all attempts to emulate the considerable powers of the brain, one is struck by both its immense size, parallelism, and complexity. While the fields of neural networks, artificial intelligence, and neuromorphic engineering have all attempted oversimplifications on the considerable complexity, all three can benefit from the inherent scalability and parallelism of optics. This thesis looks at specific aspects of three modes in which optics, and particularly volume holography, can play a part in neural computation. First, holography serves as the basis of highly-parallel correlators, which are the foundation of optical neural networks. The huge input capability of optical neural networks make them most useful for image processing and image recognition and tracking. These tasks benefit from the shift invariance of optical correlators. In this thesis, I analyze the capacity of correlators, and then present several techniques for controlling the amount of shift invariance. Of particular interest is the Fresnel correlator, in which the hologram is displaced from the Fourier plane. In this case, the amount of shift invariance is limited not just by the thickness of the hologram, but by the distance of the hologram from the Fourier plane. Second, volume holography can provide the huge storage capacity and high speed, parallel read-out necessary to support large artificial intelligence systems. However, previous methods for storing data in volume holograms have relied on awkward beam-steering or on as-yet non- existent cheap, wide-bandwidth, tunable laser sources. This thesis presents a new technique, shift multiplexing, which is capable of very high densities, but which has the advantage of a very simple implementation. In shift multiplexing, the reference wave consists of a focused spot a few millimeters in front of the hologram. Multiplexing is achieved by simply translating the hologram a few tens of microns or less. This thesis describes the theory for how shift

Computational modeling of neural activities for statistical inference

CERN Document Server

Kolossa, Antonio

2016-01-01

This authored monograph supplies empirical evidence for the Bayesian brain hypothesis by modeling event-related potentials (ERP) of the human electroencephalogram (EEG) during successive trials in cognitive tasks. The employed observer models are useful to compute probability distributions over observable events and hidden states, depending on which are present in the respective tasks. Bayesian model selection is then used to choose the model which best explains the ERP amplitude fluctuations. Thus, this book constitutes a decisive step towards a better understanding of the neural coding and computing of probabilities following Bayesian rules. The target audience primarily comprises research experts in the field of computational neurosciences, but the book may also be beneficial for graduate students who want to specialize in this field. .

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

Science.gov (United States)

Plagianakos, V P; Magoulas, G D; Vrahatis, M N

2006-03-01

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

A neural algorithm for a fundamental computing problem.

Science.gov (United States)

Dasgupta, Sanjoy; Stevens, Charles F; Navlakha, Saket

2017-11-10

Similarity search-for example, identifying similar images in a database or similar documents on the web-is a fundamental computing problem faced by large-scale information retrieval systems. We discovered that the fruit fly olfactory circuit solves this problem with a variant of a computer science algorithm (called locality-sensitive hashing). The fly circuit assigns similar neural activity patterns to similar odors, so that behaviors learned from one odor can be applied when a similar odor is experienced. The fly algorithm, however, uses three computational strategies that depart from traditional approaches. These strategies can be translated to improve the performance of computational similarity searches. This perspective helps illuminate the logic supporting an important sensory function and provides a conceptually new algorithm for solving a fundamental computational problem. Copyright © 2017 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.

Neural computation of visual imaging based on Kronecker product in the primary visual cortex

Directory of Open Access Journals (Sweden)

Guozheng Yao

2010-03-01

Full Text Available Abstract Background What kind of neural computation is actually performed by the primary visual cortex and how is this represented mathematically at the system level? It is an important problem in the visual information processing, but has not been well answered. In this paper, according to our understanding of retinal organization and parallel multi-channel topographical mapping between retina and primary visual cortex V1, we divide an image into orthogonal and orderly array of image primitives (or patches, in which each patch will evoke activities of simple cells in V1. From viewpoint of information processing, this activated process, essentially, involves optimal detection and optimal matching of receptive fields of simple cells with features contained in image patches. For the reconstruction of the visual image in the visual cortex V1 based on the principle of minimum mean squares error, it is natural to use the inner product expression in neural computation, which then is transformed into matrix form. Results The inner product is carried out by using Kronecker product between patches and function architecture (or functional column in localized and oriented neural computing. Compared with Fourier Transform, the mathematical description of Kronecker product is simple and intuitive, so is the algorithm more suitable for neural computation of visual cortex V1. Results of computer simulation based on two-dimensional Gabor pyramid wavelets show that the theoretical analysis and the proposed model are reasonable. Conclusions Our results are: 1. The neural computation of the retinal image in cortex V1 can be expressed to Kronecker product operation and its matrix form, this algorithm is implemented by the inner operation between retinal image primitives and primary visual cortex's column. It has simple, efficient and robust features, which is, therefore, such a neural algorithm, which can be completed by biological vision. 2. It is more suitable

Depth perception in frogs and toads a study in neural computing

CERN Document Server

House, Donald

1989-01-01

Depth Perception in Frogs and Toads provides a comprehensive exploration of the phenomenon of depth perception in frogs and toads, as seen from a neuro-computational point of view. Perhaps the most important feature of the book is the development and presentation of two neurally realizable depth perception algorithms that utilize both monocular and binocular depth cues in a cooperative fashion. One of these algorithms is specialized for computation of depth maps for navigation, and the other for the selection and localization of a single prey for prey catching. The book is also unique in that it thoroughly reviews the known neuroanatomical, neurophysiological and behavioral data, and then synthesizes, organizes and interprets that information to explain a complex sensory-motor task. The book will be of special interest to that segment of the neural computing community interested in understanding natural neurocomputational structures, particularly to those working in perception and sensory-motor coordination. ...

Quantum perceptron over a field and neural network architecture selection in a quantum computer.

Science.gov (United States)

da Silva, Adenilton José; Ludermir, Teresa Bernarda; de Oliveira, Wilson Rosa

2016-04-01

In this work, we propose a quantum neural network named quantum perceptron over a field (QPF). Quantum computers are not yet a reality and the models and algorithms proposed in this work cannot be simulated in actual (or classical) computers. QPF is a direct generalization of a classical perceptron and solves some drawbacks found in previous models of quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimizes the neural network weights and architectures. SAL searches for the best architecture in a finite set of neural network architectures with linear time over the number of patterns in the training set. SAL is the first learning algorithm to determine neural network architectures in polynomial time. This speedup is obtained by the use of quantum parallelism and a non-linear quantum operator. Copyright © 2016 Elsevier Ltd. All rights reserved.

Evolutionary Computation and Its Applications in Neural and Fuzzy Systems

Directory of Open Access Journals (Sweden)

Biaobiao Zhang

2011-01-01

Full Text Available Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neo-Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.

A Neural Information Field Approach to Computational Cognition

Science.gov (United States)

2016-11-18

effects of distraction during list memory . These distractions include short and long delays before recall, and continuous distraction (forced rehearsal... memory encoding and replay in hippocampus. Computational Neuroscience Society (CNS), p. 166, 2014. D. A. Pinotsis, Neural Field Coding of Short Term ...performance of children learning to count in a SPA model; proposed a new SPA model of cognitive load using the N-back task; developed a new model of the

Artificial intelligence. Application of the Statistical Neural Networks computer program in nuclear medicine

International Nuclear Information System (INIS)

Stefaniak, B.; Cholewinski, W.; Tarkowska, A.

2005-01-01

Artificial Neural Networks (ANN) may be a tool alternative and complementary to typical statistical analysis. However, in spite of many computer application of various ANN algorithms ready for use, artificial intelligence is relatively rarely applied to data processing. In this paper practical aspects of scientific application of ANN in medicine using the Statistical Neural Networks Computer program, were presented. Several steps of data analysis with the above ANN software package were discussed shortly, from material selection and its dividing into groups to the types of obtained results. The typical problems connected with assessing scintigrams by ANN were also described. (author)

Artificial intelligence in pharmaceutical product formulation: neural computing

Directory of Open Access Journals (Sweden)

Svetlana Ibrić

2009-10-01

Full Text Available The properties of a formulation are determined not only by the ratios in which the ingredients are combined but also by the processing conditions. Although the relationships between the ingredient levels, processing conditions, and product performance may be known anecdotally, they can rarely be quantified. In the past, formulators tended to use statistical techniques to model their formulations, relying on response surfaces to provide a mechanism for optimazation. However, the optimization by such a method can be misleading, especially if the formulation is complex. More recently, advances in mathematics and computer science have led to the development of alternative modeling and data mining techniques which work with a wider range of data sources: neural networks (an attempt to mimic the processing of the human brain; genetic algorithms (an attempt to mimic the evolutionary process by which biological systems self-organize and adapt, and fuzzy logic (an attempt to mimic the ability of the human brain to draw conclusions and generate responses based on incomplete or imprecise information. In this review the current technology will be examined, as well as its application in pharmaceutical formulation and processing. The challenges, benefits and future possibilities of neural computing will be discussed.

New Computer Simulations of Macular Neural Functioning

Science.gov (United States)

Ross, Muriel D.; Doshay, D.; Linton, S.; Parnas, B.; Montgomery, K.; Chimento, T.

1994-01-01

We use high performance graphics workstations and supercomputers to study the functional significance of the three-dimensional (3-D) organization of gravity sensors. These sensors have a prototypic architecture foreshadowing more complex systems. Scaled-down simulations run on a Silicon Graphics workstation and scaled-up, 3-D versions run on a Cray Y-MP supercomputer. A semi-automated method of reconstruction of neural tissue from serial sections studied in a transmission electron microscope has been developed to eliminate tedious conventional photography. The reconstructions use a mesh as a step in generating a neural surface for visualization. Two meshes are required to model calyx surfaces. The meshes are connected and the resulting prisms represent the cytoplasm and the bounding membranes. A finite volume analysis method is employed to simulate voltage changes along the calyx in response to synapse activation on the calyx or on calyceal processes. The finite volume method insures that charge is conserved at the calyx-process junction. These and other models indicate that efferent processes act as voltage followers, and that the morphology of some afferent processes affects their functioning. In a final application, morphological information is symbolically represented in three dimensions in a computer. The possible functioning of the connectivities is tested using mathematical interpretations of physiological parameters taken from the literature. Symbolic, 3-D simulations are in progress to probe the functional significance of the connectivities. This research is expected to advance computer-based studies of macular functioning and of synaptic plasticity.

COMPUTING

CERN Multimedia

M. Kasemann P. McBride Edited by M-C. Sawley with contributions from: P. Kreuzer D. Bonacorsi S. Belforte F. Wuerthwein L. Bauerdick K. Lassila-Perini M-C. Sawley

Introduction More than seventy CMS collaborators attended the Computing and Offline Workshop in San Diego, California, April 20-24th to discuss the state of readiness of software and computing for collisions. Focus and priority were given to preparations for data taking and providing room for ample dialog between groups involved in Commissioning, Data Operations, Analysis and MC Production. Throughout the workshop, aspects of software, operating procedures and issues addressing all parts of the computing model were discussed. Plans for the CMS participation in STEP’09, the combined scale testing for all four experiments due in June 2009, were refined. The article in CMS Times by Frank Wuerthwein gave a good recap of the highly collaborative atmosphere of the workshop. Many thanks to UCSD and to the organizers for taking care of this workshop, which resulted in a long list of action items and was definitely a success. A considerable amount of effort and care is invested in the estimate of the comput...

Computer simulation system of neural PID control on nuclear reactor

International Nuclear Information System (INIS)

Chen Yuzhong; Yang Kaijun; Shen Yongping

2001-01-01

Neural network proportional integral differential (PID) controller on nuclear reactor is designed, and the control process is simulated by computer. The simulation result show that neutral network PID controller can automatically adjust its parameter to ideal state, and good control result can be gotten in reactor control process

Neural and Computational Mechanisms of Action Processing: Interaction between Visual and Motor Representations.

Science.gov (United States)

Giese, Martin A; Rizzolatti, Giacomo

2015-10-07

Action recognition has received enormous interest in the field of neuroscience over the last two decades. In spite of this interest, the knowledge in terms of fundamental neural mechanisms that provide constraints for underlying computations remains rather limited. This fact stands in contrast with a wide variety of speculative theories about how action recognition might work. This review focuses on new fundamental electrophysiological results in monkeys, which provide constraints for the detailed underlying computations. In addition, we review models for action recognition and processing that have concrete mathematical implementations, as opposed to conceptual models. We think that only such implemented models can be meaningfully linked quantitatively to physiological data and have a potential to narrow down the many possible computational explanations for action recognition. In addition, only concrete implementations allow judging whether postulated computational concepts have a feasible implementation in terms of realistic neural circuits. Copyright © 2015 Elsevier Inc. All rights reserved.

Low-cost autonomous perceptron neural network inspired by quantum computation

Science.gov (United States)

Zidan, Mohammed; Abdel-Aty, Abdel-Haleem; El-Sadek, Alaa; Zanaty, E. A.; Abdel-Aty, Mahmoud

2017-11-01

Achieving low cost learning with reliable accuracy is one of the important goals to achieve intelligent machines to save time, energy and perform learning process over limited computational resources machines. In this paper, we propose an efficient algorithm for a perceptron neural network inspired by quantum computing composite from a single neuron to classify inspirable linear applications after a single training iteration O(1). The algorithm is applied over a real world data set and the results are outer performs the other state-of-the art algorithms.

A Case Study on Neural Inspired Dynamic Memory Management Strategies for High Performance Computing.

Energy Technology Data Exchange (ETDEWEB)

Vineyard, Craig Michael [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Verzi, Stephen Joseph [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

2017-09-01

As high performance computing architectures pursue more computational power there is a need for increased memory capacity and bandwidth as well. A multi-level memory (MLM) architecture addresses this need by combining multiple memory types with different characteristics as varying levels of the same architecture. How to efficiently utilize this memory infrastructure is an unknown challenge, and in this research we sought to investigate whether neural inspired approaches can meaningfully help with memory management. In particular we explored neurogenesis inspired re- source allocation, and were able to show a neural inspired mixed controller policy can beneficially impact how MLM architectures utilize memory.

COMPUTING

CERN Multimedia

M. Kasemann

Introduction More than seventy CMS collaborators attended the Computing and Offline Workshop in San Diego, California, April 20-24th to discuss the state of readiness of software and computing for collisions. Focus and priority were given to preparations for data taking and providing room for ample dialog between groups involved in Commissioning, Data Operations, Analysis and MC Production. Throughout the workshop, aspects of software, operating procedures and issues addressing all parts of the computing model were discussed. Plans for the CMS participation in STEP’09, the combined scale testing for all four experiments due in June 2009, were refined. The article in CMS Times by Frank Wuerthwein gave a good recap of the highly collaborative atmosphere of the workshop. Many thanks to UCSD and to the organizers for taking care of this workshop, which resulted in a long list of action items and was definitely a success. A considerable amount of effort and care is invested in the estimate of the co...

A state space approach for piecewise-linear recurrent neural networks for identifying computational dynamics from neural measurements.

Directory of Open Access Journals (Sweden)

Daniel Durstewitz

2017-06-01

Full Text Available The computational and cognitive properties of neural systems are often thought to be implemented in terms of their (stochastic network dynamics. Hence, recovering the system dynamics from experimentally observed neuronal time series, like multiple single-unit recordings or neuroimaging data, is an important step toward understanding its computations. Ideally, one would not only seek a (lower-dimensional state space representation of the dynamics, but would wish to have access to its statistical properties and their generative equations for in-depth analysis. Recurrent neural networks (RNNs are a computationally powerful and dynamically universal formal framework which has been extensively studied from both the computational and the dynamical systems perspective. Here we develop a semi-analytical maximum-likelihood estimation scheme for piecewise-linear RNNs (PLRNNs within the statistical framework of state space models, which accounts for noise in both the underlying latent dynamics and the observation process. The Expectation-Maximization algorithm is used to infer the latent state distribution, through a global Laplace approximation, and the PLRNN parameters iteratively. After validating the procedure on toy examples, and using inference through particle filters for comparison, the approach is applied to multiple single-unit recordings from the rodent anterior cingulate cortex (ACC obtained during performance of a classical working memory task, delayed alternation. Models estimated from kernel-smoothed spike time data were able to capture the essential computational dynamics underlying task performance, including stimulus-selective delay activity. The estimated models were rarely multi-stable, however, but rather were tuned to exhibit slow dynamics in the vicinity of a bifurcation point. In summary, the present work advances a semi-analytical (thus reasonably fast maximum-likelihood estimation framework for PLRNNs that may enable to recover

Memristor-Based Analog Computation and Neural Network Classification with a Dot Product Engine.

Science.gov (United States)

Hu, Miao; Graves, Catherine E; Li, Can; Li, Yunning; Ge, Ning; Montgomery, Eric; Davila, Noraica; Jiang, Hao; Williams, R Stanley; Yang, J Joshua; Xia, Qiangfei; Strachan, John Paul

2018-03-01

Using memristor crossbar arrays to accelerate computations is a promising approach to efficiently implement algorithms in deep neural networks. Early demonstrations, however, are limited to simulations or small-scale problems primarily due to materials and device challenges that limit the size of the memristor crossbar arrays that can be reliably programmed to stable and analog values, which is the focus of the current work. High-precision analog tuning and control of memristor cells across a 128 × 64 array is demonstrated, and the resulting vector matrix multiplication (VMM) computing precision is evaluated. Single-layer neural network inference is performed in these arrays, and the performance compared to a digital approach is assessed. Memristor computing system used here reaches a VMM accuracy equivalent of 6 bits, and an 89.9% recognition accuracy is achieved for the 10k MNIST handwritten digit test set. Forecasts show that with integrated (on chip) and scaled memristors, a computational efficiency greater than 100 trillion operations per second per Watt is possible. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Morphological neural networks

Energy Technology Data Exchange (ETDEWEB)

Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)

1996-12-31

The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.

Neural networks

International Nuclear Information System (INIS)

Denby, Bruce; Lindsey, Clark; Lyons, Louis

1992-01-01

The 1980s saw a tremendous renewal of interest in 'neural' information processing systems, or 'artificial neural networks', among computer scientists and computational biologists studying cognition. Since then, the growth of interest in neural networks in high energy physics, fueled by the need for new information processing technologies for the next generation of high energy proton colliders, can only be described as explosive

Fuzzy logic, neural networks, and soft computing

Science.gov (United States)

Zadeh, Lofti A.

1994-01-01

The past few years have witnessed a rapid growth of interest in a cluster of modes of modeling and computation which may be described collectively as soft computing. The distinguishing characteristic of soft computing is that its primary aims are to achieve tractability, robustness, low cost, and high MIQ (machine intelligence quotient) through an exploitation of the tolerance for imprecision and uncertainty. Thus, in soft computing what is usually sought is an approximate solution to a precisely formulated problem or, more typically, an approximate solution to an imprecisely formulated problem. A simple case in point is the problem of parking a car. Generally, humans can park a car rather easily because the final position of the car is not specified exactly. If it were specified to within, say, a few millimeters and a fraction of a degree, it would take hours or days of maneuvering and precise measurements of distance and angular position to solve the problem. What this simple example points to is the fact that, in general, high precision carries a high cost. The challenge, then, is to exploit the tolerance for imprecision by devising methods of computation which lead to an acceptable solution at low cost. By its nature, soft computing is much closer to human reasoning than the traditional modes of computation. At this juncture, the major components of soft computing are fuzzy logic (FL), neural network theory (NN), and probabilistic reasoning techniques (PR), including genetic algorithms, chaos theory, and part of learning theory. Increasingly, these techniques are used in combination to achieve significant improvement in performance and adaptability. Among the important application areas for soft computing are control systems, expert systems, data compression techniques, image processing, and decision support systems. It may be argued that it is soft computing, rather than the traditional hard computing, that should be viewed as the foundation for artificial

A modular architecture for transparent computation in recurrent neural networks.

Science.gov (United States)

Carmantini, Giovanni S; Beim Graben, Peter; Desroches, Mathieu; Rodrigues, Serafim

2017-01-01

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments. Copyright © 2016 Elsevier Ltd. All rights reserved.

Predictive Behavior of a Computational Foot/Ankle Model through Artificial Neural Networks.

Science.gov (United States)

Chande, Ruchi D; Hargraves, Rosalyn Hobson; Ortiz-Robinson, Norma; Wayne, Jennifer S

2017-01-01

Computational models are useful tools to study the biomechanics of human joints. Their predictive performance is heavily dependent on bony anatomy and soft tissue properties. Imaging data provides anatomical requirements while approximate tissue properties are implemented from literature data, when available. We sought to improve the predictive capability of a computational foot/ankle model by optimizing its ligament stiffness inputs using feedforward and radial basis function neural networks. While the former demonstrated better performance than the latter per mean square error, both networks provided reasonable stiffness predictions for implementation into the computational model.

Parietal neural prosthetic control of a computer cursor in a graphical-user-interface task

Science.gov (United States)

Revechkis, Boris; Aflalo, Tyson NS; Kellis, Spencer; Pouratian, Nader; Andersen, Richard A.

2014-12-01

Objective. To date, the majority of Brain-Machine Interfaces have been used to perform simple tasks with sequences of individual targets in otherwise blank environments. In this study we developed a more practical and clinically relevant task that approximated modern computers and graphical user interfaces (GUIs). This task could be problematic given the known sensitivity of areas typically used for BMIs to visual stimuli, eye movements, decision-making, and attentional control. Consequently, we sought to assess the effect of a complex, GUI-like task on the quality of neural decoding. Approach. A male rhesus macaque monkey was implanted with two 96-channel electrode arrays in area 5d of the superior parietal lobule. The animal was trained to perform a GUI-like ‘Face in a Crowd’ task on a computer screen that required selecting one cued, icon-like, face image from a group of alternatives (the ‘Crowd’) using a neurally controlled cursor. We assessed whether the crowd affected decodes of intended cursor movements by comparing it to a ‘Crowd Off’ condition in which only the matching target appeared without alternatives. We also examined if training a neural decoder with the Crowd On rather than Off had any effect on subsequent decode quality. Main results. Despite the additional demands of working with the Crowd On, the animal was able to robustly perform the task under Brain Control. The presence of the crowd did not itself affect decode quality. Training the decoder with the Crowd On relative to Off had no negative influence on subsequent decoding performance. Additionally, the subject was able to gaze around freely without influencing cursor position. Significance. Our results demonstrate that area 5d recordings can be used for decoding in a complex, GUI-like task with free gaze. Thus, this area is a promising source of signals for neural prosthetics that utilize computing devices with GUI interfaces, e.g. personal computers, mobile devices, and tablet

Parietal neural prosthetic control of a computer cursor in a graphical-user-interface task.

Science.gov (United States)

Revechkis, Boris; Aflalo, Tyson N S; Kellis, Spencer; Pouratian, Nader; Andersen, Richard A

2014-12-01

To date, the majority of Brain-Machine Interfaces have been used to perform simple tasks with sequences of individual targets in otherwise blank environments. In this study we developed a more practical and clinically relevant task that approximated modern computers and graphical user interfaces (GUIs). This task could be problematic given the known sensitivity of areas typically used for BMIs to visual stimuli, eye movements, decision-making, and attentional control. Consequently, we sought to assess the effect of a complex, GUI-like task on the quality of neural decoding. A male rhesus macaque monkey was implanted with two 96-channel electrode arrays in area 5d of the superior parietal lobule. The animal was trained to perform a GUI-like 'Face in a Crowd' task on a computer screen that required selecting one cued, icon-like, face image from a group of alternatives (the 'Crowd') using a neurally controlled cursor. We assessed whether the crowd affected decodes of intended cursor movements by comparing it to a 'Crowd Off' condition in which only the matching target appeared without alternatives. We also examined if training a neural decoder with the Crowd On rather than Off had any effect on subsequent decode quality. Despite the additional demands of working with the Crowd On, the animal was able to robustly perform the task under Brain Control. The presence of the crowd did not itself affect decode quality. Training the decoder with the Crowd On relative to Off had no negative influence on subsequent decoding performance. Additionally, the subject was able to gaze around freely without influencing cursor position. Our results demonstrate that area 5d recordings can be used for decoding in a complex, GUI-like task with free gaze. Thus, this area is a promising source of signals for neural prosthetics that utilize computing devices with GUI interfaces, e.g. personal computers, mobile devices, and tablet computers.

Neural dynamics as sampling: a model for stochastic computation in recurrent networks of spiking neurons.

Science.gov (United States)

Buesing, Lars; Bill, Johannes; Nessler, Bernhard; Maass, Wolfgang

2011-11-01

The organization of computations in networks of spiking neurons in the brain is still largely unknown, in particular in view of the inherently stochastic features of their firing activity and the experimentally observed trial-to-trial variability of neural systems in the brain. In principle there exists a powerful computational framework for stochastic computations, probabilistic inference by sampling, which can explain a large number of macroscopic experimental data in neuroscience and cognitive science. But it has turned out to be surprisingly difficult to create a link between these abstract models for stochastic computations and more detailed models of the dynamics of networks of spiking neurons. Here we create such a link and show that under some conditions the stochastic firing activity of networks of spiking neurons can be interpreted as probabilistic inference via Markov chain Monte Carlo (MCMC) sampling. Since common methods for MCMC sampling in distributed systems, such as Gibbs sampling, are inconsistent with the dynamics of spiking neurons, we introduce a different approach based on non-reversible Markov chains that is able to reflect inherent temporal processes of spiking neuronal activity through a suitable choice of random variables. We propose a neural network model and show by a rigorous theoretical analysis that its neural activity implements MCMC sampling of a given distribution, both for the case of discrete and continuous time. This provides a step towards closing the gap between abstract functional models of cortical computation and more detailed models of networks of spiking neurons.

Fast computation with spikes in a recurrent neural network

International Nuclear Information System (INIS)

Jin, Dezhe Z.; Seung, H. Sebastian

2002-01-01

Neural networks with recurrent connections are sometimes regarded as too slow at computation to serve as models of the brain. Here we analytically study a counterexample, a network consisting of N integrate-and-fire neurons with self excitation, all-to-all inhibition, instantaneous synaptic coupling, and constant external driving inputs. When the inhibition and/or excitation are large enough, the network performs a winner-take-all computation for all possible external inputs and initial states of the network. The computation is done very quickly: As soon as the winner spikes once, the computation is completed since no other neurons will spike. For some initial states, the winner is the first neuron to spike, and the computation is done at the first spike of the network. In general, there are M potential winners, corresponding to the top M external inputs. When the external inputs are close in magnitude, M tends to be larger. If M>1, the selection of the actual winner is strongly influenced by the initial states. If a special relation between the excitation and inhibition is satisfied, the network always selects the neuron with the maximum external input as the winner

Predictive Behavior of a Computational Foot/Ankle Model through Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Ruchi D. Chande

2017-01-01

Full Text Available Computational models are useful tools to study the biomechanics of human joints. Their predictive performance is heavily dependent on bony anatomy and soft tissue properties. Imaging data provides anatomical requirements while approximate tissue properties are implemented from literature data, when available. We sought to improve the predictive capability of a computational foot/ankle model by optimizing its ligament stiffness inputs using feedforward and radial basis function neural networks. While the former demonstrated better performance than the latter per mean square error, both networks provided reasonable stiffness predictions for implementation into the computational model.

Programmable neural processing on a smartdust for brain-computer interfaces.

Science.gov (United States)

Yuwen Sun; Shimeng Huang; Oresko, Joseph J; Cheng, Allen C

2010-10-01

Brain-computer interfaces (BCIs) offer tremendous promise for improving the quality of life for disabled individuals. BCIs use spike sorting to identify the source of each neural firing. To date, spike sorting has been performed by either using off-chip analysis, which requires a wired connection penetrating the skull to a bulky external power/processing unit, or via custom application-specific integrated circuits that lack the programmability to perform different algorithms and upgrades. In this research, we propose and test the feasibility of performing on-chip, real-time spike sorting on a programmable smartdust, including feature extraction, classification, compression, and wireless transmission. A detailed power/performance tradeoff analysis using DVFS is presented. Our experimental results show that the execution time and power density meet the requirements to perform real-time spike sorting and wireless transmission on a single neural channel.

Neural Computation Scheme of Compound Control: Tacit Learning for Bipedal Locomotion

Science.gov (United States)

Shimoda, Shingo; Kimura, Hidenori

The growing need for controlling complex behaviors of versatile robots working in unpredictable environment has revealed the fundamental limitation of model-based control strategy that requires precise models of robots and environments before their operations. This difficulty is fundamental and has the same root with the well-known frame problem in artificial intelligence. It has been a central long standing issue in advanced robotics, as well as machine intelligence, to find a prospective clue to attack this fundamental difficulty. The general consensus shared by many leading researchers in the related field is that the body plays an important role in acquiring intelligence that can conquer unknowns. In particular, purposeful behaviors emerge during body-environment interactions with the help of an appropriately organized neural computational scheme that can exploit what the environment can afford. Along this line, we propose a new scheme of neural computation based on compound control which represents a typical feature of biological controls. This scheme is based on classical neuron models with local rules that can create macroscopic purposeful behaviors. This scheme is applied to a bipedal robot and generates the rhythm of walking without any model of robot dynamics and environments.

Linking Inflammation, Cardiorespiratory Variability, and Neural Control in Acute Inflammation via Computational Modeling.

Science.gov (United States)

Dick, Thomas E; Molkov, Yaroslav I; Nieman, Gary; Hsieh, Yee-Hsee; Jacono, Frank J; Doyle, John; Scheff, Jeremy D; Calvano, Steve E; Androulakis, Ioannis P; An, Gary; Vodovotz, Yoram

2012-01-01

Acute inflammation leads to organ failure by engaging catastrophic feedback loops in which stressed tissue evokes an inflammatory response and, in turn, inflammation damages tissue. Manifestations of this maladaptive inflammatory response include cardio-respiratory dysfunction that may be reflected in reduced heart rate and ventilatory pattern variabilities. We have developed signal-processing algorithms that quantify non-linear deterministic characteristics of variability in biologic signals. Now, coalescing under the aegis of the NIH Computational Biology Program and the Society for Complexity in Acute Illness, two research teams performed iterative experiments and computational modeling on inflammation and cardio-pulmonary dysfunction in sepsis as well as on neural control of respiration and ventilatory pattern variability. These teams, with additional collaborators, have recently formed a multi-institutional, interdisciplinary consortium, whose goal is to delineate the fundamental interrelationship between the inflammatory response and physiologic variability. Multi-scale mathematical modeling and complementary physiological experiments will provide insight into autonomic neural mechanisms that may modulate the inflammatory response to sepsis and simultaneously reduce heart rate and ventilatory pattern variabilities associated with sepsis. This approach integrates computational models of neural control of breathing and cardio-respiratory coupling with models that combine inflammation, cardiovascular function, and heart rate variability. The resulting integrated model will provide mechanistic explanations for the phenomena of respiratory sinus-arrhythmia and cardio-ventilatory coupling observed under normal conditions, and the loss of these properties during sepsis. This approach holds the potential of modeling cross-scale physiological interactions to improve both basic knowledge and clinical management of acute inflammatory diseases such as sepsis and trauma.

Computer simulations of neural mechanisms explaining upper and lower limb excitatory neural coupling

Directory of Open Access Journals (Sweden)

Ferris Daniel P

2010-12-01

Full Text Available Abstract Background When humans perform rhythmic upper and lower limb locomotor-like movements, there is an excitatory effect of upper limb exertion on lower limb muscle recruitment. To investigate potential neural mechanisms for this behavioral observation, we developed computer simulations modeling interlimb neural pathways among central pattern generators. We hypothesized that enhancement of muscle recruitment from interlimb spinal mechanisms was not sufficient to explain muscle enhancement levels observed in experimental data. Methods We used Matsuoka oscillators for the central pattern generators (CPG and determined parameters that enhanced amplitudes of rhythmic steady state bursts. Potential mechanisms for output enhancement were excitatory and inhibitory sensory feedback gains, excitatory and inhibitory interlimb coupling gains, and coupling geometry. We first simulated the simplest case, a single CPG, and then expanded the model to have two CPGs and lastly four CPGs. In the two and four CPG models, the lower limb CPGs did not receive supraspinal input such that the only mechanisms available for enhancing output were interlimb coupling gains and sensory feedback gains. Results In a two-CPG model with inhibitory sensory feedback gains, only excitatory gains of ipsilateral flexor-extensor/extensor-flexor coupling produced reciprocal upper-lower limb bursts and enhanced output up to 26%. In a two-CPG model with excitatory sensory feedback gains, excitatory gains of contralateral flexor-flexor/extensor-extensor coupling produced reciprocal upper-lower limb bursts and enhanced output up to 100%. However, within a given excitatory sensory feedback gain, enhancement due to excitatory interlimb gains could only reach levels up to 20%. Interconnecting four CPGs to have ipsilateral flexor-extensor/extensor-flexor coupling, contralateral flexor-flexor/extensor-extensor coupling, and bilateral flexor-extensor/extensor-flexor coupling could enhance

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

Science.gov (United States)

Takiyama, Ken

2017-12-01

How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.

Topology and computational performance of attractor neural networks

International Nuclear Information System (INIS)

McGraw, Patrick N.; Menzinger, Michael

2003-01-01

To explore the relation between network structure and function, we studied the computational performance of Hopfield-type attractor neural nets with regular lattice, random, small-world, and scale-free topologies. The random configuration is the most efficient for storage and retrieval of patterns by the network as a whole. However, in the scale-free case retrieval errors are not distributed uniformly among the nodes. The portion of a pattern encoded by the subset of highly connected nodes is more robust and efficiently recognized than the rest of the pattern. The scale-free network thus achieves a very strong partial recognition. The implications of these findings for brain function and social dynamics are suggestive

Population coding and decoding in a neural field: a computational study.

Science.gov (United States)

Wu, Si; Amari, Shun-Ichi; Nakahara, Hiroyuki

2002-05-01

This study uses a neural field model to investigate computational aspects of population coding and decoding when the stimulus is a single variable. A general prototype model for the encoding process is proposed, in which neural responses are correlated, with strength specified by a gaussian function of their difference in preferred stimuli. Based on the model, we study the effect of correlation on the Fisher information, compare the performances of three decoding methods that differ in the amount of encoding information being used, and investigate the implementation of the three methods by using a recurrent network. This study not only rediscovers main results in existing literatures in a unified way, but also reveals important new features, especially when the neural correlation is strong. As the neural correlation of firing becomes larger, the Fisher information decreases drastically. We confirm that as the width of correlation increases, the Fisher information saturates and no longer increases in proportion to the number of neurons. However, we prove that as the width increases further--wider than (sqrt)2 times the effective width of the turning function--the Fisher information increases again, and it increases without limit in proportion to the number of neurons. Furthermore, we clarify the asymptotic efficiency of the maximum likelihood inference (MLI) type of decoding methods for correlated neural signals. It shows that when the correlation covers a nonlocal range of population (excepting the uniform correlation and when the noise is extremely small), the MLI type of method, whose decoding error satisfies the Cauchy-type distribution, is not asymptotically efficient. This implies that the variance is no longer adequate to measure decoding accuracy.

Neural and computational processes underlying dynamic changes in self-esteem

Science.gov (United States)

Rutledge, Robb B; Moutoussis, Michael; Dolan, Raymond J

2017-01-01

Self-esteem is shaped by the appraisals we receive from others. Here, we characterize neural and computational mechanisms underlying this form of social influence. We introduce a computational model that captures fluctuations in self-esteem engendered by prediction errors that quantify the difference between expected and received social feedback. Using functional MRI, we show these social prediction errors correlate with activity in ventral striatum/subgenual anterior cingulate cortex, while updates in self-esteem resulting from these errors co-varied with activity in ventromedial prefrontal cortex (vmPFC). We linked computational parameters to psychiatric symptoms using canonical correlation analysis to identify an ‘interpersonal vulnerability’ dimension. Vulnerability modulated the expression of prediction error responses in anterior insula and insula-vmPFC connectivity during self-esteem updates. Our findings indicate that updating of self-evaluative beliefs relies on learning mechanisms akin to those used in learning about others. Enhanced insula-vmPFC connectivity during updating of those beliefs may represent a marker for psychiatric vulnerability. PMID:29061228

Neural and computational processes underlying dynamic changes in self-esteem.

Science.gov (United States)

Will, Geert-Jan; Rutledge, Robb B; Moutoussis, Michael; Dolan, Raymond J

2017-10-24

Self-esteem is shaped by the appraisals we receive from others. Here, we characterize neural and computational mechanisms underlying this form of social influence. We introduce a computational model that captures fluctuations in self-esteem engendered by prediction errors that quantify the difference between expected and received social feedback. Using functional MRI, we show these social prediction errors correlate with activity in ventral striatum/subgenual anterior cingulate cortex, while updates in self-esteem resulting from these errors co-varied with activity in ventromedial prefrontal cortex (vmPFC). We linked computational parameters to psychiatric symptoms using canonical correlation analysis to identify an 'interpersonal vulnerability' dimension. Vulnerability modulated the expression of prediction error responses in anterior insula and insula-vmPFC connectivity during self-esteem updates. Our findings indicate that updating of self-evaluative beliefs relies on learning mechanisms akin to those used in learning about others. Enhanced insula-vmPFC connectivity during updating of those beliefs may represent a marker for psychiatric vulnerability.

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network.

Science.gov (United States)

Falat, Lukas; Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

Unification of behavioural, computational and neural accounts of word production errors in post-stroke aphasia

Directory of Open Access Journals (Sweden)

Marija Tochadse

Full Text Available Neuropsychological assessment, brain imaging and computational modelling have augmented our understanding of the multifaceted functional deficits in people with language disorders after stroke. Despite the volume of research using each technique, no studies have attempted to assimilate all three approaches in order to generate a unified behavioural-computational-neural model of post-stroke aphasia.The present study included data from 53 participants with chronic post-stroke aphasia and merged: aphasiological profiles based on a detailed neuropsychological assessment battery which was analysed with principal component and correlational analyses; measures of the impairment taken from Dell's computational model of word production; and the neural correlates of both behavioural and computational accounts analysed by voxel-based correlational methodology.As a result, all three strands coincide with the separation of semantic and phonological stages of aphasic naming, revealing the prominence of these dimensions for the explanation of aphasic performance. Over and above three previously described principal components (phonological ability, semantic ability, executive-demand, we observed auditory working memory as a novel factor. While the phonological Dell parameter was uniquely related to phonological errors/factor, the semantic parameter was less clear-cut, being related to both semantic errors and omissions, and loading heavily with semantic ability and auditory working memory factors. The close relationship between the semantic Dell parameter and omission errors recurred in their high lesion-correlate overlap in the anterior middle temporal gyrus. In addition, the simultaneous overlap of the lesion correlate of omission errors with more dorsal temporal regions, associated with the phonological parameter, highlights the multiple drivers that underpin this error type. The novel auditory working memory factor was located along left superior

Neural fields theory and applications

CERN Document Server

Graben, Peter; Potthast, Roland; Wright, James

2014-01-01

With this book, the editors present the first comprehensive collection in neural field studies, authored by leading scientists in the field - among them are two of the founding-fathers of neural field theory. Up to now, research results in the field have been disseminated across a number of distinct journals from mathematics, computational neuroscience, biophysics, cognitive science and others. Starting with a tutorial for novices in neural field studies, the book comprises chapters on emergent patterns, their phase transitions and evolution, on stochastic approaches, cortical development, cognition, robotics and computation, large-scale numerical simulations, the coupling of neural fields to the electroencephalogram and phase transitions in anesthesia. The intended readership are students and scientists in applied mathematics, theoretical physics, theoretical biology, and computational neuroscience. Neural field theory and its applications have a long-standing tradition in the mathematical and computational ...

Quantum neural network-based EEG filtering for a brain-computer interface.

Science.gov (United States)

Gandhi, Vaibhav; Prasad, Girijesh; Coyle, Damien; Behera, Laxmidhar; McGinnity, Thomas Martin

2014-02-01

A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The proposed architecture referred to as recurrent quantum neural network (RQNN) can characterize a nonstationary stochastic signal as time-varying wave packets. A robust unsupervised learning algorithm enables the RQNN to effectively capture the statistical behavior of the input signal and facilitates the estimation of signal embedded in noise with unknown characteristics. The results from a number of benchmark tests show that simple signals such as dc, staircase dc, and sinusoidal signals embedded within high noise can be accurately filtered and particle swarm optimization can be employed to select model parameters. The RQNN filtering procedure is applied in a two-class motor imagery-based brain-computer interface where the objective was to filter electroencephalogram (EEG) signals before feature extraction and classification to increase signal separability. A two-step inner-outer fivefold cross-validation approach is utilized to select the algorithm parameters subject-specifically for nine subjects. It is shown that the subject-specific RQNN EEG filtering significantly improves brain-computer interface performance compared to using only the raw EEG or Savitzky-Golay filtered EEG across multiple sessions.

A Dynamic Connectome Supports the Emergence of Stable Computational Function of Neural Circuits through Reward-Based Learning.

Science.gov (United States)

Kappel, David; Legenstein, Robert; Habenschuss, Stefan; Hsieh, Michael; Maass, Wolfgang

2018-01-01

Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown that the spontaneous synapse-autonomous component of spine dynamics is at least as large as the component that depends on the history of pre- and postsynaptic neural activity. These data are inconsistent with common models for network plasticity and raise the following questions: how can neural circuits maintain a stable computational function in spite of these continuously ongoing processes, and what could be functional uses of these ongoing processes? Here, we present a rigorous theoretical framework for these seemingly stochastic spine dynamics and rewiring processes in the context of reward-based learning tasks. We show that spontaneous synapse-autonomous processes, in combination with reward signals such as dopamine, can explain the capability of networks of neurons in the brain to configure themselves for specific computational tasks, and to compensate automatically for later changes in the network or task. Furthermore, we show theoretically and through computer simulations that stable computational performance is compatible with continuously ongoing synapse-autonomous changes. After reaching good computational performance it causes primarily a slow drift of network architecture and dynamics in task-irrelevant dimensions, as observed for neural activity in motor cortex and other areas. On the more abstract level of reinforcement learning the resulting model gives rise to an understanding of reward-driven network plasticity as continuous sampling of network configurations.

Computed tomography of x-ray images using neural networks

Science.gov (United States)

Allred, Lloyd G.; Jones, Martin H.; Sheats, Matthew J.; Davis, Anthony W.

2000-03-01

Traditional CT reconstruction is done using the technique of Filtered Backprojection. While this technique is widely employed in industrial and medical applications, it is not generally understood that FB has a fundamental flaw. Gibbs phenomena states any Fourier reconstruction will produce errors in the vicinity of all discontinuities, and that the error will equal 28 percent of the discontinuity. A number of years back, one of the authors proposed a biological perception model whereby biological neural networks perceive 3D images from stereo vision. The perception model proports an internal hard-wired neural network which emulates the external physical process. A process is repeated whereby erroneous unknown internal values are used to generate an emulated signal with is compared to external sensed data, generating an error signal. Feedback from the error signal is then sued to update the erroneous internal values. The process is repeated until the error signal no longer decrease. It was soon realized that the same method could be used to obtain CT from x-rays without having to do Fourier transforms. Neural networks have the additional potential for handling non-linearities and missing data. The technique has been applied to some coral images, collected at the Los Alamos high-energy x-ray facility. The initial images show considerable promise, in some instances showing more detail than the FB images obtained from the same data. Although routine production using this new method would require a massively parallel computer, the method shows promise, especially where refined detail is required.

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

Science.gov (United States)

Lin, Tsung-Yu; RoyChowdhury, Aruni; Maji, Subhransu

2017-07-04

We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.

Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

Science.gov (United States)

Dai, Yonghui; Han, Dongmei; Dai, Weihui

2014-01-01

The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market. PMID:24782659

Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

Directory of Open Access Journals (Sweden)

Yonghui Dai

2014-01-01

Full Text Available The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market.

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

Directory of Open Access Journals (Sweden)

Lukas Falat

2016-01-01

Full Text Available This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

Science.gov (United States)

Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process. PMID:26977450

The impact of natural aging on computational and neural indices of perceptual decision making: A review.

Science.gov (United States)

Dully, Jessica; McGovern, David P; O'Connell, Redmond G

2018-02-10

It is well established that natural aging negatively impacts on a wide variety of cognitive functions and research has sought to identify core neural mechanisms that may account for these disparate changes. A central feature of any cognitive task is the requirement to translate sensory information into an appropriate action - a process commonly known as perceptual decision making. While computational, psychophysical, and neurophysiological research has made substantial progress in establishing the key computations and neural mechanisms underpinning decision making, it is only relatively recently that this knowledge has begun to be applied to research on aging. The purpose of this review is to provide an overview of this work which is beginning to offer new insights into the core psychological processes that mediate age-related cognitive decline in adults aged 65 years and over. Mathematical modelling studies have consistently reported that older adults display longer non-decisional processing times and implement more conservative decision policies than their younger counterparts. However, there are limits on what we can learn from behavioural modeling alone and neurophysiological analyses can play an essential role in empirically validating model predictions and in pinpointing the precise neural mechanisms that are impacted by aging. Although few studies to date have explicitly examined correspondences between computational models and neural data with respect to cognitive aging, neurophysiological studies have already highlighted age-related changes at multiple levels of the sensorimotor hierarchy that are likely to be consequential for decision making behaviour. Here, we provide an overview of this literature and suggest some future directions for the field. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

Influence of extracellular oscillations on neural communication: a computational perspective

Directory of Open Access Journals (Sweden)

Zoran eTiganj

2014-02-01

Full Text Available Neural communication generates oscillations of electric potential in the extracellular medium. In feedback, these oscillations affect the electrochemical processes within the neurons, influencing the timing and the number of action potentials. It is unclear whether this influence should be considered only as noise or it has some functional role in neural communication. Through computer simulations we investigated the effect of various sinusoidal extracellular oscillations on the timing and number of action potentials. Each simulation is based on a multicompartment model of a single neuron, which is stimulated through spatially distributed synaptic activations. A thorough analysis is conducted on a large number of simulations with different models of CA3 and CA1 pyramidal neurons which are modeled using realistic morphologies and active ion conductances. We demonstrated that the influence of the weak extracellular oscillations, which are commonly present in the brain, is rather stochastic and modest. We found that the stronger fields, which are spontaneously present in the brain only in some particular cases (e.g. during seizures or that can be induced externally, could significantly modulate spike timings.

A GIS-based multi-criteria seismic vulnerability assessment using the integration of granular computing rule extraction and artificial neural networks

NARCIS (Netherlands)

Sheikhian, Hossein; Delavar, Mahmoud Reza; Stein, Alfred

2017-01-01

This study proposes multi‐criteria group decision‐making to address seismic physical vulnerability assessment. Granular computing rule extraction is combined with a feed forward artificial neural network to form a classifier capable of training a neural network on the basis of the rules provided by

Concepts and Relations in Neurally Inspired In Situ Concept-Based Computing.

Science.gov (United States)

van der Velde, Frank

2016-01-01

In situ concept-based computing is based on the notion that conceptual representations in the human brain are "in situ." In this way, they are grounded in perception and action. Examples are neuronal assemblies, whose connection structures develop over time and are distributed over different brain areas. In situ concepts representations cannot be copied or duplicated because that will disrupt their connection structure, and thus the meaning of these concepts. Higher-level cognitive processes, as found in language and reasoning, can be performed with in situ concepts by embedding them in specialized neurally inspired "blackboards." The interactions between the in situ concepts and the blackboards form the basis for in situ concept computing architectures. In these architectures, memory (concepts) and processing are interwoven, in contrast with the separation between memory and processing found in Von Neumann architectures. Because the further development of Von Neumann computing (more, faster, yet power limited) is questionable, in situ concept computing might be an alternative for concept-based computing. In situ concept computing will be illustrated with a recently developed BABI reasoning task. Neurorobotics can play an important role in the development of in situ concept computing because of the development of in situ concept representations derived in scenarios as needed for reasoning tasks. Neurorobotics would also benefit from power limited and in situ concept computing.

A computational relationship between thalamic sensory neural responses and contrast perception.

Science.gov (United States)

Jiang, Yaoguang; Purushothaman, Gopathy; Casagrande, Vivien A

2015-01-01

Uncovering the relationship between sensory neural responses and perceptual decisions remains a fundamental problem in neuroscience. Decades of experimental and modeling work in the sensory cortex have demonstrated that a perceptual decision pool is usually composed of tens to hundreds of neurons, the responses of which are significantly correlated not only with each other, but also with the behavioral choices of an animal. Few studies, however, have measured neural activity in the sensory thalamus of awake, behaving animals. Therefore, it remains unclear how many thalamic neurons are recruited and how the information from these neurons is pooled at subsequent cortical stages to form a perceptual decision. In a previous study we measured neural activity in the macaque lateral geniculate nucleus (LGN) during a two alternative forced choice (2AFC) contrast detection task, and found that single LGN neurons were significantly correlated with the monkeys' behavioral choices, despite their relatively poor contrast sensitivity and a lack of overall interneuronal correlations. We have now computationally tested a number of specific hypotheses relating these measured LGN neural responses to the contrast detection behavior of the animals. We modeled the perceptual decisions with different numbers of neurons and using a variety of pooling/readout strategies, and found that the most successful model consisted of about 50-200 LGN neurons, with individual neurons weighted differentially according to their signal-to-noise ratios (quantified as d-primes). These results supported the hypothesis that in contrast detection the perceptual decision pool consists of multiple thalamic neurons, and that the response fluctuations in these neurons can influence contrast perception, with the more sensitive thalamic neurons likely to exert a greater influence.

Cat Swarm Optimization Based Functional Link Artificial Neural Network Filter for Gaussian Noise Removal from Computed Tomography Images

Directory of Open Access Journals (Sweden)

M. Kumar

2016-01-01

Full Text Available Gaussian noise is one of the dominant noises, which degrades the quality of acquired Computed Tomography (CT image data. It creates difficulties in pathological identification or diagnosis of any disease. Gaussian noise elimination is desirable to improve the clarity of a CT image for clinical, diagnostic, and postprocessing applications. This paper proposes an evolutionary nonlinear adaptive filter approach, using Cat Swarm Functional Link Artificial Neural Network (CS-FLANN to remove the unwanted noise. The structure of the proposed filter is based on the Functional Link Artificial Neural Network (FLANN and the Cat Swarm Optimization (CSO is utilized for the selection of optimum weight of the neural network filter. The applied filter has been compared with the existing linear filters, like the mean filter and the adaptive Wiener filter. The performance indices, such as peak signal to noise ratio (PSNR, have been computed for the quantitative analysis of the proposed filter. The experimental evaluation established the superiority of the proposed filtering technique over existing methods.

Evidence for Neural Computations of Temporal Coherence in an Auditory Scene and Their Enhancement during Active Listening.

Science.gov (United States)

O'Sullivan, James A; Shamma, Shihab A; Lalor, Edmund C

2015-05-06

The human brain has evolved to operate effectively in highly complex acoustic environments, segregating multiple sound sources into perceptually distinct auditory objects. A recent theory seeks to explain this ability by arguing that stream segregation occurs primarily due to the temporal coherence of the neural populations that encode the various features of an individual acoustic source. This theory has received support from both psychoacoustic and functional magnetic resonance imaging (fMRI) studies that use stimuli which model complex acoustic environments. Termed stochastic figure-ground (SFG) stimuli, they are composed of a "figure" and background that overlap in spectrotemporal space, such that the only way to segregate the figure is by computing the coherence of its frequency components over time. Here, we extend these psychoacoustic and fMRI findings by using the greater temporal resolution of electroencephalography to investigate the neural computation of temporal coherence. We present subjects with modified SFG stimuli wherein the temporal coherence of the figure is modulated stochastically over time, which allows us to use linear regression methods to extract a signature of the neural processing of this temporal coherence. We do this under both active and passive listening conditions. Our findings show an early effect of coherence during passive listening, lasting from ∼115 to 185 ms post-stimulus. When subjects are actively listening to the stimuli, these responses are larger and last longer, up to ∼265 ms. These findings provide evidence for early and preattentive neural computations of temporal coherence that are enhanced by active analysis of an auditory scene. Copyright © 2015 the authors 0270-6474/15/357256-08$15.00/0.

Neural Cognition and Affective Computing on Cyber Language.

Science.gov (United States)

Huang, Shuang; Zhou, Xuan; Xue, Ke; Wan, Xiqiong; Yang, Zhenyi; Xu, Duo; Ivanović, Mirjana; Yu, Xueer

2015-01-01

Characterized by its customary symbol system and simple and vivid expression patterns, cyber language acts as not only a tool for convenient communication but also a carrier of abundant emotions and causes high attention in public opinion analysis, internet marketing, service feedback monitoring, and social emergency management. Based on our multidisciplinary research, this paper presents a classification of the emotional symbols in cyber language, analyzes the cognitive characteristics of different symbols, and puts forward a mechanism model to show the dominant neural activities in that process. Through the comparative study of Chinese, English, and Spanish, which are used by the largest population in the world, this paper discusses the expressive patterns of emotions in international cyber languages and proposes an intelligent method for affective computing on cyber language in a unified PAD (Pleasure-Arousal-Dominance) emotional space.

Neural Cognition and Affective Computing on Cyber Language

Directory of Open Access Journals (Sweden)

Shuang Huang

2015-01-01

Full Text Available Characterized by its customary symbol system and simple and vivid expression patterns, cyber language acts as not only a tool for convenient communication but also a carrier of abundant emotions and causes high attention in public opinion analysis, internet marketing, service feedback monitoring, and social emergency management. Based on our multidisciplinary research, this paper presents a classification of the emotional symbols in cyber language, analyzes the cognitive characteristics of different symbols, and puts forward a mechanism model to show the dominant neural activities in that process. Through the comparative study of Chinese, English, and Spanish, which are used by the largest population in the world, this paper discusses the expressive patterns of emotions in international cyber languages and proposes an intelligent method for affective computing on cyber language in a unified PAD (Pleasure-Arousal-Dominance emotional space.

Recurrent Neural Network for Computing Outer Inverse.

Science.gov (United States)

Živković, Ivan S; Stanimirović, Predrag S; Wei, Yimin

2016-05-01

Two linear recurrent neural networks for generating outer inverses with prescribed range and null space are defined. Each of the proposed recurrent neural networks is based on the matrix-valued differential equation, a generalization of dynamic equations proposed earlier for the nonsingular matrix inversion, the Moore-Penrose inversion, as well as the Drazin inversion, under the condition of zero initial state. The application of the first approach is conditioned by the properties of the spectrum of a certain matrix; the second approach eliminates this drawback, though at the cost of increasing the number of matrix operations. The cases corresponding to the most common generalized inverses are defined. The conditions that ensure stability of the proposed neural network are presented. Illustrative examples present the results of numerical simulations.

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

The quest for a Quantum Neural Network

OpenAIRE

Schuld, M.; Sinayskiy, I.; Petruccione, F.

2014-01-01

With the overwhelming success in the field of quantum information in the last decades, the "quest" for a Quantum Neural Network (QNN) model began in order to combine quantum computing with the striking properties of neural computing. This article presents a systematic approach to QNN research, which so far consists of a conglomeration of ideas and proposals. It outlines the challenge of combining the nonlinear, dissipative dynamics of neural computing and the linear, unitary dynamics of quant...

Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees

International Nuclear Information System (INIS)

Jerebko, Anna K.; Summers, Ronald M.; Malley, James D.; Franaszek, Marek; Johnson, C. Daniel

2003-01-01

Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study

Evaluating a grading change at UCSD school of medicine: pass/fail grading is associated with decreased performance on preclinical exams but unchanged performance on USMLE step 1 scores.

Science.gov (United States)

McDuff, Susan G R; McDuff, DeForest; Farace, Jennifer A; Kelly, Carolyn J; Savoia, Maria C; Mandel, Jess

2014-06-30

To assess the impact of a change in preclerkship grading system from Honors/Pass/Fail (H/P/F) to Pass/Fail (P/F) on University of California, San Diego (UCSD) medical students' academic performance. Academic performance of students in the classes of 2011 and 2012 (constant-grading classes) were collected and compared with performance of students in the class of 2013 (grading-change class) because the grading policy at UCSD SOM was changed for the class of 2013, from H/P/F during the first year (MS1) to P/F during the second year (MS2). For all students, data consisted of test scores from required preclinical courses from MS1 and MS2 years, and USMLE Step 1 scores. Linear regression analysis controlled for other factors that could be predictive of student performance (i.e., MCAT scores, undergraduate GPA, age, gender, etc.) in order to isolate the effect of the changed grading policy on academic performance. The change in grading policy in the MS2 year only, without any corresponding changes to the medical curriculum, presents a unique natural experiment with which to cleanly evaluate the effect of P/F grading on performance outcomes. After controlling for other factors, the grading policy change to P/F grading in the MS2 year had a negative impact on second-year grades relative to first-year grades (the constant-grading classes performed 1.65% points lower during their MS2 year compared to the MS1 year versus 3.25% points lower for the grading-change class, p < 0.0001), but had no observable impact on USMLE Step 1 scores. A change in grading from H/P/F grading to P/F grading was associated with decreased performance on preclinical examinations but no decrease in performance on the USMLE Step 1 examination. These results are discussed in the broader context of the multitude of factors that should be considered in assessing the merits of various grading systems, and ultimately the authors recommend the continuation of pass-fail grading at UCSD School of Medicine.

The prediction in computer color matching of dentistry based on GA+BP neural network.

Science.gov (United States)

Li, Haisheng; Lai, Long; Chen, Li; Lu, Cheng; Cai, Qiang

2015-01-01

Although the use of computer color matching can reduce the influence of subjective factors by technicians, matching the color of a natural tooth with a ceramic restoration is still one of the most challenging topics in esthetic prosthodontics. Back propagation neural network (BPNN) has already been introduced into the computer color matching in dentistry, but it has disadvantages such as unstable and low accuracy. In our study, we adopt genetic algorithm (GA) to optimize the initial weights and threshold values in BPNN for improving the matching precision. To our knowledge, we firstly combine the BPNN with GA in computer color matching in dentistry. Extensive experiments demonstrate that the proposed method improves the precision and prediction robustness of the color matching in restorative dentistry.

Binary Factorization in Hopfield-Like Neural Networks: Single-Step Approximation and Computer Simulations

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Sirota, A.M.; Húsek, Dušan; Muraviev, I. P.

2004-01-01

Roč. 14, č. 2 (2004), s. 139-152 ISSN 1210-0552 R&D Projects: GA ČR GA201/01/1192 Grant - others:BARRANDE(EU) 99010-2/99053; Intellectual computer Systems(EU) Grant 2.45 Institutional research plan: CEZ:AV0Z1030915 Keywords : nonlinear binary factor analysis * feature extraction * recurrent neural network * Single-Step approximation * neurodynamics simulation * attraction basins * Hebbian learning * unsupervised learning * neuroscience * brain function modeling Subject RIV: BA - General Mathematics

Use of artificial neural networks (computer analysis) in the diagnosis of microcalcifications on mammography

International Nuclear Information System (INIS)

Markopoulos, Christos; Kouskos, Efstratios; Koufopoulos, Konstantinos; Kyriakou, Vasiliki; Gogas, John

2001-01-01

Introduction/objective: the purpose of this study was to evaluate a computer based method for differentiating malignant from benign clustered microcalcifications, comparing it with the performance of three physicians. Methods and material: materials for the study are 240 suspicious microcalcifications on mammograms from 220 female patients who underwent breast biopsy, following hook wire localization under mammographic guidance. The histologic findings were malignant in 108 cases (45%) and benign in 132 cases (55%). Those clusters were analyzed by a computer program and eight features of the calcifications (density, number, area, brightness, diameter average, distance average, proximity average, perimeter compacity average) were quantitatively estimated by a specific artificial neural network. Human input was limited to initial identification of the calcifications. Three physicians-observers were also evaluated for the malignant or benign nature of the clustered microcalcifications. Results: the performance of the artificial network was evaluated by receiver operating characteristics (ROC) curves. ROC curves were also generated for the performance of each observer and for the three observers as a group. The ROC curves for the computer and for the physicians were compared and the results are:area under the curve (AUC) value for computer is 0.937, for physician-1 is 0.746, for physician-2 is 0.785, for physician-3 is 0.835 and for physicians as a group is 0.810. The results of the Student's t-test for paired data showed statistically significant difference between the artificial neural network and the physicians' performance, independently and as a group. Discussion and conclusion: our study showed that computer analysis achieves statistically significantly better performance than that of physicians in the classification of malignant and benign calcifications. This method, after further evaluation and improvement, may help radiologists and breast surgeons in better

Handwritten Digits Recognition Using Neural Computing

Directory of Open Access Journals (Sweden)

Călin Enăchescu

2009-12-01

Full Text Available In this paper we present a method for the recognition of handwritten digits and a practical implementation of this method for real-time recognition. A theoretical framework for the neural networks used to classify the handwritten digits is also presented.The classification task is performed using a Convolutional Neural Network (CNN. CNN is a special type of multy-layer neural network, being trained with an optimized version of the back-propagation learning algorithm.CNN is designed to recognize visual patterns directly from pixel images with minimal preprocessing, being capable to recognize patterns with extreme variability (such as handwritten characters, and with robustness to distortions and simple geometric transformations.The main contributions of this paper are related to theoriginal methods for increasing the efficiency of the learning algorithm by preprocessing the images before the learning process and a method for increasing the precision and performance for real-time applications, by removing the non useful information from the background.By combining these strategies we have obtained an accuracy of 96.76%, using as training set the NIST (National Institute of Standards and Technology database.

Artificial Neural Networks for Reducing Computational Effort in Active Truncated Model Testing of Mooring Lines

DEFF Research Database (Denmark)

Christiansen, Niels Hørbye; Voie, Per Erlend Torbergsen; Høgsberg, Jan Becker

2015-01-01

simultaneously, this method is very demanding in terms of numerical efficiency and computational power. Therefore, this method has not yet proved to be feasible. It has recently been shown how a hybrid method combining classical numerical models and artificial neural networks (ANN) can provide a dramatic...... prior to the experiment and with a properly trained ANN it is no problem to obtain accurate simulations much faster than real time-without any need for large computational capacity. The present study demonstrates how this hybrid method can be applied to the active truncated experiments yielding a system...

COMPUTING

CERN Multimedia

I. Fisk

2011-01-01

Introduction The Computing Team successfully completed the storage, initial processing, and distribution for analysis of proton-proton data in 2011. There are still a variety of activities ongoing to support winter conference activities and preparations for 2012. Heavy ions The heavy-ion run for 2011 started in early November and has already demonstrated good machine performance and success of some of the more advanced workflows planned for 2011. Data collection will continue until early December. Facilities and Infrastructure Operations Operational and deployment support for WMAgent and WorkQueue+Request Manager components, routinely used in production by Data Operations, are provided. The GlideInWMS and components installation are now deployed at CERN, which is added to the GlideInWMS factory placed in the US. There has been new operational collaboration between the CERN team and the UCSD GlideIn factory operators, covering each others time zones by monitoring/debugging pilot jobs sent from the facto...

Biomaterials and computation: a strategic alliance to investigate emergent responses of neural cells.

Science.gov (United States)

Sergi, Pier Nicola; Cavalcanti-Adam, Elisabetta Ada

2017-03-28

Topographical and chemical cues drive migration, outgrowth and regeneration of neurons in different and crucial biological conditions. In the natural extracellular matrix, their influences are so closely coupled that they result in complex cellular responses. As a consequence, engineered biomaterials are widely used to simplify in vitro conditions, disentangling intricate in vivo behaviours, and narrowing the investigation on particular emergent responses. Nevertheless, how topographical and chemical cues affect the emergent response of neural cells is still unclear, thus in silico models are used as additional tools to reproduce and investigate the interactions between cells and engineered biomaterials. This work aims at presenting the synergistic use of biomaterials-based experiments and computation as a strategic way to promote the discovering of complex neural responses as well as to allow the interactions between cells and biomaterials to be quantitatively investigated, fostering a rational design of experiments.

Antenna analysis using neural networks

Science.gov (United States)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern

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.

The Use of Neural Network to Recognize the Parts of the Computer Motherboard

OpenAIRE

Abbas M. Ali; S. D. Gore; Musaab AL-Sarierah

2005-01-01

This study suggests a new approach of learning which utilizes the techniques of computer vision to recognize the parts inside the motherboard. The main thrust is to identify different parts of the motherboard using a Hopfield Neural Network. The outcome of the net is compared with the objects stored in the database. The proposed scheme is implemented using bottom -up approach, where steps like edge detection, spatial filtering, image masking..etc are performed in sequence. the scheme is simul...

Neural Network Optimization of Ligament Stiffnesses for the Enhanced Predictive Ability of a Patient-Specific, Computational Foot/Ankle Model.

Science.gov (United States)

Chande, Ruchi D; Wayne, Jennifer S

2017-09-01

Computational models of diarthrodial joints serve to inform the biomechanical function of these structures, and as such, must be supplied appropriate inputs for performance that is representative of actual joint function. Inputs for these models are sourced from both imaging modalities as well as literature. The latter is often the source of mechanical properties for soft tissues, like ligament stiffnesses; however, such data are not always available for all the soft tissues nor is it known for patient-specific work. In the current research, a method to improve the ligament stiffness definition for a computational foot/ankle model was sought with the greater goal of improving the predictive ability of the computational model. Specifically, the stiffness values were optimized using artificial neural networks (ANNs); both feedforward and radial basis function networks (RBFNs) were considered. Optimal networks of each type were determined and subsequently used to predict stiffnesses for the foot/ankle model. Ultimately, the predicted stiffnesses were considered reasonable and resulted in enhanced performance of the computational model, suggesting that artificial neural networks can be used to optimize stiffness inputs.

Advanced Applications of Neural Networks and Artificial Intelligence: A Review

OpenAIRE

Koushal Kumar; Gour Sundar Mitra Thakur

2012-01-01

Artificial Neural Network is a branch of Artificial intelligence and has been accepted as a new computing technology in computer science fields. This paper reviews the field of Artificial intelligence and focusing on recent applications which uses Artificial Neural Networks (ANN’s) and Artificial Intelligence (AI). It also considers the integration of neural networks with other computing methods Such as fuzzy logic to enhance the interpretation ability of data. Artificial Neural Networks is c...

Program Helps Simulate Neural Networks

Science.gov (United States)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks.

Science.gov (United States)

Längkvist, Martin; Jendeberg, Johan; Thunberg, Per; Loutfi, Amy; Lidén, Mats

2018-06-01

Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

[Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network].

Science.gov (United States)

Wang, Yuanyuan; Zhou, Tao; Lu, Huiling; Wu, Cuiying; Yang, Pengfei

2017-08-01

The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.

Is Neural Activity Detected by ERP-Based Brain-Computer Interfaces Task Specific?

Directory of Open Access Journals (Sweden)

Markus A Wenzel

Full Text Available Brain-computer interfaces (BCIs that are based on event-related potentials (ERPs can estimate to which stimulus a user pays particular attention. In typical BCIs, the user silently counts the selected stimulus (which is repeatedly presented among other stimuli in order to focus the attention. The stimulus of interest is then inferred from the electroencephalogram (EEG. Detecting attention allocation implicitly could be also beneficial for human-computer interaction (HCI, because it would allow software to adapt to the user's interest. However, a counting task would be inappropriate for the envisaged implicit application in HCI. Therefore, the question was addressed if the detectable neural activity is specific for silent counting, or if it can be evoked also by other tasks that direct the attention to certain stimuli.Thirteen people performed a silent counting, an arithmetic and a memory task. The tasks required the subjects to pay particular attention to target stimuli of a random color. The stimulus presentation was the same in all three tasks, which allowed a direct comparison of the experimental conditions.Classifiers that were trained to detect the targets in one task, according to patterns present in the EEG signal, could detect targets in all other tasks (irrespective of some task-related differences in the EEG.The neural activity detected by the classifiers is not strictly task specific but can be generalized over tasks and is presumably a result of the attention allocation or of the augmented workload. The results may hold promise for the transfer of classification algorithms from BCI research to implicit relevance detection in HCI.

Neural computation and particle accelerators research, technology and applications

CERN Document Server

D'Arras, Horace

2010-01-01

This book discusses neural computation, a network or circuit of biological neurons and relatedly, particle accelerators, a scientific instrument which accelerates charged particles such as protons, electrons and deuterons. Accelerators have a very broad range of applications in many industrial fields, from high energy physics to medical isotope production. Nuclear technology is one of the fields discussed in this book. The development that has been reached by particle accelerators in energy and particle intensity has opened the possibility to a wide number of new applications in nuclear technology. This book reviews the applications in the nuclear energy field and the design features of high power neutron sources are explained. Surface treatments of niobium flat samples and superconducting radio frequency cavities by a new technique called gas cluster ion beam are also studied in detail, as well as the process of electropolishing. Furthermore, magnetic devises such as solenoids, dipoles and undulators, which ...

Computational optical tomography using 3-D deep convolutional neural networks

Science.gov (United States)

Nguyen, Thanh; Bui, Vy; Nehmetallah, George

2018-04-01

Deep convolutional neural networks (DCNNs) offer a promising performance for many image processing areas, such as super-resolution, deconvolution, image classification, denoising, and segmentation, with outstanding results. Here, we develop for the first time, to our knowledge, a method to perform 3-D computational optical tomography using 3-D DCNN. A simulated 3-D phantom dataset was first constructed and converted to a dataset of phase objects imaged on a spatial light modulator. For each phase image in the dataset, the corresponding diffracted intensity image was experimentally recorded on a CCD. We then experimentally demonstrate the ability of the developed 3-D DCNN algorithm to solve the inverse problem by reconstructing the 3-D index of refraction distributions of test phantoms from the dataset from their corresponding diffraction patterns.

On the Reduction of Computational Complexity of Deep Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Partha Maji

2018-04-01

Full Text Available Deep convolutional neural networks (ConvNets, which are at the heart of many new emerging applications, achieve remarkable performance in audio and visual recognition tasks. Unfortunately, achieving accuracy often implies significant computational costs, limiting deployability. In modern ConvNets it is typical for the convolution layers to consume the vast majority of computational resources during inference. This has made the acceleration of these layers an important research area in academia and industry. In this paper, we examine the effects of co-optimizing the internal structures of the convolutional layers and underlying implementation of fundamental convolution operation. We demonstrate that a combination of these methods can have a big impact on the overall speedup of a ConvNet, achieving a ten-fold increase over baseline. We also introduce a new class of fast one-dimensional (1D convolutions for ConvNets using the Toom–Cook algorithm. We show that our proposed scheme is mathematically well-grounded, robust, and does not require any time-consuming retraining, while still achieving speedups solely from convolutional layers with no loss in baseline accuracy.

Encoding neural and synaptic functionalities in electron spin: A pathway to efficient neuromorphic computing

Science.gov (United States)

Sengupta, Abhronil; Roy, Kaushik

2017-12-01

Present day computers expend orders of magnitude more computational resources to perform various cognitive and perception related tasks that humans routinely perform every day. This has recently resulted in a seismic shift in the field of computation where research efforts are being directed to develop a neurocomputer that attempts to mimic the human brain by nanoelectronic components and thereby harness its efficiency in recognition problems. Bridging the gap between neuroscience and nanoelectronics, this paper attempts to provide a review of the recent developments in the field of spintronic device based neuromorphic computing. Description of various spin-transfer torque mechanisms that can be potentially utilized for realizing device structures mimicking neural and synaptic functionalities is provided. A cross-layer perspective extending from the device to the circuit and system level is presented to envision the design of an All-Spin neuromorphic processor enabled with on-chip learning functionalities. Device-circuit-algorithm co-simulation framework calibrated to experimental results suggest that such All-Spin neuromorphic systems can potentially achieve almost two orders of magnitude energy improvement in comparison to state-of-the-art CMOS implementations.

Design and update of a classification system: the UCSD map of science.

Directory of Open Access Journals (Sweden)

Katy Börner

Full Text Available Global maps of science can be used as a reference system to chart career trajectories, the location of emerging research frontiers, or the expertise profiles of institutes or nations. This paper details data preparation, analysis, and layout performed when designing and subsequently updating the UCSD map of science and classification system. The original classification and map use 7.2 million papers and their references from Elsevier's Scopus (about 15,000 source titles, 2001-2005 and Thomson Reuters' Web of Science (WoS Science, Social Science, Arts & Humanities Citation Indexes (about 9,000 source titles, 2001-2004-about 16,000 unique source titles. The updated map and classification adds six years (2005-2010 of WoS data and three years (2006-2008 from Scopus to the existing category structure-increasing the number of source titles to about 25,000. To our knowledge, this is the first time that a widely used map of science was updated. A comparison of the original 5-year and the new 10-year maps and classification system show (i an increase in the total number of journals that can be mapped by 9,409 journals (social sciences had a 80% increase, humanities a 119% increase, medical (32% and natural science (74%, (ii a simplification of the map by assigning all but five highly interdisciplinary journals to exactly one discipline, (iii a more even distribution of journals over the 554 subdisciplines and 13 disciplines when calculating the coefficient of variation, and (iv a better reflection of journal clusters when compared with paper-level citation data. When evaluating the map with a listing of desirable features for maps of science, the updated map is shown to have higher mapping accuracy, easier understandability as fewer journals are multiply classified, and higher usability for the generation of data overlays, among others.

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.

Computational Models of Neuron-Astrocyte Interactions Lead to Improved Efficacy in the Performance of Neural Networks

Science.gov (United States)

Alvarellos-González, Alberto; Pazos, Alejandro; Porto-Pazos, Ana B.

2012-01-01

The importance of astrocytes, one part of the glial system, for information processing in the brain has recently been demonstrated. Regarding information processing in multilayer connectionist systems, it has been shown that systems which include artificial neurons and astrocytes (Artificial Neuron-Glia Networks) have well-known advantages over identical systems including only artificial neurons. Since the actual impact of astrocytes in neural network function is unknown, we have investigated, using computational models, different astrocyte-neuron interactions for information processing; different neuron-glia algorithms have been implemented for training and validation of multilayer Artificial Neuron-Glia Networks oriented toward classification problem resolution. The results of the tests performed suggest that all the algorithms modelling astrocyte-induced synaptic potentiation improved artificial neural network performance, but their efficacy depended on the complexity of the problem. PMID:22649480

A novel role for visual perspective cues in the neural computation of depth.

Science.gov (United States)

Kim, HyungGoo R; Angelaki, Dora E; DeAngelis, Gregory C

2015-01-01

As we explore a scene, our eye movements add global patterns of motion to the retinal image, complicating visual motion produced by self-motion or moving objects. Conventionally, it has been assumed that extraretinal signals, such as efference copy of smooth pursuit commands, are required to compensate for the visual consequences of eye rotations. We consider an alternative possibility: namely, that the visual system can infer eye rotations from global patterns of image motion. We visually simulated combinations of eye translation and rotation, including perspective distortions that change dynamically over time. We found that incorporating these 'dynamic perspective' cues allowed the visual system to generate selectivity for depth sign from motion parallax in macaque cortical area MT, a computation that was previously thought to require extraretinal signals regarding eye velocity. Our findings suggest neural mechanisms that analyze global patterns of visual motion to perform computations that require knowledge of eye rotations.

Goal-directed behaviour and instrumental devaluation: a neural system-level computational model

Directory of Open Access Journals (Sweden)

Francesco Mannella

2016-10-01

Full Text Available Devaluation is the key experimental paradigm used to demonstrate the presence of instrumental behaviours guided by goals in mammals. We propose a neural system-level computational model to address the question of which brain mechanisms allow the current value of rewards to control instrumental actions. The model pivots on and shows the computational soundness of the hypothesis for which the internal representation of instrumental manipulanda (e.g., levers activate the representation of rewards (or `action-outcomes', e.g. foods while attributing to them a value which depends on the current internal state of the animal (e.g., satiation for some but not all foods. The model also proposes an initial hypothesis of the integrated system of key brain components supporting this process and allowing the recalled outcomes to bias action selection: (a the sub-system formed by the basolateral amygdala and insular cortex acquiring the manipulanda-outcomes associations and attributing the current value to the outcomes; (b the three basal ganglia-cortical loops selecting respectively goals, associative sensory representations, and actions; (c the cortico-cortical and striato-nigro-striatal neural pathways supporting the selection, and selection learning, of actions based on habits and goals. The model reproduces and integrates the results of different devaluation experiments carried out with control rats and rats with pre- and post-training lesions of the basolateral amygdala, the nucleus accumbens core, the prelimbic cortex, and the dorso-medial striatum. The results support the soundness of the hypotheses of the model and show its capacity to integrate, at the system-level, the operations of the key brain structures underlying devaluation. Based on its hypotheses and predictions, the model also represents an operational framework to support the design and analysis of new experiments on the motivational aspects of goal-directed behaviour.

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

The Study of Learners' Preference for Visual Complexity on Small Screens of Mobile Computers Using Neural Networks

Science.gov (United States)

Wang, Lan-Ting; Lee, Kun-Chou

2014-01-01

The vision plays an important role in educational technologies because it can produce and communicate quite important functions in teaching and learning. In this paper, learners' preference for the visual complexity on small screens of mobile computers is studied by neural networks. The visual complexity in this study is divided into five…

Neural Systems Laboratory

Data.gov (United States)

Federal Laboratory Consortium — As part of the Electrical and Computer Engineering Department and The Institute for System Research, the Neural Systems Laboratory studies the functionality of the...

Hardware implementation of stochastic spiking neural networks.

Science.gov (United States)

Rosselló, Josep L; Canals, Vincent; Morro, Antoni; Oliver, Antoni

2012-08-01

Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.

Application of artificial neural networks to identify equilibration in computer simulations

Science.gov (United States)

Leibowitz, Mitchell H.; Miller, Evan D.; Henry, Michael M.; Jankowski, Eric

2017-11-01

Determining which microstates generated by a thermodynamic simulation are representative of the ensemble for which sampling is desired is a ubiquitous, underspecified problem. Artificial neural networks are one type of machine learning algorithm that can provide a reproducible way to apply pattern recognition heuristics to underspecified problems. Here we use the open-source TensorFlow machine learning library and apply it to the problem of identifying which hypothetical observation sequences from a computer simulation are “equilibrated” and which are not. We generate training populations and test populations of observation sequences with embedded linear and exponential correlations. We train a two-neuron artificial network to distinguish the correlated and uncorrelated sequences. We find that this simple network is good enough for > 98% accuracy in identifying exponentially-decaying energy trajectories from molecular simulations.

Attacks and Intrusion Detection in Cloud Computing Using Neural Networks and Particle Swarm Optimization Algorithms

Directory of Open Access Journals (Sweden)

Ahmad Shokuh Saljoughi

2018-01-01

Full Text Available Today, cloud computing has become popular among users in organizations and companies. Security and efficiency are the two major issues facing cloud service providers and their customers. Since cloud computing is a virtual pool of resources provided in an open environment (Internet, cloud-based services entail security risks. Detection of intrusions and attacks through unauthorized users is one of the biggest challenges for both cloud service providers and cloud users. In the present study, artificial intelligence techniques, e.g. MLP Neural Network sand particle swarm optimization algorithm, were used to detect intrusion and attacks. The methods were tested for NSL-KDD, KDD-CUP datasets. The results showed improved accuracy in detecting attacks and intrusions by unauthorized users.

An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks

Science.gov (United States)

Cabessa, Jérémie; Villa, Alessandro E. P.

2014-01-01

We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of -automata, and then translating the most refined classification of -automata to the Boolean neural network context. As a result, a hierarchical classification of Boolean neural networks based on their attractive dynamics is obtained, thus providing a novel refined attractor-based complexity measurement for Boolean recurrent neural networks. These results provide new theoretical insights to the computational and dynamical capabilities of neural networks according to their attractive potentialities. An application of our findings is illustrated by the analysis of the dynamics of a simplified model of the basal ganglia-thalamocortical network simulated by a Boolean recurrent neural network. This example shows the significance of measuring network complexity, and how our results bear new founding elements for the understanding of the complexity of real brain circuits. PMID:24727866

A high-speed analog neural processor

NARCIS (Netherlands)

Masa, P.; Masa, Peter; Hoen, Klaas; Hoen, Klaas; Wallinga, Hans

1994-01-01

Targeted at high-energy physics research applications, our special-purpose analog neural processor can classify up to 70 dimensional vectors within 50 nanoseconds. The decision-making process of the implemented feedforward neural network enables this type of computation to tolerate weight

International Conference on Artificial Neural Networks (ICANN)

CERN Document Server

Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics

2015-01-01

The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...

A Reconfigurable and Biologically Inspired Paradigm for Computation Using Network-On-Chip and Spiking Neural Networks

Directory of Open Access Journals (Sweden)

Jim Harkin

2009-01-01

Full Text Available FPGA devices have emerged as a popular platform for the rapid prototyping of biological Spiking Neural Networks (SNNs applications, offering the key requirement of reconfigurability. However, FPGAs do not efficiently realise the biologically plausible neuron and synaptic models of SNNs, and current FPGA routing structures cannot accommodate the high levels of interneuron connectivity inherent in complex SNNs. This paper highlights and discusses the current challenges of implementing scalable SNNs on reconfigurable FPGAs. The paper proposes a novel field programmable neural network architecture (EMBRACE, incorporating low-power analogue spiking neurons, interconnected using a Network-on-Chip architecture. Results on the evaluation of the EMBRACE architecture using the XOR benchmark problem are presented, and the performance of the architecture is discussed. The paper also discusses the adaptability of the EMBRACE architecture in supporting fault tolerant computing.

Artificial neural networks in NDT

International Nuclear Information System (INIS)

Abdul Aziz Mohamed

2001-01-01

Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)

Deep learning for computational chemistry

Energy Technology Data Exchange (ETDEWEB)

Goh, Garrett B. [Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, 902 Battelle Blvd Richland Washington 99354; Hodas, Nathan O. [Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, 902 Battelle Blvd Richland Washington 99354; Vishnu, Abhinav [Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, 902 Battelle Blvd Richland Washington 99354

2017-03-08

The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.

Dual Coding Theory Explains Biphasic Collective Computation in Neural Decision-Making

Directory of Open Access Journals (Sweden)

Bryan C. Daniels

2017-06-01

Full Text Available A central question in cognitive neuroscience is how unitary, coherent decisions at the whole organism level can arise from the distributed behavior of a large population of neurons with only partially overlapping information. We address this issue by studying neural spiking behavior recorded from a multielectrode array with 169 channels during a visual motion direction discrimination task. It is well known that in this task there are two distinct phases in neural spiking behavior. Here we show Phase I is a distributed or incompressible phase in which uncertainty about the decision is substantially reduced by pooling information from many cells. Phase II is a redundant or compressible phase in which numerous single cells contain all the information present at the population level in Phase I, such that the firing behavior of a single cell is enough to predict the subject's decision. Using an empirically grounded dynamical modeling framework, we show that in Phase I large cell populations with low redundancy produce a slow timescale of information aggregation through critical slowing down near a symmetry-breaking transition. Our model indicates that increasing collective amplification in Phase II leads naturally to a faster timescale of information pooling and consensus formation. Based on our results and others in the literature, we propose that a general feature of collective computation is a “coding duality” in which there are accumulation and consensus formation processes distinguished by different timescales.

Dual Coding Theory Explains Biphasic Collective Computation in Neural Decision-Making.

Science.gov (United States)

Daniels, Bryan C; Flack, Jessica C; Krakauer, David C

2017-01-01

A central question in cognitive neuroscience is how unitary, coherent decisions at the whole organism level can arise from the distributed behavior of a large population of neurons with only partially overlapping information. We address this issue by studying neural spiking behavior recorded from a multielectrode array with 169 channels during a visual motion direction discrimination task. It is well known that in this task there are two distinct phases in neural spiking behavior. Here we show Phase I is a distributed or incompressible phase in which uncertainty about the decision is substantially reduced by pooling information from many cells. Phase II is a redundant or compressible phase in which numerous single cells contain all the information present at the population level in Phase I, such that the firing behavior of a single cell is enough to predict the subject's decision. Using an empirically grounded dynamical modeling framework, we show that in Phase I large cell populations with low redundancy produce a slow timescale of information aggregation through critical slowing down near a symmetry-breaking transition. Our model indicates that increasing collective amplification in Phase II leads naturally to a faster timescale of information pooling and consensus formation. Based on our results and others in the literature, we propose that a general feature of collective computation is a "coding duality" in which there are accumulation and consensus formation processes distinguished by different timescales.

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

Premonitory urges and tics in Tourette syndrome: computational mechanisms and neural correlates.

Science.gov (United States)

Conceição, Vasco A; Dias, Ângelo; Farinha, Ana C; Maia, Tiago V

2017-10-01

Tourette syndrome is characterized by open motor behaviors - tics - but another crucial aspect of the disorder is the presence of premonitory urges: uncomfortable sensations that typically precede tics and are temporarily alleviated by tics. We review the evidence implicating the somatosensory cortices and the insula in premonitory urges and the motor cortico-basal ganglia-thalamo-cortical loop in tics. We consider how these regions interact during tic execution, suggesting that the insula plays an important role as a nexus linking the sensory and emotional character of premonitory urges with their translation into tics. We also consider how these regions interact during tic learning, integrating the neural evidence with a computational perspective on how premonitory-urge alleviation reinforces tics. Copyright © 2017 Elsevier Ltd. All rights reserved.

An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture

Directory of Open Access Journals (Sweden)

Xiaopu Zhang

2018-06-01

Full Text Available Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR. The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN and long short-term memory (LSTM is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96% with less transmitted data (about 90% was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture.

Science.gov (United States)

Zhang, Xiaopu; Lin, Jun; Chen, Zubin; Sun, Feng; Zhu, Xi; Fang, Gengfa

2018-06-05

Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR). The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN) and long short-term memory (LSTM) is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96%) with less transmitted data (about 90%) was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

A neutron spectrum unfolding computer code based on artificial neural networks

International Nuclear Information System (INIS)

Ortiz-Rodríguez, J.M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J.M.; Vega-Carrillo, H.R.

2014-01-01

The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6 LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding

MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning.

Science.gov (United States)

Liu, Yang; Yang, Jie; Huang, Yuan; Xu, Lixiong; Li, Siguang; Qi, Man

2015-01-01

Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation.

Deep learning for computational chemistry.

Science.gov (United States)

Goh, Garrett B; Hodas, Nathan O; Vishnu, Abhinav

2017-06-15

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Neural networks - Potential appplication in the nuclear industry

International Nuclear Information System (INIS)

Yiftah, S.

1989-01-01

Neural networks are an emerging technology which is perceived to have potential for solving complex computation problems which cannot be solved by standard computational methods. One such example is the inverse kinematics problem which is considered to be the most difficult problem in robotics. In 1986, only one neural network modelling tool was available, now there are about twenty offered commercially by various companies in North America

Computing Generalized Matrix Inverse on Spiking Neural Substrate

Directory of Open Access Journals (Sweden)

Rohit Shukla

2018-03-01

Full Text Available Emerging neural hardware substrates, such as IBM's TrueNorth Neurosynaptic System, can provide an appealing platform for deploying numerical algorithms. For example, a recurrent Hopfield neural network can be used to find the Moore-Penrose generalized inverse of a matrix, thus enabling a broad class of linear optimizations to be solved efficiently, at low energy cost. However, deploying numerical algorithms on hardware platforms that severely limit the range and precision of representation for numeric quantities can be quite challenging. This paper discusses these challenges and proposes a rigorous mathematical framework for reasoning about range and precision on such substrates. The paper derives techniques for normalizing inputs and properly quantizing synaptic weights originating from arbitrary systems of linear equations, so that solvers for those systems can be implemented in a provably correct manner on hardware-constrained neural substrates. The analytical model is empirically validated on the IBM TrueNorth platform, and results show that the guarantees provided by the framework for range and precision hold under experimental conditions. Experiments with optical flow demonstrate the energy benefits of deploying a reduced-precision and energy-efficient generalized matrix inverse engine on the IBM TrueNorth platform, reflecting 10× to 100× improvement over FPGA and ARM core baselines.

Computing Generalized Matrix Inverse on Spiking Neural Substrate

Science.gov (United States)

Shukla, Rohit; Khoram, Soroosh; Jorgensen, Erik; Li, Jing; Lipasti, Mikko; Wright, Stephen

2018-01-01

Emerging neural hardware substrates, such as IBM's TrueNorth Neurosynaptic System, can provide an appealing platform for deploying numerical algorithms. For example, a recurrent Hopfield neural network can be used to find the Moore-Penrose generalized inverse of a matrix, thus enabling a broad class of linear optimizations to be solved efficiently, at low energy cost. However, deploying numerical algorithms on hardware platforms that severely limit the range and precision of representation for numeric quantities can be quite challenging. This paper discusses these challenges and proposes a rigorous mathematical framework for reasoning about range and precision on such substrates. The paper derives techniques for normalizing inputs and properly quantizing synaptic weights originating from arbitrary systems of linear equations, so that solvers for those systems can be implemented in a provably correct manner on hardware-constrained neural substrates. The analytical model is empirically validated on the IBM TrueNorth platform, and results show that the guarantees provided by the framework for range and precision hold under experimental conditions. Experiments with optical flow demonstrate the energy benefits of deploying a reduced-precision and energy-efficient generalized matrix inverse engine on the IBM TrueNorth platform, reflecting 10× to 100× improvement over FPGA and ARM core baselines. PMID:29593483

Reconstruction of sub-surface archaeological remains from magnetic data using neural computing.

Science.gov (United States)

Bescoby, D. J.; Cawley, G. C.; Chroston, P. N.

2003-04-01

The remains of a former Roman colonial settlement, once part of the classical city of Butrint in southern Albania have been the subject of a high resolution magnetic survey using a caesium-vapour magnetometer. The survey revealed the surviving remains of an extensive planned settlement and a number of outlying buildings, today buried beneath over 0.5 m of alluvial deposits. The aim of the current research is to derive a sub-surface model from the magnetic survey measurements, allowing an enhanced archaeological interpretation of the data. Neural computing techniques are used to perform the non-linear mapping between magnetic data and corresponding sub-surface model parameters. The adoption of neural computing paradigms potentially holds several advantages over other modelling techniques, allowing fast solutions for complex data, while having a high tolerance to noise. A multi-layer perceptron network with a feed-forward architecture is trained to estimate the shape and burial depth of wall foundations using a series of representative models as training data. Parameters used to forward model the training data sets are derived from a number of trial trench excavations targeted over features identified by the magnetic survey. The training of the network was optimized by first applying it to synthetic test data of known source parameters. Pre-processing of the network input data, including the use of a rotationally invariant transform, enhanced network performance and the efficiency of the training data. The approach provides good results when applied to real magnetic data, accurately predicting the depths and layout of wall foundations within the former settlement, verified by subsequent excavation. The resulting sub-surface model is derived from the averaged outputs of a ‘committee’ of five networks, trained with individualized training sets. Fuzzy logic inference has also been used to combine individual network outputs through correlation with data from a second

MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning

Directory of Open Access Journals (Sweden)

Yang Liu

2015-01-01

Full Text Available Artificial neural networks (ANNs have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation.

Neural Parallel Engine: A toolbox for massively parallel neural signal processing.

Science.gov (United States)

Tam, Wing-Kin; Yang, Zhi

2018-05-01

Large-scale neural recordings provide detailed information on neuronal activities and can help elicit the underlying neural mechanisms of the brain. However, the computational burden is also formidable when we try to process the huge data stream generated by such recordings. In this study, we report the development of Neural Parallel Engine (NPE), a toolbox for massively parallel neural signal processing on graphical processing units (GPUs). It offers a selection of the most commonly used routines in neural signal processing such as spike detection and spike sorting, including advanced algorithms such as exponential-component-power-component (EC-PC) spike detection and binary pursuit spike sorting. We also propose a new method for detecting peaks in parallel through a parallel compact operation. Our toolbox is able to offer a 5× to 110× speedup compared with its CPU counterparts depending on the algorithms. A user-friendly MATLAB interface is provided to allow easy integration of the toolbox into existing workflows. Previous efforts on GPU neural signal processing only focus on a few rudimentary algorithms, are not well-optimized and often do not provide a user-friendly programming interface to fit into existing workflows. There is a strong need for a comprehensive toolbox for massively parallel neural signal processing. A new toolbox for massively parallel neural signal processing has been created. It can offer significant speedup in processing signals from large-scale recordings up to thousands of channels. Copyright © 2018 Elsevier B.V. All rights reserved.

The feasibility of using neural networks to obtain cross sections from electron swarm data

International Nuclear Information System (INIS)

Morgan, W.L.

1991-01-01

This paper reports that although still more a curiosity than an accepted technique in computational modeling, the very new field of neural computing is beginning to find applications in physics. Presented in some background on neural computing and a discussion on the use of neural networks to obtain electron-impact cross sections from measured drift velocities, characteristic energies, and other swarm data. This is what is known as an inverse problem, a class of problems for which neural networks may be frequently superior to other numerical algorithms. Momentum transfer cross sections obtained for a model problem and for xenon using a neural network are presented

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.

Type-2 fuzzy neural networks and their applications

CERN Document Server

Aliev, Rafik Aziz

2014-01-01

This book deals with the theory, design principles, and application of hybrid intelligent systems using type-2 fuzzy sets in combination with other paradigms of Soft Computing technology such as Neuro-Computing and Evolutionary Computing. It provides a self-contained exposition of the foundation of type-2 fuzzy neural networks and presents a vast compendium of its applications to control, forecasting, decision making, system identification and other real problems. Type-2 Fuzzy Neural Networks and Their Applications is helpful for teachers and students of universities and colleges, for scientis

Emerging phenomena in neural networks with dynamic synapses and their computational implications

Directory of Open Access Journals (Sweden)

Joaquin J. eTorres

2013-04-01

Full Text Available In this paper we review our research on the effect and computational role of dynamical synapses on feed-forward and recurrent neural networks. Among others, we report on the appearance of a new class of dynamical memories which result from the destabilisation of learned memory attractors. This has important consequences for dynamic information processing allowing the system to sequentially access the information stored in the memories under changing stimuli. Although storage capacity of stable memories also decreases, our study demonstrated the positive effect of synaptic facilitation to recover maximum storage capacity and to enlarge the capacity of the system for memory recall in noisy conditions. Possibly, the new dynamical behaviour can be associated with the voltage transitions between up and down states observed in cortical areas in the brain. We investigated the conditions for which the permanence times in the up state are power-law distributed, which is a sign for criticality, and concluded that the experimentally observed large variability of permanence times could be explained as the result of noisy dynamic synapses with large recovery times. Finally, we report how short-term synaptic processes can transmit weak signals throughout more than one frequency range in noisy neural networks, displaying a kind of stochastic multi-resonance. This effect is due to competition between activity-dependent synaptic fluctuations (due to dynamic synapses and the existence of neuron firing threshold which adapts to the incoming mean synaptic input.

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.

Modular Neural Tile Architecture for Compact Embedded Hardware Spiking Neural Network

NARCIS (Netherlands)

Pande, Sandeep; Morgan, Fearghal; Cawley, Seamus; Bruintjes, Tom; Smit, Gerardus Johannes Maria; McGinley, Brian; Carrillo, Snaider; Harkin, Jim; McDaid, Liam

2013-01-01

Biologically-inspired packet switched network on chip (NoC) based hardware spiking neural network (SNN) architectures have been proposed as an embedded computing platform for classification, estimation and control applications. Storage of large synaptic connectivity (SNN topology) information in

Random noise effects in pulse-mode digital multilayer neural networks.

Science.gov (United States)

Kim, Y C; Shanblatt, M A

1995-01-01

A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

Characterization of physiological networks in sleep apnea patients using artificial neural networks for Granger causality computation

Science.gov (United States)

Cárdenas, Jhon; Orjuela-Cañón, Alvaro D.; Cerquera, Alexander; Ravelo, Antonio

2017-11-01

Different studies have used Transfer Entropy (TE) and Granger Causality (GC) computation to quantify interconnection between physiological systems. These methods have disadvantages in parametrization and availability in analytic formulas to evaluate the significance of the results. Other inconvenience is related with the assumptions in the distribution of the models generated from the data. In this document, the authors present a way to measure the causality that connect the Central Nervous System (CNS) and the Cardiac System (CS) in people diagnosed with obstructive sleep apnea syndrome (OSA) before and during treatment with continuous positive air pressure (CPAP). For this purpose, artificial neural networks were used to obtain models for GC computation, based on time series of normalized powers calculated from electrocardiography (EKG) and electroencephalography (EEG) signals recorded in polysomnography (PSG) studies.

The Effects of GABAergic Polarity Changes on Episodic Neural Network Activity in Developing Neural Systems

Directory of Open Access Journals (Sweden)

Wilfredo Blanco

2017-09-01

Full Text Available Early in development, neural systems have primarily excitatory coupling, where even GABAergic synapses are excitatory. Many of these systems exhibit spontaneous episodes of activity that have been characterized through both experimental and computational studies. As development progress the neural system goes through many changes, including synaptic remodeling, intrinsic plasticity in the ion channel expression, and a transformation of GABAergic synapses from excitatory to inhibitory. What effect each of these, and other, changes have on the network behavior is hard to know from experimental studies since they all happen in parallel. One advantage of a computational approach is that one has the ability to study developmental changes in isolation. Here, we examine the effects of GABAergic synapse polarity change on the spontaneous activity of both a mean field and a neural network model that has both glutamatergic and GABAergic coupling, representative of a developing neural network. We find some intuitive behavioral changes as the GABAergic neurons go from excitatory to inhibitory, shared by both models, such as a decrease in the duration of episodes. We also find some paradoxical changes in the activity that are only present in the neural network model. In particular, we find that during early development the inter-episode durations become longer on average, while later in development they become shorter. In addressing this unexpected finding, we uncover a priming effect that is particularly important for a small subset of neurons, called the “intermediate neurons.” We characterize these neurons and demonstrate why they are crucial to episode initiation, and why the paradoxical behavioral change result from priming of these neurons. The study illustrates how even arguably the simplest of developmental changes that occurs in neural systems can present non-intuitive behaviors. It also makes predictions about neural network behavioral changes

A Quantum Implementation Model for Artificial Neural Networks

OpenAIRE

Ammar Daskin

2018-01-01

The learning process for multilayered neural networks with many nodes makes heavy demands on computational resources. In some neural network models, the learning formulas, such as the Widrow–Hoff formula, do not change the eigenvectors of the weight matrix while flatting the eigenvalues. In infinity, these iterative formulas result in terms formed by the principal components of the weight matrix, namely, the eigenvectors corresponding to the non-zero eigenvalues. In quantum computing, the pha...

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.

Application of neural network to CT

International Nuclear Information System (INIS)

Ma, Xiao-Feng; Takeda, Tatsuoki

1999-01-01

This paper presents a new method for two-dimensional image reconstruction by using a multilayer neural network. Multilayer neural networks are extensively investigated and practically applied to solution of various problems such as inverse problems or time series prediction problems. From learning an input-output mapping from a set of examples, neural networks can be regarded as synthesizing an approximation of multidimensional function (that is, solving the problem of hypersurface reconstruction, including smoothing and interpolation). From this viewpoint, neural networks are well suited to the solution of CT image reconstruction. Though a conventionally used object function of a neural network is composed of a sum of squared errors of the output data, we can define an object function composed of a sum of residue of an integral equation. By employing an appropriate line integral for this integral equation, we can construct a neural network that can be used for CT. We applied this method to some model problems and obtained satisfactory results. As it is not necessary to discretized the integral equation using this reconstruction method, therefore it is application to the problem of complicated geometrical shapes is also feasible. Moreover, in neural networks, interpolation is performed quite smoothly, as a result, inverse mapping can be achieved smoothly even in case of including experimental and numerical errors, However, use of conventional back propagation technique for optimization leads to an expensive computation cost. To overcome this drawback, 2nd order optimization methods or parallel computing will be applied in future. (J.P.N.)

Hardware for soft computing and soft computing for hardware

CERN Document Server

Nedjah, Nadia

2014-01-01

Single and Multi-Objective Evolutionary Computation (MOEA),  Genetic Algorithms (GAs), Artificial Neural Networks (ANNs), Fuzzy Controllers (FCs), Particle Swarm Optimization (PSO) and Ant colony Optimization (ACO) are becoming omnipresent in almost every intelligent system design. Unfortunately, the application of the majority of these techniques is complex and so requires a huge computational effort to yield useful and practical results. Therefore, dedicated hardware for evolutionary, neural and fuzzy computation is a key issue for designers. With the spread of reconfigurable hardware such as FPGAs, digital as well as analog hardware implementations of such computation become cost-effective. The idea behind this book is to offer a variety of hardware designs for soft computing techniques that can be embedded in any final product. Also, to introduce the successful application of soft computing technique to solve many hard problem encountered during the design of embedded hardware designs. Reconfigurable em...

A computational model incorporating neural stem cell dynamics reproduces glioma incidence across the lifespan in the human population.

Directory of Open Access Journals (Sweden)

Roman Bauer

Full Text Available Glioma is the most common form of primary brain tumor. Demographically, the risk of occurrence increases until old age. Here we present a novel computational model to reproduce the probability of glioma incidence across the lifespan. Previous mathematical models explaining glioma incidence are framed in a rather abstract way, and do not directly relate to empirical findings. To decrease this gap between theory and experimental observations, we incorporate recent data on cellular and molecular factors underlying gliomagenesis. Since evidence implicates the adult neural stem cell as the likely cell-of-origin of glioma, we have incorporated empirically-determined estimates of neural stem cell number, cell division rate, mutation rate and oncogenic potential into our model. We demonstrate that our model yields results which match actual demographic data in the human population. In particular, this model accounts for the observed peak incidence of glioma at approximately 80 years of age, without the need to assert differential susceptibility throughout the population. Overall, our model supports the hypothesis that glioma is caused by randomly-occurring oncogenic mutations within the neural stem cell population. Based on this model, we assess the influence of the (experimentally indicated decrease in the number of neural stem cells and increase of cell division rate during aging. Our model provides multiple testable predictions, and suggests that different temporal sequences of oncogenic mutations can lead to tumorigenesis. Finally, we conclude that four or five oncogenic mutations are sufficient for the formation of glioma.

A Quantum Implementation Model for Artificial Neural Networks

OpenAIRE

Daskin, Ammar

2016-01-01

The learning process for multi layered neural networks with many nodes makes heavy demands on computational resources. In some neural network models, the learning formulas, such as the Widrow-Hoff formula, do not change the eigenvectors of the weight matrix while flatting the eigenvalues. In infinity, this iterative formulas result in terms formed by the principal components of the weight matrix: i.e., the eigenvectors corresponding to the non-zero eigenvalues. In quantum computing, the phase...

Prediction of the Thermal Conductivity of Refrigerants by Computational Methods and Artificial Neural Network.

Science.gov (United States)

Ghaderi, Forouzan; Ghaderi, Amir H; Ghaderi, Noushin; Najafi, Bijan

2017-01-01

Background: The thermal conductivity of fluids can be calculated by several computational methods. However, these methods are reliable only at the confined levels of density, and there is no specific computational method for calculating thermal conductivity in the wide ranges of density. Methods: In this paper, two methods, an Artificial Neural Network (ANN) approach and a computational method established upon the Rainwater-Friend theory, were used to predict the value of thermal conductivity in all ranges of density. The thermal conductivity of six refrigerants, R12, R14, R32, R115, R143, and R152 was predicted by these methods and the effectiveness of models was specified and compared. Results: The results show that the computational method is a usable method for predicting thermal conductivity at low levels of density. However, the efficiency of this model is considerably reduced in the mid-range of density. It means that this model cannot be used at density levels which are higher than 6. On the other hand, the ANN approach is a reliable method for thermal conductivity prediction in all ranges of density. The best accuracy of ANN is achieved when the number of units is increased in the hidden layer. Conclusion: The results of the computational method indicate that the regular dependence between thermal conductivity and density at higher densities is eliminated. It can develop a nonlinear problem. Therefore, analytical approaches are not able to predict thermal conductivity in wide ranges of density. Instead, a nonlinear approach such as, ANN is a valuable method for this purpose.

Parallel consensual neural networks.

Science.gov (United States)

Benediktsson, J A; Sveinsson, J R; Ersoy, O K; Swain, P H

1997-01-01

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

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)

Iris Data Classification Using Quantum Neural Networks

International Nuclear Information System (INIS)

Sahni, Vishal; Patvardhan, C.

2006-01-01

Quantum computing is a novel paradigm that promises to be the future of computing. The performance of quantum algorithms has proved to be stunning. ANN within the context of classical computation has been used for approximation and classification tasks with some success. This paper presents an idea of quantum neural networks along with the training algorithm and its convergence property. It synergizes the unique properties of quantum bits or qubits with the various techniques in vogue in neural networks. An example application of Fisher's Iris data set, a benchmark classification problem has also been presented. The results obtained amply demonstrate the classification capabilities of the quantum neuron and give an idea of their promising capabilities

22nd Italian Workshop on Neural Nets

CERN Document Server

Bassis, Simone; Esposito, Anna; Morabito, Francesco

2013-01-01

This volume collects a selection of contributions which has been presented at the 22nd Italian Workshop on Neural Networks, the yearly meeting of the Italian Society for Neural Networks (SIREN). The conference was held in Italy, Vietri sul Mare (Salerno), during May 17-19, 2012. The annual meeting of SIREN is sponsored by International Neural Network Society (INNS), European Neural Network Society (ENNS) and IEEE Computational Intelligence Society (CIS). The book – as well as the workshop-  is organized in three main components, two special sessions and a group of regular sessions featuring different aspects and point of views of artificial neural networks and natural intelligence, also including applications of present compelling interest.

Event- and Time-Driven Techniques Using Parallel CPU-GPU Co-processing for Spiking Neural Networks.

Science.gov (United States)

Naveros, Francisco; Garrido, Jesus A; Carrillo, Richard R; Ros, Eduardo; Luque, Niceto R

2017-01-01

Modeling and simulating the neural structures which make up our central neural system is instrumental for deciphering the computational neural cues beneath. Higher levels of biological plausibility usually impose higher levels of complexity in mathematical modeling, from neural to behavioral levels. This paper focuses on overcoming the simulation problems (accuracy and performance) derived from using higher levels of mathematical complexity at a neural level. This study proposes different techniques for simulating neural models that hold incremental levels of mathematical complexity: leaky integrate-and-fire (LIF), adaptive exponential integrate-and-fire (AdEx), and Hodgkin-Huxley (HH) neural models (ranged from low to high neural complexity). The studied techniques are classified into two main families depending on how the neural-model dynamic evaluation is computed: the event-driven or the time-driven families. Whilst event-driven techniques pre-compile and store the neural dynamics within look-up tables, time-driven techniques compute the neural dynamics iteratively during the simulation time. We propose two modifications for the event-driven family: a look-up table recombination to better cope with the incremental neural complexity together with a better handling of the synchronous input activity. Regarding the time-driven family, we propose a modification in computing the neural dynamics: the bi-fixed-step integration method. This method automatically adjusts the simulation step size to better cope with the stiffness of the neural model dynamics running in CPU platforms. One version of this method is also implemented for hybrid CPU-GPU platforms. Finally, we analyze how the performance and accuracy of these modifications evolve with increasing levels of neural complexity. We also demonstrate how the proposed modifications which constitute the main contribution of this study systematically outperform the traditional event- and time-driven techniques under

Neural components of altruistic punishment

Directory of Open Access Journals (Sweden)

Emily eDu

2015-02-01

Full Text Available Altruistic punishment, which occurs when an individual incurs a cost to punish in response to unfairness or a norm violation, may play a role in perpetuating cooperation. The neural correlates underlying costly punishment have only recently begun to be explored. Here we review the current state of research on the neural basis of altruism from the perspectives of costly punishment, emphasizing the importance of characterizing elementary neural processes underlying a decision to punish. In particular, we emphasize three cognitive processes that contribute to the decision to altruistically punish in most scenarios: inequity aversion, cost-benefit calculation, and social reference frame to distinguish self from others. Overall, we argue for the importance of understanding the neural correlates of altruistic punishment with respect to the core computations necessary to achieve a decision to punish.

Pulsed neural networks consisting of single-flux-quantum spiking neurons

International Nuclear Information System (INIS)

Hirose, T.; Asai, T.; Amemiya, Y.

2007-01-01

An inhibitory pulsed neural network was developed for brain-like information processing, by using single-flux-quantum (SFQ) circuits. It consists of spiking neuron devices that are coupled to each other through all-to-all inhibitory connections. The network selects neural activity. The operation of the neural network was confirmed by computer simulation. SFQ neuron devices can imitate the operation of the inhibition phenomenon of neural networks

Computations Underlying Social Hierarchy Learning: Distinct Neural Mechanisms for Updating and Representing Self-Relevant Information.

Science.gov (United States)

Kumaran, Dharshan; Banino, Andrea; Blundell, Charles; Hassabis, Demis; Dayan, Peter

2016-12-07

Knowledge about social hierarchies organizes human behavior, yet we understand little about the underlying computations. Here we show that a Bayesian inference scheme, which tracks the power of individuals, better captures behavioral and neural data compared with a reinforcement learning model inspired by rating systems used in games such as chess. We provide evidence that the medial prefrontal cortex (MPFC) selectively mediates the updating of knowledge about one's own hierarchy, as opposed to that of another individual, a process that underpinned successful performance and involved functional interactions with the amygdala and hippocampus. In contrast, we observed domain-general coding of rank in the amygdala and hippocampus, even when the task did not require it. Our findings reveal the computations underlying a core aspect of social cognition and provide new evidence that self-relevant information may indeed be afforded a unique representational status in the brain. Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.

Utility of the UCSD Performance-based Skills Assessment-Brief Japanese version: discriminative ability and relation to neurocognition

Directory of Open Access Journals (Sweden)

Chika Sumiyoshi

2014-09-01

Full Text Available The UCSD Performance-based Skills Assessment Brief (the UPSA-B has been widely used for evaluating functional capacity in patients with schizophrenia. The utility of the battery in a wide range of cultural contexts has been of concern among developers. The current study investigated the validity of the Japanese version of the UPSA-B as a measure of functional capacity and as a co-primary for neurocognion. Sixty-four Japanese patients with schizophrenia and 83 healthy adults entered the study. The Japanese version of the UPSA-B (UPSA-B Japanese version and the MATRICS Cognitive Consensus Battery Japanese version (MCCB Japanese version were administered. Normal controls performed significantly better than patients, with large effect sizes for the Total and the subscale scores of the UPSA-B. Receiver Operating Characteristic (ROC curve analysis revealed that the optimal cut-off point for the UPSA-B Total score was estimated at around 80. The UPSA-B Total score was significantly correlated with the MCCB Composite score and several domain scores, indicating the relationship between this co-primary measure and overall cognitive functioning in Japanese patients with schizophrenia. The results obtained here suggest that the UPSA-B Japanese version is an effective tool for evaluating disturbances of daily-living skills linked to cognitive functioning in schizophrenia, providing an identifiable cut-off point and relationships to neurocognition. Further research is warranted to evaluate the psychometrical properties and response to treatment of the Japanese version of the UPSA-B.

NeuroMEMS: Neural Probe Microtechnologies

Directory of Open Access Journals (Sweden)

Sam Musallam

2008-10-01

Full Text Available Neural probe technologies have already had a significant positive effect on our understanding of the brain by revealing the functioning of networks of biological neurons. Probes are implanted in different areas of the brain to record and/or stimulate specific sites in the brain. Neural probes are currently used in many clinical settings for diagnosis of brain diseases such as seizers, epilepsy, migraine, Alzheimer’s, and dementia. We find these devices assisting paralyzed patients by allowing them to operate computers or robots using their neural activity. In recent years, probe technologies were assisted by rapid advancements in microfabrication and microelectronic technologies and thus are enabling highly functional and robust neural probes which are opening new and exciting avenues in neural sciences and brain machine interfaces. With a wide variety of probes that have been designed, fabricated, and tested to date, this review aims to provide an overview of the advances and recent progress in the microfabrication techniques of neural probes. In addition, we aim to highlight the challenges faced in developing and implementing ultralong multi-site recording probes that are needed to monitor neural activity from deeper regions in the brain. Finally, we review techniques that can improve the biocompatibility of the neural probes to minimize the immune response and encourage neural growth around the electrodes for long term implantation studies.

Livermore Big Artificial Neural Network Toolkit

Energy Technology Data Exchange (ETDEWEB)

2016-07-01

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Design of a computation tool for neutron spectrometry and dosimetry through evolutionary neural networks

International Nuclear Information System (INIS)

Ortiz R, J. M.; Vega C, H. R.; Martinez B, M. R.; Gallego, E.

2009-10-01

The neutron dosimetry is one of the most complicated tasks of radiation protection, due to it is a complex technique and highly dependent of neutron energy. One of the first devices used to perform neutron spectrometry is the system known as spectrometric system of Bonner spheres, that continuous being one of spectrometers most commonly used. This system has disadvantages such as: the components weight, the low resolution of spectrum, long and drawn out procedure for the spectra reconstruction, which require an expert user in system management, the need of use a reconstruction code as BUNKIE, SAND, etc., which are based on an iterative reconstruction algorithm and whose greatest inconvenience is that for the spectrum reconstruction, are needed to provide to system and initial spectrum as close as possible to the desired spectrum get. Consequently, researchers have mentioned the need to developed alternative measurement techniques to improve existing monitoring systems for workers. Among these alternative techniques have been reported several reconstruction procedures based on artificial intelligence techniques such as genetic algorithms, artificial neural networks and hybrid systems of evolutionary artificial neural networks using genetic algorithms. However, the use of these techniques in the nuclear science area is not free of problems, so it has been suggested that more research is conducted in such a way as to solve these disadvantages. Because they are emerging technologies, there are no tools for the results analysis, so in this paper we present first the design of a computation tool that allow to analyze the neutron spectra and equivalent doses, obtained through the hybrid technology of neural networks and genetic algorithms. This tool provides an user graphical environment, friendly, intuitive and easy of operate. The speed of program operation is high, executing the analysis in a few seconds, so it may storage and or print the obtained information for

Parameter estimation using compensatory neural networks

Indian Academy of Sciences (India)

of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron ..... Engelbrecht A P, Cloete I, Geldenhuys J, Zurada J M 1995 Automatic scaling using gamma learning for feedforward neural networks. From natural to artificial computing.

Hierarchical modular granular neural networks with fuzzy aggregation

CERN Document Server

Sanchez, Daniela

2016-01-01

In this book, a new method for hybrid intelligent systems is proposed. The proposed method is based on a granular computing approach applied in two levels. The techniques used and combined in the proposed method are modular neural networks (MNNs) with a Granular Computing (GrC) approach, thus resulting in a new concept of MNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL) and hierarchical genetic algorithms (HGAs) are techniques used in this research work to improve results. These techniques are chosen because in other works have demonstrated to be a good option, and in the case of MNNs and HGAs, these techniques allow to improve the results obtained than with their conventional versions; respectively artificial neural networks and genetic algorithms.

Dynamic decomposition of spatiotemporal neural signals.

Directory of Open Access Journals (Sweden)

Luca Ambrogioni

2017-05-01

Full Text Available Neural signals are characterized by rich temporal and spatiotemporal dynamics that reflect the organization of cortical networks. Theoretical research has shown how neural networks can operate at different dynamic ranges that correspond to specific types of information processing. Here we present a data analysis framework that uses a linearized model of these dynamic states in order to decompose the measured neural signal into a series of components that capture both rhythmic and non-rhythmic neural activity. The method is based on stochastic differential equations and Gaussian process regression. Through computer simulations and analysis of magnetoencephalographic data, we demonstrate the efficacy of the method in identifying meaningful modulations of oscillatory signals corrupted by structured temporal and spatiotemporal noise. These results suggest that the method is particularly suitable for the analysis and interpretation of complex temporal and spatiotemporal neural signals.

Computational vision

CERN Document Server

Wechsler, Harry

1990-01-01

The book is suitable for advanced courses in computer vision and image processing. In addition to providing an overall view of computational vision, it contains extensive material on topics that are not usually covered in computer vision texts (including parallel distributed processing and neural networks) and considers many real applications.

Designing neural networks that process mean values of random variables

International Nuclear Information System (INIS)

Barber, Michael J.; Clark, John W.

2014-01-01

We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. - Highlights: • High-level neural computations are specified by Bayesian belief networks of random variables. • Probability densities of random variables are encoded in activities of populations of neurons. • Top-down algorithm generates specific neural network implementation of given computation. • Resulting “neural belief networks” process mean values of random variables. • Such networks pool multiple sources of evidence and deal properly with inconsistent evidence

Designing neural networks that process mean values of random variables

Energy Technology Data Exchange (ETDEWEB)

Barber, Michael J. [AIT Austrian Institute of Technology, Innovation Systems Department, 1220 Vienna (Austria); Clark, John W. [Department of Physics and McDonnell Center for the Space Sciences, Washington University, St. Louis, MO 63130 (United States); Centro de Ciências Matemáticas, Universidade de Madeira, 9000-390 Funchal (Portugal)

2014-06-13

We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. - Highlights: • High-level neural computations are specified by Bayesian belief networks of random variables. • Probability densities of random variables are encoded in activities of populations of neurons. • Top-down algorithm generates specific neural network implementation of given computation. • Resulting “neural belief networks” process mean values of random variables. • Such networks pool multiple sources of evidence and deal properly with inconsistent evidence.

Optimal Brain Surgeon on Artificial Neural Networks in

DEFF Research Database (Denmark)

Christiansen, Niels Hørbye; Job, Jonas Hultmann; Klyver, Katrine

2012-01-01

It is shown how the procedure know as optimal brain surgeon can be used to trim and optimize artificial neural networks in nonlinear structural dynamics. Beside optimizing the neural network, and thereby minimizing computational cost in simulation, the surgery procedure can also serve as a quick...

Neurosecurity: security and privacy for neural devices.

Science.gov (United States)

Denning, Tamara; Matsuoka, Yoky; Kohno, Tadayoshi

2009-07-01

An increasing number of neural implantable devices will become available in the near future due to advances in neural engineering. This discipline holds the potential to improve many patients' lives dramatically by offering improved-and in some cases entirely new-forms of rehabilitation for conditions ranging from missing limbs to degenerative cognitive diseases. The use of standard engineering practices, medical trials, and neuroethical evaluations during the design process can create systems that are safe and that follow ethical guidelines; unfortunately, none of these disciplines currently ensure that neural devices are robust against adversarial entities trying to exploit these devices to alter, block, or eavesdrop on neural signals. The authors define "neurosecurity"-a version of computer science security principles and methods applied to neural engineering-and discuss why neurosecurity should be a critical consideration in the design of future neural devices.

Topology influences performance in the associative memory neural networks

International Nuclear Information System (INIS)

Lu Jianquan; He Juan; Cao Jinde; Gao Zhiqiang

2006-01-01

To explore how topology affects performance within Hopfield-type associative memory neural networks (AMNNs), we studied the computational performance of the neural networks with regular lattice, random, small-world, and scale-free structures. In this Letter, we found that the memory performance of neural networks obtained through asynchronous updating from 'larger' nodes to 'smaller' nodes are better than asynchronous updating in random order, especially for the scale-free topology. The computational performance of associative memory neural networks linked by the above-mentioned network topologies with the same amounts of nodes (neurons) and edges (synapses) were studied respectively. Along with topologies becoming more random and less locally disordered, we will see that the performance of associative memory neural network is quite improved. By comparing, we show that the regular lattice and random network form two extremes in terms of patterns stability and retrievability. For a network, its patterns stability and retrievability can be largely enhanced by adding a random component or some shortcuts to its structured component. According to the conclusions of this Letter, we can design the associative memory neural networks with high performance and minimal interconnect requirements

Advances in Artificial Neural Networks - Methodological Development and Application

Science.gov (United States)

Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...

Data systems and computer science: Neural networks base R/T program overview

Science.gov (United States)

Gulati, Sandeep

1991-01-01

The research base, in the U.S. and abroad, for the development of neural network technology is discussed. The technical objectives are to develop and demonstrate adaptive, neural information processing concepts. The leveraging of external funding is also discussed.

Enhancing neural-network performance via assortativity

International Nuclear Information System (INIS)

Franciscis, Sebastiano de; Johnson, Samuel; Torres, Joaquin J.

2011-01-01

The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations - assortativity - on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.

Abstract computation in schizophrenia detection through artificial neural network based systems.

Science.gov (United States)

Cardoso, L; Marins, F; Magalhães, R; Marins, N; Oliveira, T; Vicente, H; Abelha, A; Machado, J; Neves, J

2015-01-01

Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.

Classification of dried vegetables using computer image analysis and artificial neural networks

Science.gov (United States)

Koszela, K.; Łukomski, M.; Mueller, W.; Górna, K.; Okoń, P.; Boniecki, P.; Zaborowicz, M.; Wojcieszak, D.

2017-07-01

In the recent years, there has been a continuously increasing demand for vegetables and dried vegetables. This trend affects the growth of the dehydration industry in Poland helping to exploit excess production. More and more often dried vegetables are used in various sectors of the food industry, both due to their high nutritional qualities and changes in consumers' food preferences. As we observe an increase in consumer awareness regarding a healthy lifestyle and a boom in health food, there is also an increase in the consumption of such food, which means that the production and crop area can increase further. Among the dried vegetables, dried carrots play a strategic role due to their wide application range and high nutritional value. They contain high concentrations of carotene and sugar which is present in the form of crystals. Carrots are also the vegetables which are most often subjected to a wide range of dehydration processes; this makes it difficult to perform a reliable qualitative assessment and classification of this dried product. The many qualitative properties of dried carrots determining their positive or negative quality assessment include colour and shape. The aim of the research was to develop and implement the model of a computer system for the recognition and classification of freeze-dried, convection-dried and microwave vacuum dried products using the methods of computer image analysis and artificial neural networks.

Comparisons of a Quantum Annealing and Classical Computer Neural Net Approach for Inferring Global Annual CO2 Fluxes over Land

Science.gov (United States)

Halem, M.; Radov, A.; Singh, D.

2017-12-01

Investigations of mid to high latitude atmospheric CO2 show growing amplitudes in seasonal variations over the past several decades. Recent high-resolution satellite measurements of CO2 concentration are now available for three years from the Orbiting Carbon Observatory-2. The Atmospheric Radiation Measurement (ARM) program of DOE has been making long-term CO2-flux measurements (in addition to CO2 concentration and an array of other meteorological quantities) at several towers and mobile sites located around the globe at half-hour frequencies. Recent papers have shown CO2 fluxes inferred by assimilating CO2 observations into ecosystem models are largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks. Thus, new approaches for calculating CO2-flux for assimilation into land surface models are necessary for improving the prediction of annual carbon uptake. In this study, we calculate and compare the predicted CO2 fluxes results employing a Feed Forward Backward Propagation Neural Network model on two architectures, (i) an IBM Minsky Computer node and (ii) a hybrid version of the ARC D-Wave quantum annealing computer. We compare the neural net results of predictions of CO2 flux from ARM station data for three different DOE ecosystem sites; an arid plains near Oklahoma City, a northern arctic site at Barrows AL, and a tropical rainforest site in the Amazon. Training times and predictive results for the calculating annual CO2 flux for the two architectures for each of the three sites are presented. Comparative results of predictions as measured by RMSE and MAE are discussed. Plots and correlations of observed vs predicted CO2 flux are also presented for all three sites. We show the estimated training times for quantum and classical calculations when extended to calculating global annual Carbon Uptake over land. We also

2D neural hardware versus 3D biological ones

Energy Technology Data Exchange (ETDEWEB)

Beiu, V.

1998-12-31

This paper will present important limitations of hardware neural nets as opposed to biological neural nets (i.e. the real ones). The author starts by discussing neural structures and their biological inspirations, while mentioning the simplifications leading to artificial neural nets. Going further, the focus will be on hardware constraints. The author will present recent results for three different alternatives of implementing neural networks: digital, threshold gate, and analog, while the area and the delay will be related to neurons' fan-in and weights' precision. Based on all of these, it will be shown why hardware implementations cannot cope with their biological inspiration with respect to their power of computation: the mapping onto silicon lacking the third dimension of biological nets. This translates into reduced fan-in, and leads to reduced precision. The main conclusion is that one is faced with the following alternatives: (1) try to cope with the limitations imposed by silicon, by speeding up the computation of the elementary silicon neurons; (2) investigate solutions which would allow one to use the third dimension, e.g. using optical interconnections.

Neural networks: Application to medical imaging

Science.gov (United States)

Clarke, Laurence P.

1994-01-01

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

Computational models of neuromodulation.

Science.gov (United States)

Fellous, J M; Linster, C

1998-05-15

Computational modeling of neural substrates provides an excellent theoretical framework for the understanding of the computational roles of neuromodulation. In this review, we illustrate, with a large number of modeling studies, the specific computations performed by neuromodulation in the context of various neural models of invertebrate and vertebrate preparations. We base our characterization of neuromodulations on their computational and functional roles rather than on anatomical or chemical criteria. We review the main framework in which neuromodulation has been studied theoretically (central pattern generation and oscillations, sensory processing, memory and information integration). Finally, we present a detailed mathematical overview of how neuromodulation has been implemented at the single cell and network levels in modeling studies. Overall, neuromodulation is found to increase and control computational complexity.

Short-Term Load Forecasting Model Based on Quantum Elman Neural Networks

Directory of Open Access Journals (Sweden)

Zhisheng Zhang

2016-01-01

Full Text Available Short-term load forecasting model based on quantum Elman neural networks was constructed in this paper. The quantum computation and Elman feedback mechanism were integrated into quantum Elman neural networks. Quantum computation can effectively improve the approximation capability and the information processing ability of the neural networks. Quantum Elman neural networks have not only the feedforward connection but also the feedback connection. The feedback connection between the hidden nodes and the context nodes belongs to the state feedback in the internal system, which has formed specific dynamic memory performance. Phase space reconstruction theory is the theoretical basis of constructing the forecasting model. The training samples are formed by means of K-nearest neighbor approach. Through the example simulation, the testing results show that the model based on quantum Elman neural networks is better than the model based on the quantum feedforward neural network, the model based on the conventional Elman neural network, and the model based on the conventional feedforward neural network. So the proposed model can effectively improve the prediction accuracy. The research in the paper makes a theoretical foundation for the practical engineering application of the short-term load forecasting model based on quantum Elman neural networks.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

Science.gov (United States)

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

Science.gov (United States)

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

Neural dynamics in reconfigurable silicon.

Science.gov (United States)

Basu, A; Ramakrishnan, S; Petre, C; Koziol, S; Brink, S; Hasler, P E

2010-10-01

A neuromorphic analog chip is presented that is capable of implementing massively parallel neural computations while retaining the programmability of digital systems. We show measurements from neurons with Hopf bifurcations and integrate and fire neurons, excitatory and inhibitory synapses, passive dendrite cables, coupled spiking neurons, and central pattern generators implemented on the chip. This chip provides a platform for not only simulating detailed neuron dynamics but also uses the same to interface with actual cells in applications such as a dynamic clamp. There are 28 computational analog blocks (CAB), each consisting of ion channels with tunable parameters, synapses, winner-take-all elements, current sources, transconductance amplifiers, and capacitors. There are four other CABs which have programmable bias generators. The programmability is achieved using floating gate transistors with on-chip programming control. The switch matrix for interconnecting the components in CABs also consists of floating-gate transistors. Emphasis is placed on replicating the detailed dynamics of computational neural models. Massive computational area efficiency is obtained by using the reconfigurable interconnect as synaptic weights, resulting in more than 50 000 possible 9-b accurate synapses in 9 mm(2).

High level cognitive information processing in neural networks

Science.gov (United States)

Barnden, John A.; Fields, Christopher A.

1992-01-01

Two related research efforts were addressed: (1) high-level connectionist cognitive modeling; and (2) local neural circuit modeling. The goals of the first effort were to develop connectionist models of high-level cognitive processes such as problem solving or natural language understanding, and to understand the computational requirements of such models. The goals of the second effort were to develop biologically-realistic model of local neural circuits, and to understand the computational behavior of such models. In keeping with the nature of NASA's Innovative Research Program, all the work conducted under the grant was highly innovative. For instance, the following ideas, all summarized, are contributions to the study of connectionist/neural networks: (1) the temporal-winner-take-all, relative-position encoding, and pattern-similarity association techniques; (2) the importation of logical combinators into connection; (3) the use of analogy-based reasoning as a bridge across the gap between the traditional symbolic paradigm and the connectionist paradigm; and (4) the application of connectionism to the domain of belief representation/reasoning. The work on local neural circuit modeling also departs significantly from the work of related researchers. In particular, its concentration on low-level neural phenomena that could support high-level cognitive processing is unusual within the area of biological local circuit modeling, and also serves to expand the horizons of the artificial neural net field.

The UCSD HIRES/Keck I Damped Lyα Abundance Database. II. The Implications

Science.gov (United States)

Prochaska, Jason X.; Wolfe, Arthur M.

2002-02-01

of the damped systems and may pose a great challenge to the protogalactic clump scenarios favored by hierarchical galaxy formation. http://kingpin.ucsd.edu/~hiresdla.

Non-linear feedback neural networks VLSI implementations and applications

CERN Document Server

Ansari, Mohd Samar

2014-01-01

This book aims to present a viable alternative to the Hopfield Neural Network (HNN) model for analog computation. It is well known that the standard HNN suffers from problems of convergence to local minima, and requirement of a large number of neurons and synaptic weights. Therefore, improved solutions are needed. The non-linear synapse neural network (NoSyNN) is one such possibility and is discussed in detail in this book. This book also discusses the applications in computationally intensive tasks like graph coloring, ranking, and linear as well as quadratic programming. The material in the book is useful to students, researchers and academician working in the area of analog computation.

Developing Scene Understanding Neural Software for Realistic Autonomous Outdoor Missions

Science.gov (United States)

2017-09-01

computer using a single graphics processing unit (GPU). To the best of our knowledge, an implementation of the open-source Python -based AlexNet CNN on...1. Introduction Neurons in the brain enable us to understand scenes by assessing the spatial, temporal, and feature relations of objects in the...effort to use computer neural networks to augment human neural intelligence to improve our scene understanding (Krizhevsky et al. 2012; Zhou et al

Mass reconstruction with a neural network

International Nuclear Information System (INIS)

Loennblad, L.; Peterson, C.; Roegnvaldsson, T.

1992-01-01

A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qanti q, where W-bosons are produced in panti p reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using 'intelligent' variables in instances when the amount of training instances is limited. (orig.)

Neural Computations for Biosonar Imaging in the Big Brown Bat

Science.gov (United States)

Saillant, Prestor Augusto

1995-11-01

The study of the intimate relationship between space and time has taken many forms, ranging from the Theory of Relativity down to the problem of avoiding traffic jams. However, nowhere has this relationship been more fully developed and exploited than in dolphins and bats, which have the ability to utilize biosonar. This thesis describes research on the behavioral and computational basis of echolocation carried out in order to explore the neural mechanisms which may account for the space-time constructs which are of psychological importance to the big brown bat. The SCAT (Spectrogram Correlation and Transformation) computational model was developed to provide a framework for understanding the computational requirements of FM echolocation as determined from psychophysical experiments (i.e., high resolution imaging) and neurobiological constraints (Saillant et al., 1993). The second part of the thesis consisted in developing a new behavioral paradigm for simultaneously studying acoustic behavior and flight behavior of big brown bats in pursuit of stationary or moving targets. In the third part of the thesis a complete acoustic "artificial bat" was constructed, making use of the SCAT process. The development of the artificial bat allowed us to begin experimentation with real world echoes from various targets, in order to gain a better appreciation for the additional complexities and sources of information encountered by bats in flight. Finally, the continued development of the SCAT model has allowed a deeper understanding of the phenomenon of "time expansion" and of the phenomenon of phase sensitivity in the ultrasonic range. Time expansion, first predicted through the use of the SCAT model, and later found in auditory local evoked potential recordings, opens up a new realm of information processing and representation in the brain which as of yet has not been considered. It seems possible, from the work in the auditory system, that time expansion may provide a novel

Application of two neural network paradigms to the study of voluntary employee turnover.

Science.gov (United States)

Somers, M J

1999-04-01

Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

Deep Gate Recurrent Neural Network

Science.gov (United States)

2016-11-22

and Fred Cummins. Learning to forget: Continual prediction with lstm . Neural computation, 12(10):2451–2471, 2000. Alex Graves. Generating sequences...DSGU) and Simple Gated Unit (SGU), which are structures for learning long-term dependencies. Compared to traditional Long Short-Term Memory ( LSTM ) and...Gated Recurrent Unit (GRU), both structures require fewer parameters and less computation time in sequence classification tasks. Unlike GRU and LSTM

Classes of feedforward neural networks and their circuit complexity

NARCIS (Netherlands)

Shawe-Taylor, John S.; Anthony, Martin H.G.; Kern, Walter

1992-01-01

This paper aims to place neural networks in the context of boolean circuit complexity. We define appropriate classes of feedforward neural networks with specified fan-in, accuracy of computation and depth and using techniques of communication complexity proceed to show that the classes fit into a

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

An Algebra-Based Introductory Computational Neuroscience Course with Lab.

Science.gov (United States)

Fink, Christian G

2017-01-01

A course in computational neuroscience has been developed at Ohio Wesleyan University which requires no previous experience with calculus or computer programming, and which exposes students to theoretical models of neural information processing and techniques for analyzing neural data. The exploration of theoretical models of neural processes is conducted in the classroom portion of the course, while data analysis techniques are covered in lab. Students learn to program in MATLAB and are offered the opportunity to conclude the course with a final project in which they explore a topic of their choice within computational neuroscience. Results from a questionnaire administered at the beginning and end of the course indicate significant gains in student facility with core concepts in computational neuroscience, as well as with analysis techniques applied to neural data.

Neural network modeling for near wall turbulent flow

International Nuclear Information System (INIS)

Milano, Michele; Koumoutsakos, Petros

2002-01-01

A neural network methodology is developed in order to reconstruct the near wall field in a turbulent flow by exploiting flow fields provided by direct numerical simulations. The results obtained from the neural network methodology are compared with the results obtained from prediction and reconstruction using proper orthogonal decomposition (POD). Using the property that the POD is equivalent to a specific linear neural network, a nonlinear neural network extension is presented. It is shown that for a relatively small additional computational cost nonlinear neural networks provide us with improved reconstruction and prediction capabilities for the near wall velocity fields. Based on these results advantages and drawbacks of both approaches are discussed with an outlook toward the development of near wall models for turbulence modeling and control

Anomaly detection in an automated safeguards system using neural networks

International Nuclear Information System (INIS)

Whiteson, R.; Howell, J.A.

1992-01-01

An automated safeguards system must be able to detect an anomalous event, identify the nature of the event, and recommend a corrective action. Neural networks represent a new way of thinking about basic computational mechanisms for intelligent information processing. In this paper, we discuss the issues involved in applying a neural network model to the first step of this process: anomaly detection in materials accounting systems. We extend our previous model to a 3-tank problem and compare different neural network architectures and algorithms. We evaluate the computational difficulties in training neural networks and explore how certain design principles affect the problems. The issues involved in building a neural network architecture include how the information flows, how the network is trained, how the neurons in a network are connected, how the neurons process information, and how the connections between neurons are modified. Our approach is based on the demonstrated ability of neural networks to model complex, nonlinear, real-time processes. By modeling the normal behavior of the processes, we can predict how a system should be behaving and, therefore, detect when an abnormality occurs

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...

Runoff Modelling in Urban Storm Drainage by Neural Networks

DEFF Research Database (Denmark)

Rasmussen, Michael R.; Brorsen, Michael; Schaarup-Jensen, Kjeld

1995-01-01

A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural...... network is used to compute flow or water level at selected points in the sewer system, and to forecast the flow from a small residential area. The main advantages of the neural network are the build-in self calibration procedure and high speed performance, but the neural network cannot be used to extract...... knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model....

Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets.

Science.gov (United States)

Sengupta, Abhronil; Shim, Yong; Roy, Kaushik

2016-12-01

Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking the neuron, or the synapse functionality. While memristive devices have been proposed to emulate biological synapses, spintronic devices have proved to be efficient at performing the thresholding operation of the neuron at ultra-low currents. In this work, we propose an All-Spin Artificial Neural Network where a single spintronic device acts as the basic building block of the system. The device offers a direct mapping to synapse and neuron functionalities in the brain while inter-layer network communication is accomplished via CMOS transistors. To the best of our knowledge, this is the first demonstration of a neural architecture where a single nanoelectronic device is able to mimic both neurons and synapses. The ultra-low voltage operation of low resistance magneto-metallic neurons enables the low-voltage operation of the array of spintronic synapses, thereby leading to ultra-low power neural architectures. Device-level simulations, calibrated to experimental results, was used to drive the circuit and system level simulations of the neural network for a standard pattern recognition problem. Simulation studies indicate energy savings by  ∼  100× in comparison to a corresponding digital/analog CMOS neuron implementation.

Implementing Signature Neural Networks with Spiking Neurons.

Science.gov (United States)

Carrillo-Medina, José Luis; Latorre, Roberto

2016-01-01

Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm-i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data-to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence

Artificial Neural Networks For Hadron Hadron Cross-sections

International Nuclear Information System (INIS)

ELMashad, M.; ELBakry, M.Y.; Tantawy, M.; Habashy, D.M.

2011-01-01

In recent years artificial neural networks (ANN ) have emerged as a mature and viable framework with many applications in various areas. Artificial neural networks theory is sometimes used to refer to a branch of computational science that uses neural networks as models to either simulate or analyze complex phenomena and/or study the principles of operation of neural networks analytically. In this work a model of hadron- hadron collision using the ANN technique is present, the hadron- hadron based ANN model calculates the cross sections of hadron- hadron collision. The results amply demonstrate the feasibility of such new technique in extracting the collision features and prove its effectiveness

Dynamical networks: Finding, measuring, and tracking neural population activity using network science

Directory of Open Access Journals (Sweden)

Mark D. Humphries

2017-12-01

Full Text Available Systems neuroscience is in a headlong rush to record from as many neurons at the same time as possible. As the brain computes and codes using neuron populations, it is hoped these data will uncover the fundamentals of neural computation. But with hundreds, thousands, or more simultaneously recorded neurons come the inescapable problems of visualizing, describing, and quantifying their interactions. Here I argue that network science provides a set of scalable, analytical tools that already solve these problems. By treating neurons as nodes and their interactions as links, a single network can visualize and describe an arbitrarily large recording. I show that with this description we can quantify the effects of manipulating a neural circuit, track changes in population dynamics over time, and quantitatively define theoretical concepts of neural populations such as cell assemblies. Using network science as a core part of analyzing population recordings will thus provide both qualitative and quantitative advances to our understanding of neural computation.

Sensitivity analysis of linear programming problem through a recurrent neural network

Science.gov (United States)

Das, Raja

2017-11-01

In this paper we study the recurrent neural network for solving linear programming problems. To achieve optimality in accuracy and also in computational effort, an algorithm is presented. We investigate the sensitivity analysis of linear programming problem through the neural network. A detailed example is also presented to demonstrate the performance of the recurrent neural network.

The neural processing of voluntary completed, real and virtual violent and nonviolent computer game scenarios displaying predefined actions in gamers and nongamers.

Science.gov (United States)

Regenbogen, Christina; Herrmann, Manfred; Fehr, Thorsten

2010-01-01

Studies investigating the effects of violent computer and video game playing have resulted in heterogeneous outcomes. It has been assumed that there is a decreased ability to differentiate between virtuality and reality in people that play these games intensively. FMRI data of a group of young males with (gamers) and without (controls) a history of long-term violent computer game playing experience were obtained during the presentation of computer game and realistic video sequences. In gamers the processing of real violence in contrast to nonviolence produced activation clusters in right inferior frontal, left lingual and superior temporal brain regions. Virtual violence activated a network comprising bilateral inferior frontal, occipital, postcentral, right middle temporal, and left fusiform regions. Control participants showed extended left frontal, insula and superior frontal activations during the processing of real, and posterior activations during the processing of virtual violent scenarios. The data suggest that the ability to differentiate automatically between real and virtual violence has not been diminished by a long-term history of violent video game play, nor have gamers' neural responses to real violence in particular been subject to desensitization processes. However, analyses of individual data indicated that group-related analyses reflect only a small part of actual individual different neural network involvement, suggesting that the consideration of individual learning history is sufficient for the present discussion.

Applications of neural network to numerical analyses

International Nuclear Information System (INIS)

Takeda, Tatsuoki; Fukuhara, Makoto; Ma, Xiao-Feng; Liaqat, Ali

1999-01-01

Applications of a multi-layer neural network to numerical analyses are described. We are mainly concerned with the computed tomography and the solution of differential equations. In both cases as the objective functions for the training process of the neural network we employed residuals of the integral equation or the differential equations. This is different from the conventional neural network training where sum of the squared errors of the output values is adopted as the objective function. For model problems both the methods gave satisfactory results and the methods are considered promising for some kind of problems. (author)

Energy efficiency optimisation for distillation column using artificial neural network models

International Nuclear Information System (INIS)

Osuolale, Funmilayo N.; Zhang, Jie

2016-01-01

This paper presents a neural network based strategy for the modelling and optimisation of energy efficiency in distillation columns incorporating the second law of thermodynamics. Real-time optimisation of distillation columns based on mechanistic models is often infeasible due to the effort in model development and the large computation effort associated with mechanistic model computation. This issue can be addressed by using neural network models which can be quickly developed from process operation data. The computation time in neural network model evaluation is very short making them ideal for real-time optimisation. Bootstrap aggregated neural networks are used in this study for enhanced model accuracy and reliability. Aspen HYSYS is used for the simulation of the distillation systems. Neural network models for exergy efficiency and product compositions are developed from simulated process operation data and are used to maximise exergy efficiency while satisfying products qualities constraints. Applications to binary systems of methanol-water and benzene-toluene separations culminate in a reduction of utility consumption of 8.2% and 28.2% respectively. Application to multi-component separation columns also demonstrate the effectiveness of the proposed method with a 32.4% improvement in the exergy efficiency. - Highlights: • Neural networks can accurately model exergy efficiency in distillation columns. • Bootstrap aggregated neural network offers improved model prediction accuracy. • Improved exergy efficiency is obtained through model based optimisation. • Reductions of utility consumption by 8.2% and 28.2% were achieved for binary systems. • The exergy efficiency for multi-component distillation is increased by 32.4%.

Computer interpretation of thallium SPECT studies based on neural network analysis

Science.gov (United States)

Wang, David C.; Karvelis, K. C.

1991-06-01

A class of artificial intelligence (Al) programs known as neural networks are well suited to pattern recognition. A neural network is trained rather than programmed to recognize patterns. This differs from "expert system" Al programs in that it is not following an extensive set of rules determined by the programmer, but rather bases its decision on a gestalt interpretation of the image. The "bullseye" images from cardiac stress thallium tests performed on 50 male patients, as well as several simulated images were used to train the network. The network was able to accurately classify all patients in the training set. The network was then tested against 50 unknown patients and was able to correctly categorize 77% of the areas of ischemia and 92% of the areas of infarction. While not yet matching the ability of a trained physician, the neural network shows great promise in this area and has potential application in other areas of medical imaging.

Computer interpretation of thallium SPECT studies based on neural network analysis

International Nuclear Information System (INIS)

Wang, D.C.; Karvelis, K.C.

1991-01-01

This paper reports that a class of artificial intelligence (AI) programs known as neural-networks are well suited to pattern recognition. A neural network is trained rather than programmed to recognize patterns. This differs from expert system AI programs in that it is not following an extensive set of rules determined by the programmer, but rather bases its decision on a gestalt interpretation of the image. The bullseye images from cardiac stress thallium tests performed on 50 male patients, as well as several simulated images were used to train the network. The network was able to accurately classify all patients in the training set. The network was then tested against 50 unknown patients and was able to correctly categorize 77% of the areas of ischemia and 92% of the areas of infarction. While not yet matching the ability of the trained physician, the neural network shows great promise in this area and has potential application in other areas of medical imaging

Abstract Computation in Schizophrenia Detection through Artificial Neural Network Based Systems

Directory of Open Access Journals (Sweden)

L. Cardoso

2015-01-01

Full Text Available Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason of defective information.

Neural-network-based depth computation for blind navigation

Science.gov (United States)

Wong, Farrah; Nagarajan, Ramachandran R.; Yaacob, Sazali

2004-12-01

A research undertaken to help blind people to navigate autonomously or with minimum assistance is termed as "Blind Navigation". In this research, an aid that could help blind people in their navigation is proposed. Distance serves as an important clue during our navigation. A stereovision navigation aid implemented with two digital video cameras that are spaced apart and fixed on a headgear to obtain the distance information is presented. In this paper, a neural network methodology is used to obtain the required parameters of the camera which is known as camera calibration. These parameters are not known but obtained by adjusting the weights in the network. The inputs to the network consist of the matching features in the stereo pair images. A back propagation network with 16-input neurons, 3 hidden neurons and 1 output neuron, which gives depth, is created. The distance information is incorporated into the final processed image as four gray levels such as white, light gray, dark gray and black. Preliminary results have shown that the percentage errors fall below 10%. It is envisaged that the distance provided by neural network shall enable blind individuals to go near and pick up an object of interest.

Concurrent heterogeneous neural model simulation on real-time neuromimetic hardware.

Science.gov (United States)

Rast, Alexander; Galluppi, Francesco; Davies, Sergio; Plana, Luis; Patterson, Cameron; Sharp, Thomas; Lester, David; Furber, Steve

2011-11-01

Dedicated hardware is becoming increasingly essential to simulate emerging very-large-scale neural models. Equally, however, it needs to be able to support multiple models of the neural dynamics, possibly operating simultaneously within the same system. This may be necessary either to simulate large models with heterogeneous neural types, or to simplify simulation and analysis of detailed, complex models in a large simulation by isolating the new model to a small subpopulation of a larger overall network. The SpiNNaker neuromimetic chip is a dedicated neural processor able to support such heterogeneous simulations. Implementing these models on-chip uses an integrated library-based tool chain incorporating the emerging PyNN interface that allows a modeller to input a high-level description and use an automated process to generate an on-chip simulation. Simulations using both LIF and Izhikevich models demonstrate the ability of the SpiNNaker system to generate and simulate heterogeneous networks on-chip, while illustrating, through the network-scale effects of wavefront synchronisation and burst gating, methods that can provide effective behavioural abstractions for large-scale hardware modelling. SpiNNaker's asynchronous virtual architecture permits greater scope for model exploration, with scalable levels of functional and temporal abstraction, than conventional (or neuromorphic) computing platforms. The complete system illustrates a potential path to understanding the neural model of computation, by building (and breaking) neural models at various scales, connecting the blocks, then comparing them against the biology: computational cognitive neuroscience. Copyright © 2011 Elsevier Ltd. All rights reserved.

Optimization behavior of brainstem respiratory neurons. A cerebral neural network model.

Science.gov (United States)

Poon, C S

1991-01-01

A recent model of respiratory control suggested that the steady-state respiratory responses to CO2 and exercise may be governed by an optimal control law in the brainstem respiratory neurons. It was not certain, however, whether such complex optimization behavior could be accomplished by a realistic biological neural network. To test this hypothesis, we developed a hybrid computer-neural model in which the dynamics of the lung, brain and other tissue compartments were simulated on a digital computer. Mimicking the "controller" was a human subject who pedalled on a bicycle with varying speed (analog of ventilatory output) with a view to minimize an analog signal of the total cost of breathing (chemical and mechanical) which was computed interactively and displayed on an oscilloscope. In this manner, the visuomotor cortex served as a proxy (homolog) of the brainstem respiratory neurons in the model. Results in 4 subjects showed a linear steady-state ventilatory CO2 response to arterial PCO2 during simulated CO2 inhalation and a nearly isocapnic steady-state response during simulated exercise. Thus, neural optimization is a plausible mechanism for respiratory control during exercise and can be achieved by a neural network with cognitive computational ability without the need for an exercise stimulus.

Neuromorphic neural interfaces: from neurophysiological inspiration to biohybrid coupling with nervous systems

Science.gov (United States)

Broccard, Frédéric D.; Joshi, Siddharth; Wang, Jun; Cauwenberghs, Gert

2017-08-01

Objective. Computation in nervous systems operates with different computational primitives, and on different hardware, than traditional digital computation and is thus subjected to different constraints from its digital counterpart regarding the use of physical resources such as time, space and energy. In an effort to better understand neural computation on a physical medium with similar spatiotemporal and energetic constraints, the field of neuromorphic engineering aims to design and implement electronic systems that emulate in very large-scale integration (VLSI) hardware the organization and functions of neural systems at multiple levels of biological organization, from individual neurons up to large circuits and networks. Mixed analog/digital neuromorphic VLSI systems are compact, consume little power and operate in real time independently of the size and complexity of the model. Approach. This article highlights the current efforts to interface neuromorphic systems with neural systems at multiple levels of biological organization, from the synaptic to the system level, and discusses the prospects for future biohybrid systems with neuromorphic circuits of greater complexity. Main results. Single silicon neurons have been interfaced successfully with invertebrate and vertebrate neural networks. This approach allowed the investigation of neural properties that are inaccessible with traditional techniques while providing a realistic biological context not achievable with traditional numerical modeling methods. At the network level, populations of neurons are envisioned to communicate bidirectionally with neuromorphic processors of hundreds or thousands of silicon neurons. Recent work on brain-machine interfaces suggests that this is feasible with current neuromorphic technology. Significance. Biohybrid interfaces between biological neurons and VLSI neuromorphic systems of varying complexity have started to emerge in the literature. Primarily intended as a

An Expedient Study on Back-Propagation (BPN) Neural Networks for Modeling Automated Evaluation of the Answers and Progress of Deaf Students' That Possess Basic Knowledge of the English Language and Computer Skills

Science.gov (United States)

Vrettaros, John; Vouros, George; Drigas, Athanasios S.

This article studies the expediency of using neural networks technology and the development of back-propagation networks (BPN) models for modeling automated evaluation of the answers and progress of deaf students' that possess basic knowledge of the English language and computer skills, within a virtual e-learning environment. The performance of the developed neural models is evaluated with the correlation factor between the neural networks' response values and the real value data as well as the percentage measurement of the error between the neural networks' estimate values and the real value data during its training process and afterwards with unknown data that weren't used in the training process.

Robust Adaptive Neural Control of Morphing Aircraft with Prescribed Performance

OpenAIRE

Wu, Zhonghua; Lu, Jingchao; Shi, Jingping; Liu, Yang; Zhou, Qing

2017-01-01

This study proposes a low-computational composite adaptive neural control scheme for the longitudinal dynamics of a swept-back wing aircraft subject to parameter uncertainties. To efficiently release the constraint often existing in conventional neural designs, whose closed-loop stability analysis always necessitates that neural networks (NNs) be confined in the active regions, a smooth switching function is presented to conquer this issue. By integrating minimal learning parameter (MLP) tech...

Spike Neural Models Part II: Abstract Neural Models

Directory of Open Access Journals (Sweden)

Johnson, Melissa G.

2018-02-01

Full Text Available Neurons are complex cells that require a lot of time and resources to model completely. In spiking neural networks (SNN though, not all that complexity is required. Therefore simple, abstract models are often used. These models save time, use less computer resources, and are easier to understand. This tutorial presents two such models: Izhikevich's model, which is biologically realistic in the resulting spike trains but not in the parameters, and the Leaky Integrate and Fire (LIF model which is not biologically realistic but does quickly and easily integrate input to produce spikes. Izhikevich's model is based on Hodgkin-Huxley's model but simplified such that it uses only two differentiation equations and four parameters to produce various realistic spike patterns. LIF is based on a standard electrical circuit and contains one equation. Either of these two models, or any of the many other models in literature can be used in a SNN. Choosing a neural model is an important task that depends on the goal of the research and the resources available. Once a model is chosen, network decisions such as connectivity, delay, and sparseness, need to be made. Understanding neural models and how they are incorporated into the network is the first step in creating a SNN.

A Quantum Implementation Model for Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Ammar Daskin

2018-02-01

Full Text Available The learning process for multilayered neural networks with many nodes makes heavy demands on computational resources. In some neural network models, the learning formulas, such as the Widrow–Hoff formula, do not change the eigenvectors of the weight matrix while flatting the eigenvalues. In infinity, these iterative formulas result in terms formed by the principal components of the weight matrix, namely, the eigenvectors corresponding to the non-zero eigenvalues. In quantum computing, the phase estimation algorithm is known to provide speedups over the conventional algorithms for the eigenvalue-related problems. Combining the quantum amplitude amplification with the phase estimation algorithm, a quantum implementation model for artificial neural networks using the Widrow–Hoff learning rule is presented. The complexity of the model is found to be linear in the size of the weight matrix. This provides a quadratic improvement over the classical algorithms. Quanta 2018; 7: 7–18.

[Computer-assisted diet therapy in pediatric kidney diseases].

Science.gov (United States)

Dartois, A M; Ducamp, S; Decaux, F; Broyer, M

1989-01-01

The authors present a computer program written in UCSD Pascal) which monitors the dietary management of children with kidney diseases. Diet is established according to height, weight, chronological and statural age and recommended dietary allowances (USRDA). The composition of the prescribed diet and of food intake is given as amounts of animal and vegetable protein, fat, carbohydrates, energy, water, Na, K, Ca, P and renal solute load, per day and per kilo BW as compared to RDA. The amount of food is presented in tabular form, per day, per meal, per feed, or per tube-feeding with the schedule. It is possible to calculate the nutrients of food recipes. The food table includes 500 items, that can be modified as required. The drug table contains 100 items. The program calculates also average food consumption for dietary surveys. Diets, recipes and food tables may be viewed and modified before print out at each step of the calculation. The diet data bank stores 100 diets per floppy disk.

Applying Gradient Descent in Convolutional Neural Networks

Science.gov (United States)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

Science.gov (United States)

Mahmoudi, Fariborz; Mirzashaeri, Mohsen; Shahamatnia, Ehsan; Faridnia, Saed

This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.

Limits to high-speed simulations of spiking neural networks using general-purpose computers.

Science.gov (United States)

Zenke, Friedemann; Gerstner, Wulfram

2014-01-01

To understand how the central nervous system performs computations using recurrent neuronal circuitry, simulations have become an indispensable tool for theoretical neuroscience. To study neuronal circuits and their ability to self-organize, increasing attention has been directed toward synaptic plasticity. In particular spike-timing-dependent plasticity (STDP) creates specific demands for simulations of spiking neural networks. On the one hand a high temporal resolution is required to capture the millisecond timescale of typical STDP windows. On the other hand network simulations have to evolve over hours up to days, to capture the timescale of long-term plasticity. To do this efficiently, fast simulation speed is the crucial ingredient rather than large neuron numbers. Using different medium-sized network models consisting of several thousands of neurons and off-the-shelf hardware, we compare the simulation speed of the simulators: Brian, NEST and Neuron as well as our own simulator Auryn. Our results show that real-time simulations of different plastic network models are possible in parallel simulations in which numerical precision is not a primary concern. Even so, the speed-up margin of parallelism is limited and boosting simulation speeds beyond one tenth of real-time is difficult. By profiling simulation code we show that the run times of typical plastic network simulations encounter a hard boundary. This limit is partly due to latencies in the inter-process communications and thus cannot be overcome by increased parallelism. Overall, these results show that to study plasticity in medium-sized spiking neural networks, adequate simulation tools are readily available which run efficiently on small clusters. However, to run simulations substantially faster than real-time, special hardware is a prerequisite.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

Science.gov (United States)

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-01-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

A neutron spectrum unfolding computer code based on artificial neural networks

Science.gov (United States)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2014-02-01

The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding in

Neural Networks and Micromechanics

Science.gov (United States)

Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.

The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.

Application of Neural Network Optimized by Mind Evolutionary Computation in Building Energy Prediction

Science.gov (United States)

Song, Chen; Zhong-Cheng, Wu; Hong, Lv

2018-03-01

Building Energy forecasting plays an important role in energy management and plan. Using mind evolutionary algorithm to find the optimal network weights and threshold, to optimize the BP neural network, can overcome the problem of the BP neural network into a local minimum point. The optimized network is used for time series prediction, and the same month forecast, to get two predictive values. Then two kinds of predictive values are put into neural network, to get the final forecast value. The effectiveness of the method was verified by experiment with the energy value of three buildings in Hefei.

A Tensor-Product-Kernel Framework for Multiscale Neural Activity Decoding and Control

Science.gov (United States)

Li, Lin; Brockmeier, Austin J.; Choi, John S.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2014-01-01

Brain machine interfaces (BMIs) have attracted intense attention as a promising technology for directly interfacing computers or prostheses with the brain's motor and sensory areas, thereby bypassing the body. The availability of multiscale neural recordings including spike trains and local field potentials (LFPs) brings potential opportunities to enhance computational modeling by enriching the characterization of the neural system state. However, heterogeneity on data type (spike timing versus continuous amplitude signals) and spatiotemporal scale complicates the model integration of multiscale neural activity. In this paper, we propose a tensor-product-kernel-based framework to integrate the multiscale activity and exploit the complementary information available in multiscale neural activity. This provides a common mathematical framework for incorporating signals from different domains. The approach is applied to the problem of neural decoding and control. For neural decoding, the framework is able to identify the nonlinear functional relationship between the multiscale neural responses and the stimuli using general purpose kernel adaptive filtering. In a sensory stimulation experiment, the tensor-product-kernel decoder outperforms decoders that use only a single neural data type. In addition, an adaptive inverse controller for delivering electrical microstimulation patterns that utilizes the tensor-product kernel achieves promising results in emulating the responses to natural stimulation. PMID:24829569

Recurrent Neural Network Approach Based on the Integral Representation of the Drazin Inverse.

Science.gov (United States)

Stanimirović, Predrag S; Živković, Ivan S; Wei, Yimin

2015-10-01

In this letter, we present the dynamical equation and corresponding artificial recurrent neural network for computing the Drazin inverse for arbitrary square real matrix, without any restriction on its eigenvalues. Conditions that ensure the stability of the defined recurrent neural network as well as its convergence toward the Drazin inverse are considered. Several illustrative examples present the results of computer simulations.

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

OpenAIRE

Zhao, Liang; Liao, Siyu; Wang, Yanzhi; Li, Zhe; Tang, Jian; Pan, Victor; Yuan, Bo

2017-01-01

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity while retaining high accuracy. We formally study LDR matrices in deep learning. First, we prove the universal approximation property of LDR neural networks with a ...

The neural correlates of problem states: testing FMRI predictions of a computational model of multitasking.

Directory of Open Access Journals (Sweden)

Jelmer P Borst

Full Text Available BACKGROUND: It has been shown that people can only maintain one problem state, or intermediate mental representation, at a time. When more than one problem state is required, for example in multitasking, performance decreases considerably. This effect has been explained in terms of a problem state bottleneck. METHODOLOGY: In the current study we use the complimentary methodologies of computational cognitive modeling and neuroimaging to investigate the neural correlates of this problem state bottleneck. In particular, an existing computational cognitive model was used to generate a priori fMRI predictions for a multitasking experiment in which the problem state bottleneck plays a major role. Hemodynamic responses were predicted for five brain regions, corresponding to five cognitive resources in the model. Most importantly, we predicted the intraparietal sulcus to show a strong effect of the problem state manipulations. CONCLUSIONS: Some of the predictions were confirmed by a subsequent fMRI experiment, while others were not matched by the data. The experiment supported the hypothesis that the problem state bottleneck is a plausible cause of the interference in the experiment and that it could be located in the intraparietal sulcus.

STICK: Spike Time Interval Computational Kernel, a Framework for General Purpose Computation Using Neurons, Precise Timing, Delays, and Synchrony.

Science.gov (United States)

Lagorce, Xavier; Benosman, Ryad

2015-11-01

There has been significant research over the past two decades in developing new platforms for spiking neural computation. Current neural computers are primarily developed to mimic biology. They use neural networks, which can be trained to perform specific tasks to mainly solve pattern recognition problems. These machines can do more than simulate biology; they allow us to rethink our current paradigm of computation. The ultimate goal is to develop brain-inspired general purpose computation architectures that can breach the current bottleneck introduced by the von Neumann architecture. This work proposes a new framework for such a machine. We show that the use of neuron-like units with precise timing representation, synaptic diversity, and temporal delays allows us to set a complete, scalable compact computation framework. The framework provides both linear and nonlinear operations, allowing us to represent and solve any function. We show usability in solving real use cases from simple differential equations to sets of nonlinear differential equations leading to chaotic attractors.

Neural networks advances and applications 2

CERN Document Server

Gelenbe, E

1992-01-01

The present volume is a natural follow-up to Neural Networks: Advances and Applications which appeared one year previously. As the title indicates, it combines the presentation of recent methodological results concerning computational models and results inspired by neural networks, and of well-documented applications which illustrate the use of such models in the solution of difficult problems. The volume is balanced with respect to these two orientations: it contains six papers concerning methodological developments and five papers concerning applications and examples illustrating the theoret

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.

Hybrid Neural Network Approach Based Tool for the Modelling of Photovoltaic Panels

Directory of Open Access Journals (Sweden)

Antonino Laudani

2015-01-01

Full Text Available A hybrid neural network approach based tool for identifying the photovoltaic one-diode model is presented. The generalization capabilities of neural networks are used together with the robustness of the reduced form of one-diode model. Indeed, from the studies performed by the authors and the works present in the literature, it was found that a direct computation of the five parameters via multiple inputs and multiple outputs neural network is a very difficult task. The reduced form consists in a series of explicit formulae for the support to the neural network that, in our case, is aimed at predicting just two parameters among the five ones identifying the model: the other three parameters are computed by reduced form. The present hybrid approach is efficient from the computational cost point of view and accurate in the estimation of the five parameters. It constitutes a complete and extremely easy tool suitable to be implemented in a microcontroller based architecture. Validations are made on about 10000 PV panels belonging to the California Energy Commission database.

Event-Based Computation of Motion Flow on a Neuromorphic Analog Neural Platform.

Science.gov (United States)

Giulioni, Massimiliano; Lagorce, Xavier; Galluppi, Francesco; Benosman, Ryad B

2016-01-01

Estimating the speed and direction of moving objects is a crucial component of agents behaving in a dynamic world. Biological organisms perform this task by means of the neural connections originating from their retinal ganglion cells. In artificial systems the optic flow is usually extracted by comparing activity of two or more frames captured with a vision sensor. Designing artificial motion flow detectors which are as fast, robust, and efficient as the ones found in biological systems is however a challenging task. Inspired by the architecture proposed by Barlow and Levick in 1965 to explain the spiking activity of the direction-selective ganglion cells in the rabbit's retina, we introduce an architecture for robust optical flow extraction with an analog neuromorphic multi-chip system. The task is performed by a feed-forward network of analog integrate-and-fire neurons whose inputs are provided by contrast-sensitive photoreceptors. Computation is supported by the precise time of spike emission, and the extraction of the optical flow is based on time lag in the activation of nearby retinal neurons. Mimicking ganglion cells our neuromorphic detectors encode the amplitude and the direction of the apparent visual motion in their output spiking pattern. Hereby we describe the architectural aspects, discuss its latency, scalability, and robustness properties and demonstrate that a network of mismatched delicate analog elements can reliably extract the optical flow from a simple visual scene. This work shows how precise time of spike emission used as a computational basis, biological inspiration, and neuromorphic systems can be used together for solving specific tasks.

Efficient decoding with steady-state Kalman filter in neural interface systems.

Science.gov (United States)

Malik, Wasim Q; Truccolo, Wilson; Brown, Emery N; Hochberg, Leigh R

2011-02-01

The Kalman filter is commonly used in neural interface systems to decode neural activity and estimate the desired movement kinematics. We analyze a low-complexity Kalman filter implementation in which the filter gain is approximated by its steady-state form, computed offline before real-time decoding commences. We evaluate its performance using human motor cortical spike train data obtained from an intracortical recording array as part of an ongoing pilot clinical trial. We demonstrate that the standard Kalman filter gain converges to within 95% of the steady-state filter gain in 1.5±0.5 s (mean ±s.d.). The difference in the intended movement velocity decoded by the two filters vanishes within 5 s, with a correlation coefficient of 0.99 between the two decoded velocities over the session length. We also find that the steady-state Kalman filter reduces the computational load (algorithm execution time) for decoding the firing rates of 25±3 single units by a factor of 7.0±0.9. We expect that the gain in computational efficiency will be much higher in systems with larger neural ensembles. The steady-state filter can thus provide substantial runtime efficiency at little cost in terms of estimation accuracy. This far more efficient neural decoding approach will facilitate the practical implementation of future large-dimensional, multisignal neural interface systems.

Intelligent neural network diagnostic system

International Nuclear Information System (INIS)

Mohamed, A.H.

2010-01-01

Recently, artificial neural network (ANN) has made a significant mark in the domain of diagnostic applications. Neural networks are used to implement complex non-linear mappings (functions) using simple elementary units interrelated through connections with adaptive weights. The performance of the ANN is mainly depending on their topology structure and weights. Some systems have been developed using genetic algorithm (GA) to optimize the topology of the ANN. But, they suffer from some limitations. They are : (1) The computation time requires for training the ANN several time reaching for the average weight required, (2) Slowness of GA for optimization process and (3) Fitness noise appeared in the optimization of ANN. This research suggests new issues to overcome these limitations for finding optimal neural network architectures to learn particular problems. This proposed methodology is used to develop a diagnostic neural network system. It has been applied for a 600 MW turbo-generator as a case of real complex systems. The proposed system has proved its significant performance compared to two common methods used in the diagnostic applications.

Spiking neural P systems with multiple channels.

Science.gov (United States)

Peng, Hong; Yang, Jinyu; Wang, Jun; Wang, Tao; Sun, Zhang; Song, Xiaoxiao; Luo, Xiaohui; Huang, Xiangnian

2017-11-01

Spiking neural P systems (SNP systems, in short) are a class of distributed parallel computing systems inspired from the neurophysiological behavior of biological spiking neurons. In this paper, we investigate a new variant of SNP systems in which each neuron has one or more synaptic channels, called spiking neural P systems with multiple channels (SNP-MC systems, in short). The spiking rules with channel label are introduced to handle the firing mechanism of neurons, where the channel labels indicate synaptic channels of transmitting the generated spikes. The computation power of SNP-MC systems is investigated. Specifically, we prove that SNP-MC systems are Turing universal as both number generating and number accepting devices. Copyright © 2017 Elsevier Ltd. All rights reserved.

A loop-based neural architecture for structured behavior encoding and decoding.

Science.gov (United States)

Gisiger, Thomas; Boukadoum, Mounir

2018-02-01

We present a new type of artificial neural network that generalizes on anatomical and dynamical aspects of the mammal brain. Its main novelty lies in its topological structure which is built as an array of interacting elementary motifs shaped like loops. These loops come in various types and can implement functions such as gating, inhibitory or executive control, or encoding of task elements to name a few. Each loop features two sets of neurons and a control region, linked together by non-recurrent projections. The two neural sets do the bulk of the loop's computations while the control unit specifies the timing and the conditions under which the computations implemented by the loop are to be performed. By functionally linking many such loops together, a neural network is obtained that may perform complex cognitive computations. To demonstrate the potential offered by such a system, we present two neural network simulations. The first illustrates the structure and dynamics of a single loop implementing a simple gating mechanism. The second simulation shows how connecting four loops in series can produce neural activity patterns that are sufficient to pass a simplified delayed-response task. We also show that this network reproduces electrophysiological measurements gathered in various regions of the brain of monkeys performing similar tasks. We also demonstrate connections between this type of neural network and recurrent or long short-term memory network models, and suggest ways to generalize them for future artificial intelligence research. Copyright © 2017 Elsevier Ltd. All rights reserved.

Four Degree Freedom Robot Arm with Fuzzy Neural Network Control

Directory of Open Access Journals (Sweden)

Şinasi Arslan

2013-01-01

Full Text Available In this study, the control of four degree freedom robot arm has been realized with the computed torque control method.. It is usually required that the four jointed robot arm has high precision capability and good maneuverability for using in industrial applications. Besides, high speed working and external applied loads have been acting as important roles. For those purposes, the computed torque control method has been developed in a good manner that the robot arm can track the given trajectory, which has been able to enhance the feedback control together with fuzzy neural network control. The simulation results have proved that the computed torque control with the neural network has been so successful in robot control.

Neural networks and their application to nuclear power plant diagnosis

International Nuclear Information System (INIS)

Reifman, J.

1997-01-01

The authors present a survey of artificial neural network-based computer systems that have been proposed over the last decade for the detection and identification of component faults in thermal-hydraulic systems of nuclear power plants. The capabilities and advantages of applying neural networks as decision support systems for nuclear power plant operators and their inherent characteristics are discussed along with their limitations and drawbacks. The types of neural network structures used and their applications are described and the issues of process diagnosis and neural network-based diagnostic systems are identified. A total of thirty-four publications are reviewed

High speed VLSI neural network for high energy physics

NARCIS (Netherlands)

Masa, P.; Masa, P.; Hoen, K.; Hoen, Klaas; Wallinga, Hans

1994-01-01

A CMOS neural network IC is discussed which was designed for very high speed applications. The parallel architecture, analog computing and digital weight storage provides unprecedented computing speed combined with ease of use. The circuit classifies up to 70 dimensional vectors within 20

Modular representation of layered neural networks.

Science.gov (United States)

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

Computationally Efficient Neural Network Intrusion Security Awareness

Energy Technology Data Exchange (ETDEWEB)

Todd Vollmer; Milos Manic

2009-08-01

An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.

DEVELOPMENT OF A COMPUTER SYSTEM FOR IDENTITY AUTHENTICATION USING ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Timur Kartbayev

2017-03-01

Full Text Available The aim of the study is to increase the effectiveness of automated face recognition to authenticate identity, considering features of change of the face parameters over time. The improvement of the recognition accuracy, as well as consideration of the features of temporal changes in a human face can be based on the methodology of artificial neural networks. Hybrid neural networks, combining the advantages of classical neural networks and fuzzy logic systems, allow using the network learnability along with the explanation of the findings. The structural scheme of intelligent system for identification based on artificial neural networks is proposed in this work. It realizes the principles of digital information processing and identity recognition taking into account the forecast of key characteristics’ changes over time (e.g., due to aging. The structural scheme has a three-tier architecture and implements preliminary processing, recognition and identification of images obtained as a result of monitoring. On the basis of expert knowledge, the fuzzy base of products is designed. It allows assessing possible changes in key characteristics, used to authenticate identity based on the image. To take this possibility into consideration, a neuro-fuzzy network of ANFIS type was used, which implements the algorithm of Tagaki-Sugeno. The conducted experiments showed high efficiency of the developed neural network and a low value of learning errors, which allows recommending this approach for practical implementation. Application of the developed system of fuzzy production rules that allow predicting changes in individuals over time, will improve the recognition accuracy, reduce the number of authentication failures and improve the efficiency of information processing and decision-making in applications, such as authentication of bank customers, users of mobile applications, or in video monitoring systems of sensitive sites.

The parallel implementation of a backpropagation neural network and its applicability to SPECT image reconstruction

Energy Technology Data Exchange (ETDEWEB)

Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)

1992-01-01

The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.

Computer vision-based method for classification of wheat grains using artificial neural network.

Science.gov (United States)

Sabanci, Kadir; Kayabasi, Ahmet; Toktas, Abdurrahim

2017-06-01

A simplified computer vision-based application using artificial neural network (ANN) depending on multilayer perceptron (MLP) for accurately classifying wheat grains into bread or durum is presented. The images of 100 bread and 100 durum wheat grains are taken via a high-resolution camera and subjected to pre-processing. The main visual features of four dimensions, three colors and five textures are acquired using image-processing techniques (IPTs). A total of 21 visual features are reproduced from the 12 main features to diversify the input population for training and testing the ANN model. The data sets of visual features are considered as input parameters of the ANN model. The ANN with four different input data subsets is modelled to classify the wheat grains into bread or durum. The ANN model is trained with 180 grains and its accuracy tested with 20 grains from a total of 200 wheat grains. Seven input parameters that are most effective on the classifying results are determined using the correlation-based CfsSubsetEval algorithm to simplify the ANN model. The results of the ANN model are compared in terms of accuracy rate. The best result is achieved with a mean absolute error (MAE) of 9.8 × 10 -6 by the simplified ANN model. This shows that the proposed classifier based on computer vision can be successfully exploited to automatically classify a variety of grains. © 2016 Society of Chemical Industry. © 2016 Society of Chemical Industry.

Ensemble of Neural Network Conditional Random Fields for Self-Paced Brain Computer Interfaces

Directory of Open Access Journals (Sweden)

Hossein Bashashati

2017-07-01

Full Text Available Classification of EEG signals in self-paced Brain Computer Interfaces (BCI is an extremely challenging task. The main difficulty stems from the fact that start time of a control task is not defined. Therefore it is imperative to exploit the characteristics of the EEG data to the extent possible. In sensory motor self-paced BCIs, while performing the mental task, the user’s brain goes through several well-defined internal state changes. Applying appropriate classifiers that can capture these state changes and exploit the temporal correlation in EEG data can enhance the performance of the BCI. In this paper, we propose an ensemble learning approach for self-paced BCIs. We use Bayesian optimization to train several different classifiers on different parts of the BCI hyper- parameter space. We call each of these classifiers Neural Network Conditional Random Field (NNCRF. NNCRF is a combination of a neural network and conditional random field (CRF. As in the standard CRF, NNCRF is able to model the correlation between adjacent EEG samples. However, NNCRF can also model the nonlinear dependencies between the input and the output, which makes it more powerful than the standard CRF. We compare the performance of our algorithm to those of three popular sequence labeling algorithms (Hidden Markov Models, Hidden Markov Support Vector Machines and CRF, and to two classical classifiers (Logistic Regression and Support Vector Machines. The classifiers are compared for the two cases: when the ensemble learning approach is not used and when it is. The data used in our studies are those from the BCI competition IV and the SM2 dataset. We show that our algorithm is considerably superior to the other approaches in terms of the Area Under the Curve (AUC of the BCI system.

State-of-the-art of applications of neural networks in the nuclear industry

International Nuclear Information System (INIS)

Zwingelstein, G.; Masson, M.H.

1990-01-01

Artificial neural net models have been extensively studied for many years in various laboratories to try to simulate with computer programs the human brain performances. The first applications were developed in the fields of speech and image recognition. The aims of these studies were mainly to classify rapidly patterns corrupted by noises or partly missing. Neural networks with the development of new net topologies and algorithms and parallel computing hardwares and softwares are to-day very promising for applications in many industries. In the introduction, this paper presents the anticipated benefits of the uses of neural networks for industrial applications. Then a brief overview of the main neural networks is provided. Finally a short review of neural networks applications in the nuclear industry is given. It covers domains such as: predictive maintenance for vibratory surveillance of rotating machinery, signal processing, operator guidance and eddy current inspection. In conclusion recommendations are made to use with efficiency neural networks for practical applications. In particular the need for supercomputing will be pinpointed. (author)

Modeling and Speed Control of Induction Motor Drives Using Neural Networks

Directory of Open Access Journals (Sweden)

V. Jamuna

2010-08-01

Full Text Available Speed control of induction motor drives using neural networks is presented. The mathematical model of single phase induction motor is developed. A new simulink model for a neural network-controlled bidirectional chopper fed single phase induction motor is proposed. Under normal operation, the true drive parameters are real-time identified and they are converted into the controller parameters through multilayer forward computation by neural networks. Comparative study has been made between the conventional and neural network controllers. It is observed that the neural network controlled drive system has better dynamic performance, reduced overshoot and faster transient response than the conventional controlled system.

Seismic activity prediction using computational intelligence techniques in northern Pakistan

Science.gov (United States)

Asim, Khawaja M.; Awais, Muhammad; Martínez-Álvarez, F.; Iqbal, Talat

2017-10-01

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar's statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.

Computational aspects of feedback in neural circuits.

Directory of Open Access Journals (Sweden)

Wolfgang Maass

2007-01-01

Full Text Available It has previously been shown that generic cortical microcircuit models can perform complex real-time computations on continuous input streams, provided that these computations can be carried out with a rapidly fading memory. We investigate the computational capability of such circuits in the more realistic case where not only readout neurons, but in addition a few neurons within the circuit, have been trained for specific tasks. This is essentially equivalent to the case where the output of trained readout neurons is fed back into the circuit. We show that this new model overcomes the limitation of a rapidly fading memory. In fact, we prove that in the idealized case without noise it can carry out any conceivable digital or analog computation on time-varying inputs. But even with noise, the resulting computational model can perform a large class of biologically relevant real-time computations that require a nonfading memory. We demonstrate these computational implications of feedback both theoretically, and through computer simulations of detailed cortical microcircuit models that are subject to noise and have complex inherent dynamics. We show that the application of simple learning procedures (such as linear regression or perceptron learning to a few neurons enables such circuits to represent time over behaviorally relevant long time spans, to integrate evidence from incoming spike trains over longer periods of time, and to process new information contained in such spike trains in diverse ways according to the current internal state of the circuit. In particular we show that such generic cortical microcircuits with feedback provide a new model for working memory that is consistent with a large set of biological constraints. Although this article examines primarily the computational role of feedback in circuits of neurons, the mathematical principles on which its analysis is based apply to a variety of dynamical systems. Hence they may also

DANoC: An Efficient Algorithm and Hardware Codesign of Deep Neural Networks on Chip.

Science.gov (United States)

Zhou, Xichuan; Li, Shengli; Tang, Fang; Hu, Shengdong; Lin, Zhi; Zhang, Lei

2017-07-18

Deep neural networks (NNs) are the state-of-the-art models for understanding the content of images and videos. However, implementing deep NNs in embedded systems is a challenging task, e.g., a typical deep belief network could exhaust gigabytes of memory and result in bandwidth and computational bottlenecks. To address this challenge, this paper presents an algorithm and hardware codesign for efficient deep neural computation. A hardware-oriented deep learning algorithm, named the deep adaptive network, is proposed to explore the sparsity of neural connections. By adaptively removing the majority of neural connections and robustly representing the reserved connections using binary integers, the proposed algorithm could save up to 99.9% memory utility and computational resources without undermining classification accuracy. An efficient sparse-mapping-memory-based hardware architecture is proposed to fully take advantage of the algorithmic optimization. Different from traditional Von Neumann architecture, the deep-adaptive network on chip (DANoC) brings communication and computation in close proximity to avoid power-hungry parameter transfers between on-board memory and on-chip computational units. Experiments over different image classification benchmarks show that the DANoC system achieves competitively high accuracy and efficiency comparing with the state-of-the-art approaches.

Chaos-based encryption keys and neural key-store for cloud-hosted data confidentiality

CSIR Research Space (South Africa)

Mosola, NN

2017-09-01

Full Text Available learning and cryptography, using neural networks. In their research, [7] proposes artificial intelligence techniques to invent cryptosystems to curb eavesdropping. The research proposes two artificial neural networks for develop a cryptographic... or UP. REFERENCES [1] A. Shawish and M. Salama, 2014. Cloud Computing: Paradigms and Technologies, F. Xhafa and N. Bessis (eds.), Inter-cooperative Collective Intelligence: Techniques and Applications, Studies in Computational Intelligence 495, DOI...

The benefit of combining a deep neural network architecture with ideal ratio mask estimation in computational speech segregation to improve speech intelligibility

DEFF Research Database (Denmark)

Bentsen, Thomas; May, Tobias; Kressner, Abigail Anne

2018-01-01

Computational speech segregation attempts to automatically separate speech from noise. This is challenging in conditions with interfering talkers and low signal-to-noise ratios. Recent approaches have adopted deep neural networks and successfully demonstrated speech intelligibility improvements....... A selection of components may be responsible for the success with these state-of-the-art approaches: the system architecture, a time frame concatenation technique and the learning objective. The aim of this study was to explore the roles and the relative contributions of these components by measuring speech......, to a state-of-the-art deep neural network-based architecture. Another improvement of 13.9 percentage points was obtained by changing the learning objective from the ideal binary mask, in which individual time-frequency units are labeled as either speech- or noise-dominated, to the ideal ratio mask, where...

A quantum-implementable neural network model

Science.gov (United States)

Chen, Jialin; Wang, Lingli; Charbon, Edoardo

2017-10-01

A quantum-implementable neural network, namely quantum probability neural network (QPNN) model, is proposed in this paper. QPNN can use quantum parallelism to trace all possible network states to improve the result. Due to its unique quantum nature, this model is robust to several quantum noises under certain conditions, which can be efficiently implemented by the qubus quantum computer. Another advantage is that QPNN can be used as memory to retrieve the most relevant data and even to generate new data. The MATLAB experimental results of Iris data classification and MNIST handwriting recognition show that much less neuron resources are required in QPNN to obtain a good result than the classical feedforward neural network. The proposed QPNN model indicates that quantum effects are useful for real-life classification tasks.

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.

Invariant recognition drives neural representations of action sequences.

Directory of Open Access Journals (Sweden)

Andrea Tacchetti

2017-12-01

Full Text Available Recognizing the actions of others from visual stimuli is a crucial aspect of human perception that allows individuals to respond to social cues. Humans are able to discriminate between similar actions despite transformations, like changes in viewpoint or actor, that substantially alter the visual appearance of a scene. This ability to generalize across complex transformations is a hallmark of human visual intelligence. Advances in understanding action recognition at the neural level have not always translated into precise accounts of the computational principles underlying what representations of action sequences are constructed by human visual cortex. Here we test the hypothesis that invariant action discrimination might fill this gap. Recently, the study of artificial systems for static object perception has produced models, Convolutional Neural Networks (CNNs, that achieve human level performance in complex discriminative tasks. Within this class, architectures that better support invariant object recognition also produce image representations that better match those implied by human and primate neural data. However, whether these models produce representations of action sequences that support recognition across complex transformations and closely follow neural representations of actions remains unknown. Here we show that spatiotemporal CNNs accurately categorize video stimuli into action classes, and that deliberate model modifications that improve performance on an invariant action recognition task lead to data representations that better match human neural recordings. Our results support our hypothesis that performance on invariant discrimination dictates the neural representations of actions computed in the brain. These results broaden the scope of the invariant recognition framework for understanding visual intelligence from perception of inanimate objects and faces in static images to the study of human perception of action sequences.

A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network.

Science.gov (United States)

Zhao, Haiquan; Zhang, Jiashu

2009-12-01

To enhance the performance and overcome the heavy computational complexity of recurrent neural networks (RNN), a novel nonlinear adaptive filter based on a pipelined second-order Volterra recurrent neural network (PSOVRNN) is proposed in this paper. A modified real-time recurrent learning (RTRL) algorithm of the proposed filter is derived in much more detail. The PSOVRNN comprises of a number of simple small-scale second-order Volterra recurrent neural network (SOVRNN) modules. In contrast to the standard RNN, these modules of a PSOVRNN can be performed simultaneously in a pipelined parallelism fashion, which can lead to a significant improvement in its total computational efficiency. Moreover, since each module of the PSOVRNN is a SOVRNN in which nonlinearity is introduced by the recursive second-order Volterra (RSOV) expansion, its performance can be further improved. Computer simulations have demonstrated that the PSOVRNN performs better than the pipelined recurrent neural network (PRNN) and RNN for nonlinear colored signals prediction and nonlinear channel equalization. However, the superiority of the PSOVRNN over the PRNN is at the cost of increasing computational complexity due to the introduced nonlinear expansion of each module.

Learning from large scale neural simulations

DEFF Research Database (Denmark)

Serban, Maria

2017-01-01

Large-scale neural simulations have the marks of a distinct methodology which can be fruitfully deployed to advance scientific understanding of the human brain. Computer simulation studies can be used to produce surrogate observational data for better conceptual models and new how...

Integrating probabilistic models of perception and interactive neural networks: a historical and tutorial review.

Science.gov (United States)

McClelland, James L

2013-01-01

This article seeks to establish a rapprochement between explicitly Bayesian models of contextual effects in perception and neural network models of such effects, particularly the connectionist interactive activation (IA) model of perception. The article is in part an historical review and in part a tutorial, reviewing the probabilistic Bayesian approach to understanding perception and how it may be shaped by context, and also reviewing ideas about how such probabilistic computations may be carried out in neural networks, focusing on the role of context in interactive neural networks, in which both bottom-up and top-down signals affect the interpretation of sensory inputs. It is pointed out that connectionist units that use the logistic or softmax activation functions can exactly compute Bayesian posterior probabilities when the bias terms and connection weights affecting such units are set to the logarithms of appropriate probabilistic quantities. Bayesian concepts such the prior, likelihood, (joint and marginal) posterior, probability matching and maximizing, and calculating vs. sampling from the posterior are all reviewed and linked to neural network computations. Probabilistic and neural network models are explicitly linked to the concept of a probabilistic generative model that describes the relationship between the underlying target of perception (e.g., the word intended by a speaker or other source of sensory stimuli) and the sensory input that reaches the perceiver for use in inferring the underlying target. It is shown how a new version of the IA model called the multinomial interactive activation (MIA) model can sample correctly from the joint posterior of a proposed generative model for perception of letters in words, indicating that interactive processing is fully consistent with principled probabilistic computation. Ways in which these computations might be realized in real neural systems are also considered.

A new fuzzy regression model based on interval-valued fuzzy neural network and its applications to management

Directory of Open Access Journals (Sweden)

Somaye Yeylaghi

2017-06-01

Full Text Available In this paper, a novel hybrid method based on interval-valued fuzzy neural network for approximate of interval-valued fuzzy regression models, is presented. The work of this paper is an expansion of the research of real fuzzy regression models. In this paper interval-valued fuzzy neural network (IVFNN can be trained with crisp and interval-valued fuzzy data. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate parameters, a simple algorithm from the cost function of the fuzzy neural network is proposed. Finally, we illustrate our approach by some numerical examples and compare this method with existing methods.

An Overview of Bayesian Methods for Neural Spike Train Analysis

Directory of Open Access Journals (Sweden)

Zhe Chen

2013-01-01

Full Text Available Neural spike train analysis is an important task in computational neuroscience which aims to understand neural mechanisms and gain insights into neural circuits. With the advancement of multielectrode recording and imaging technologies, it has become increasingly demanding to develop statistical tools for analyzing large neuronal ensemble spike activity. Here we present a tutorial overview of Bayesian methods and their representative applications in neural spike train analysis, at both single neuron and population levels. On the theoretical side, we focus on various approximate Bayesian inference techniques as applied to latent state and parameter estimation. On the application side, the topics include spike sorting, tuning curve estimation, neural encoding and decoding, deconvolution of spike trains from calcium imaging signals, and inference of neuronal functional connectivity and synchrony. Some research challenges and opportunities for neural spike train analysis are discussed.

Local Dynamics in Trained Recurrent Neural Networks.

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-23

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Local Dynamics in Trained Recurrent Neural Networks

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-01

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Optimization of blanking process using neural network simulation

International Nuclear Information System (INIS)

Hambli, R.

2005-01-01

The present work describes a methodology using the finite element method and neural network simulation in order to predict the optimum punch-die clearance during sheet metal blanking processes. A damage model is used in order to describe crack initiation and propagation into the sheet. The proposed approach combines predictive finite element and neural network modeling of the leading blanking parameters. Numerical results obtained by finite element computation including damage and fracture modeling were utilized to train the developed simulation environment based on back propagation neural network modeling. The comparative study between the numerical results and the experimental ones shows the good agreement. (author)

Nondestructive pavement evaluation using ILLI-PAVE based artificial neural network models.

Science.gov (United States)

2008-09-01

The overall objective in this research project is to develop advanced pavement structural analysis models for more accurate solutions with fast computation schemes. Soft computing and modeling approaches, specifically the Artificial Neural Network (A...

Qualitative analysis and control of complex neural networks with delays

CERN Document Server

Wang, Zhanshan; Zheng, Chengde

2016-01-01

This book focuses on the stability of the dynamical neural system, synchronization of the coupling neural system and their applications in automation control and electrical engineering. The redefined concept of stability, synchronization and consensus are adopted to provide a better explanation of the complex neural network. Researchers in the fields of dynamical systems, computer science, electrical engineering and mathematics will benefit from the discussions on complex systems. The book will also help readers to better understand the theory behind the control technique and its design.

Efficient computation in networks of spiking neurons: simulations and theory

International Nuclear Information System (INIS)

Natschlaeger, T.

1999-01-01

One of the most prominent features of biological neural systems is that individual neurons communicate via short electrical pulses, the so called action potentials or spikes. In this thesis we investigate possible mechanisms which can in principle explain how complex computations in spiking neural networks (SNN) can be performed very fast, i.e. within a few 10 milliseconds. Some of these models are based on the assumption that relevant information is encoded by the timing of individual spikes (temporal coding). We will also discuss a model which is based on a population code and still is able to perform fast complex computations. In their natural environment biological neural systems have to process signals with a rich temporal structure. Hence it is an interesting question how neural systems process time series. In this context we explore possible links between biophysical characteristics of single neurons (refractory behavior, connectivity, time course of postsynaptic potentials) and synapses (unreliability, dynamics) on the one hand and possible computations on times series on the other hand. Furthermore we describe a general model of computation that exploits dynamic synapses. This model provides a general framework for understanding how neural systems process time-varying signals. (author)

Application of neural computing paradigms for signal validation

International Nuclear Information System (INIS)

Upadhyaya, B.R.; Eryurek, E.; Mathai, G.

1989-01-01

Signal validation and process monitoring problems often require the prediction of one or more process variables in a system. The feasibility of applying neural network paradigms to relate one variable with a set of other related variables is studied. The backpropagation network (BPN) is applied to develop models of signals from both a commercial power plant and the EBR-II. Modification of the BPN algorithm is studied with emphasis on the speed of network training and the accuracy of prediction. The prediction of process variables in a Westinghouse PWR is presented in this paper

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.

Computation of optimal transport and related hedging problems via penalization and neural networks

OpenAIRE

Eckstein, Stephan; Kupper, Michael

2018-01-01

This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversa...

A comparative study of two neural networks for document retrieval

International Nuclear Information System (INIS)

Hui, S.C.; Goh, A.

1997-01-01

In recent years there has been specific interest in adopting advanced computer techniques in the field of document retrieval. This interest is generated by the fact that classical methods such as the Boolean search, the vector space model or even probabilistic retrieval cannot handle the increasing demands of end-users in satisfying their needs. The most recent attempt is the application of the neural network paradigm as a means of providing end-users with a more powerful retrieval mechanism. Neural networks are not only good pattern matchers but also highly versatile and adaptable. In this paper, we demonstrate how to apply two neural networks, namely Adaptive Resonance Theory and Fuzzy Kohonen Neural Network, for document retrieval. In addition, a comparison of these two neural networks based on performance is also given

Investigation of efficient features for image recognition by neural networks.

Science.gov (United States)

Goltsev, Alexander; Gritsenko, Vladimir

2012-04-01

In the paper, effective and simple features for image recognition (named LiRA-features) are investigated in the task of handwritten digit recognition. Two neural network classifiers are considered-a modified 3-layer perceptron LiRA and a modular assembly neural network. A method of feature selection is proposed that analyses connection weights formed in the preliminary learning process of a neural network classifier. In the experiments using the MNIST database of handwritten digits, the feature selection procedure allows reduction of feature number (from 60 000 to 7000) preserving comparable recognition capability while accelerating computations. Experimental comparison between the LiRA perceptron and the modular assembly neural network is accomplished, which shows that recognition capability of the modular assembly neural network is somewhat better. Copyright © 2011 Elsevier Ltd. All rights reserved.

23rd Workshop of the Italian Neural Networks Society (SIREN)

CERN Document Server

Esposito, Anna; Morabito, Francesco

2014-01-01

This volume collects a selection of contributions which has been presented at the 23rd Italian Workshop on Neural Networks, the yearly meeting of the Italian Society for Neural Networks (SIREN). The conference was held in Vietri sul Mare, Salerno, Italy during May 23-24, 2013. The annual meeting of SIREN is sponsored by International Neural Network Society (INNS), European Neural Network Society (ENNS) and IEEE Computational Intelligence Society (CIS). The book – as well as the workshop-  is organized in two main components, a special session and a group of regular sessions featuring different aspects and point of views of artificial neural networks, artificial and natural intelligence, as well as psychological and cognitive theories for modeling human behaviors and human machine interactions, including Information Communication applications of compelling interest.  .

Neural Global Pattern Similarity Underlies True and False Memories.

Science.gov (United States)

Ye, Zhifang; Zhu, Bi; Zhuang, Liping; Lu, Zhonglin; Chen, Chuansheng; Xue, Gui

2016-06-22

The neural processes giving rise to human memory strength signals remain poorly understood. Inspired by formal computational models that posit a central role of global matching in memory strength, we tested a novel hypothesis that the strengths of both true and false memories arise from the global similarity of an item's neural activation pattern during retrieval to that of all the studied items during encoding (i.e., the encoding-retrieval neural global pattern similarity [ER-nGPS]). We revealed multiple ER-nGPS signals that carried distinct information and contributed differentially to true and false memories: Whereas the ER-nGPS in the parietal regions reflected semantic similarity and was scaled with the recognition strengths of both true and false memories, ER-nGPS in the visual cortex contributed solely to true memory. Moreover, ER-nGPS differences between the parietal and visual cortices were correlated with frontal monitoring processes. By combining computational and neuroimaging approaches, our results advance a mechanistic understanding of memory strength in recognition. What neural processes give rise to memory strength signals, and lead to our conscious feelings of familiarity? Using fMRI, we found that the memory strength of a given item depends not only on how it was encoded during learning, but also on the similarity of its neural representation with other studied items. The global neural matching signal, mainly in the parietal lobule, could account for the memory strengths of both studied and unstudied items. Interestingly, a different global matching signal, originated from the visual cortex, could distinguish true from false memories. The findings reveal multiple neural mechanisms underlying the memory strengths of events registered in the brain. Copyright © 2016 the authors 0270-6474/16/366792-11$15.00/0.

Training Deep Spiking Neural Networks Using Backpropagation.

Science.gov (United States)

Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael

2016-01-01

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

Numerical experiments with neural networks

International Nuclear Information System (INIS)

Miranda, Enrique.

1990-01-01

Neural networks are highly idealized models which, in spite of their simplicity, reproduce some key features of the real brain. In this paper, they are introduced at a level adequate for an undergraduate computational physics course. Some relevant magnitudes are defined and evaluated numerically for the Hopfield model and a short term memory model. (Author)

Convolutional Neural Networks - Generalizability and Interpretations

DEFF Research Database (Denmark)

Malmgren-Hansen, David

from data despite it being limited in amount or context representation. Within Machine Learning this thesis focuses on Convolutional Neural Networks for Computer Vision. The research aims to answer how to explore a model's generalizability to the whole population of data samples and how to interpret...

Neural Ranking Models with Weak Supervision

NARCIS (Netherlands)

Dehghani, M.; Zamani, H.; Severyn, A.; Kamps, J.; Croft, W.B.

2017-01-01

Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the ranking problem, as it is not obvious how to learn from

Energy Complexity of Recurrent Neural Networks

Czech Academy of Sciences Publication Activity Database

Šíma, Jiří

2014-01-01

Roč. 26, č. 5 (2014), s. 953-973 ISSN 0899-7667 R&D Projects: GA ČR GAP202/10/1333 Institutional support: RVO:67985807 Keywords : neural network * finite automaton * energy complexity * optimal size Subject RIV: IN - Informatics, Computer Science Impact factor: 2.207, year: 2014

Application of neural networks in CRM systems

Directory of Open Access Journals (Sweden)

Bojanowska Agnieszka

2017-01-01

Full Text Available The central aim of this study is to investigate how to apply artificial neural networks in Customer Relationship Management (CRM. The paper presents several business applications of neural networks in software systems designed to aid CRM, e.g. in deciding on the profitability of building a relationship with a given customer. Furthermore, a framework for a neural-network based CRM software tool is developed. Building beneficial relationships with customers is generating considerable interest among various businesses, and is often mentioned as one of the crucial objectives of enterprises, next to their key aim: to bring satisfactory profit. There is a growing tendency among businesses to invest in CRM systems, which together with an organisational culture of a company aid managing customer relationships. It is the sheer amount of gathered data as well as the need for constant updating and analysis of this breadth of information that may imply the suitability of neural networks for the application in question. Neural networks exhibit considerably higher computational capabilities than sequential calculations because the solution to a problem is obtained without the need for developing a special algorithm. In the majority of presented CRM applications neural networks constitute and are presented as a managerial decision-taking optimisation tool.

water demand prediction using artificial neural network

African Journals Online (AJOL)

user

2017-01-01

Jan 1, 2017 ... Interface for activation and deactivation of valves. •. Interface demand ... process could be done and monitored at the computer terminal as expected of a .... [15] Arbib, M. A.The Handbook of Brain Theory and Neural. Networks.

A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography.

Science.gov (United States)

Yang, Xiaogang; De Carlo, Francesco; Phatak, Charudatta; Gürsoy, Dogˇa

2017-03-01

This paper presents an algorithm to calibrate the center-of-rotation for X-ray tomography by using a machine learning approach, the Convolutional Neural Network (CNN). The algorithm shows excellent accuracy from the evaluation of synthetic data with various noise ratios. It is further validated with experimental data of four different shale samples measured at the Advanced Photon Source and at the Swiss Light Source. The results are as good as those determined by visual inspection and show better robustness than conventional methods. CNN has also great potential for reducing or removing other artifacts caused by instrument instability, detector non-linearity, etc. An open-source toolbox, which integrates the CNN methods described in this paper, is freely available through GitHub at tomography/xlearn and can be easily integrated into existing computational pipelines available at various synchrotron facilities. Source code, documentation and information on how to contribute are also provided.

Heterotic computing: exploiting hybrid computational devices.

Science.gov (United States)

Kendon, Viv; Sebald, Angelika; Stepney, Susan

2015-07-28

Current computational theory deals almost exclusively with single models: classical, neural, analogue, quantum, etc. In practice, researchers use ad hoc combinations, realizing only recently that they can be fundamentally more powerful than the individual parts. A Theo Murphy meeting brought together theorists and practitioners of various types of computing, to engage in combining the individual strengths to produce powerful new heterotic devices. 'Heterotic computing' is defined as a combination of two or more computational systems such that they provide an advantage over either substrate used separately. This post-meeting collection of articles provides a wide-ranging survey of the state of the art in diverse computational paradigms, together with reflections on their future combination into powerful and practical applications. © 2015 The Author(s) Published by the Royal Society. All rights reserved.

Predicting Motivation: Computational Models of PFC Can Explain Neural Coding of Motivation and Effort-based Decision-making in Health and Disease.

Science.gov (United States)

Vassena, Eliana; Deraeve, James; Alexander, William H

2017-10-01

Human behavior is strongly driven by the pursuit of rewards. In daily life, however, benefits mostly come at a cost, often requiring that effort be exerted to obtain potential benefits. Medial PFC (MPFC) and dorsolateral PFC (DLPFC) are frequently implicated in the expectation of effortful control, showing increased activity as a function of predicted task difficulty. Such activity partially overlaps with expectation of reward and has been observed both during decision-making and during task preparation. Recently, novel computational frameworks have been developed to explain activity in these regions during cognitive control, based on the principle of prediction and prediction error (predicted response-outcome [PRO] model [Alexander, W. H., & Brown, J. W. Medial prefrontal cortex as an action-outcome predictor. Nature Neuroscience, 14, 1338-1344, 2011], hierarchical error representation [HER] model [Alexander, W. H., & Brown, J. W. Hierarchical error representation: A computational model of anterior cingulate and dorsolateral prefrontal cortex. Neural Computation, 27, 2354-2410, 2015]). Despite the broad explanatory power of these models, it is not clear whether they can also accommodate effects related to the expectation of effort observed in MPFC and DLPFC. Here, we propose a translation of these computational frameworks to the domain of effort-based behavior. First, we discuss how the PRO model, based on prediction error, can explain effort-related activity in MPFC, by reframing effort-based behavior in a predictive context. We propose that MPFC activity reflects monitoring of motivationally relevant variables (such as effort and reward), by coding expectations and discrepancies from such expectations. Moreover, we derive behavioral and neural model-based predictions for healthy controls and clinical populations with impairments of motivation. Second, we illustrate the possible translation to effort-based behavior of the HER model, an extended version of PRO

Brain architecture: a design for natural computation.

Science.gov (United States)

Kaiser, Marcus

2007-12-15

Fifty years ago, John von Neumann compared the architecture of the brain with that of the computers he invented and which are still in use today. In those days, the organization of computers was based on concepts of brain organization. Here, we give an update on current results on the global organization of neural systems. For neural systems, we outline how the spatial and topological architecture of neuronal and cortical networks facilitates robustness against failures, fast processing and balanced network activation. Finally, we discuss mechanisms of self-organization for such architectures. After all, the organization of the brain might again inspire computer architecture.

Application of a Shallow Neural Network to Short-Term Stock Trading

OpenAIRE

Madahar, Abhinav; Ma, Yuze; Patel, Kunal

2017-01-01

Machine learning is increasingly prevalent in stock market trading. Though neural networks have seen success in computer vision and natural language processing, they have not been as useful in stock market trading. To demonstrate the applicability of a neural network in stock trading, we made a single-layer neural network that recommends buying or selling shares of a stock by comparing the highest high of 10 consecutive days with that of the next 10 days, a process repeated for the stock's ye...

Neural information processing in cognition: we start to understand the orchestra, but where is the conductor?

Directory of Open Access Journals (Sweden)

Guenther ePalm

2016-01-01

Full Text Available Research in neural information processing has been successful in the past, providing useful approaches both to practical problems in computer science and to computational models in neuroscience. Recent developments in the area of cognitive neuroscience present new challenges for a computational or theoretical understanding asking for neural information processing models that fulfill criteria or constraints from cognitive psychology, neuroscience and computational efficiency. The most important of these criteria for the evaluation of present and future contributions to this new emerging field are listed at the end of this article.

Neural Information Processing in Cognition: We Start to Understand the Orchestra, but Where is the Conductor?

Science.gov (United States)

Palm, Günther

2016-01-01

Research in neural information processing has been successful in the past, providing useful approaches both to practical problems in computer science and to computational models in neuroscience. Recent developments in the area of cognitive neuroscience present new challenges for a computational or theoretical understanding asking for neural information processing models that fulfill criteria or constraints from cognitive psychology, neuroscience and computational efficiency. The most important of these criteria for the evaluation of present and future contributions to this new emerging field are listed at the end of this article. PMID:26858632

Neural codes of seeing architectural styles.

Science.gov (United States)

Choo, Heeyoung; Nasar, Jack L; Nikrahei, Bardia; Walther, Dirk B

2017-01-10

Images of iconic buildings, such as the CN Tower, instantly transport us to specific places, such as Toronto. Despite the substantial impact of architectural design on people's visual experience of built environments, we know little about its neural representation in the human brain. In the present study, we have found patterns of neural activity associated with specific architectural styles in several high-level visual brain regions, but not in primary visual cortex (V1). This finding suggests that the neural correlates of the visual perception of architectural styles stem from style-specific complex visual structure beyond the simple features computed in V1. Surprisingly, the network of brain regions representing architectural styles included the fusiform face area (FFA) in addition to several scene-selective regions. Hierarchical clustering of error patterns further revealed that the FFA participated to a much larger extent in the neural encoding of architectural styles than entry-level scene categories. We conclude that the FFA is involved in fine-grained neural encoding of scenes at a subordinate-level, in our case, architectural styles of buildings. This study for the first time shows how the human visual system encodes visual aspects of architecture, one of the predominant and longest-lasting artefacts of human culture.

Pattern recognition, neural networks, genetic algorithms and high performance computing in nuclear reactor diagnostics. Results and perspectives

International Nuclear Information System (INIS)

Dzwinel, W.; Pepyolyshev, N.

1996-01-01

The main goal of this paper is the presentation of our experience in development of the diagnostic system for the IBR-2 (Russia - Dubna) nuclear reactor. The authors show the principal results of the system modifications to make it work more reliable and much faster. The former needs the adaptation of new techniques of data processing, the latter, implementation of the newest computational facilities. The results of application of the clustering techniques and a method of visualization of the multi-dimensional information directly on the operator display are presented. The experiences with neural nets, used for prediction of the reactor operation, are discussed. The genetic algorithms were also tested, to reduce the quantity of data nd extracting the most informative components of the analyzed spectra. (authors)

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.

Three neural network based sensor systems for environmental monitoring

International Nuclear Information System (INIS)

Keller, P.E.; Kouzes, R.T.; Kangas, L.J.

1994-05-01

Compact, portable systems capable of quickly identifying contaminants in the field are of great importance when monitoring the environment. One of the missions of the Pacific Northwest Laboratory is to examine and develop new technologies for environmental restoration and waste management at the Hanford Site. In this paper, three prototype sensing systems are discussed. These prototypes are composed of sensing elements, data acquisition system, computer, and neural network implemented in software, and are capable of automatically identifying contaminants. The first system employs an array of tin-oxide gas sensors and is used to identify chemical vapors. The second system employs an array of optical sensors and is used to identify the composition of chemical dyes in liquids. The third system contains a portable gamma-ray spectrometer and is used to identify radioactive isotopes. In these systems, the neural network is used to identify the composition of the sensed contaminant. With a neural network, the intense computation takes place during the training process. Once the network is trained, operation consists of propagating the data through the network. Since the computation involved during operation consists of vector-matrix multiplication and application of look-up tables unknown samples can be rapidly identified in the field

A Neural Network Approach for Inverse Kinematic of a SCARA Manipulator

Directory of Open Access Journals (Sweden)

Panchanand Jha

2014-07-01

Full Text Available Inverse kinematic is one of the most interesting problems of industrial robot. The inverse kinematics problem in robotics is about the determination of joint angles for a desired Cartesian position of the end effector. It comprises of the computation need to find the joint angles for a given Cartesian position and orientation of the end effectors to control a robot arm. There is no unique solution for the inverse kinematics thus necessitating application of appropriate predictive models from the soft computing domain. Artificial neural network is one such technique which can be gainfully used to yield the acceptable results. This paper proposes a structured artificial neural network (ANN model to find the inverse kinematics solution of a 4-dof SCARA manipulator. The ANN model used is a multi-layered perceptron neural network (MLPNN, wherein gradient descent type of learning rules is applied. An attempt has been made to find the best ANN configuration for the problem. It is found that multi-layered perceptron neural network gives minimum mean square error.

Analysis of neural data

CERN Document Server

Kass, Robert E; Brown, Emery N

2014-01-01

Continual improvements in data collection and processing have had a huge impact on brain research, producing data sets that are often large and complicated. By emphasizing a few fundamental principles, and a handful of ubiquitous techniques, Analysis of Neural Data provides a unified treatment of analytical methods that have become essential for contemporary researchers. Throughout the book ideas are illustrated with more than 100 examples drawn from the literature, ranging from electrophysiology, to neuroimaging, to behavior. By demonstrating the commonality among various statistical approaches the authors provide the crucial tools for gaining knowledge from diverse types of data. Aimed at experimentalists with only high-school level mathematics, as well as computationally-oriented neuroscientists who have limited familiarity with statistics, Analysis of Neural Data serves as both a self-contained introduction and a reference work.

Methods and procedures for the verification and validation of artificial neural networks

CERN Document Server

Taylor, Brian J

2006-01-01

Neural networks are members of a class of software that have the potential to enable intelligent computational systems capable of simulating characteristics of biological thinking and learning. This volume introduces some of the methods and techniques used for the verification and validation of neural networks and adaptive systems.

Realistic thermodynamic and statistical-mechanical measures for neural synchronization.

Science.gov (United States)

Kim, Sang-Yoon; Lim, Woochang

2014-04-15

Synchronized brain rhythms, associated with diverse cognitive functions, have been observed in electrical recordings of brain activity. Neural synchronization may be well described by using the population-averaged global potential VG in computational neuroscience. The time-averaged fluctuation of VG plays the role of a "thermodynamic" order parameter O used for describing the synchrony-asynchrony transition in neural systems. Population spike synchronization may be well visualized in the raster plot of neural spikes. The degree of neural synchronization seen in the raster plot is well measured in terms of a "statistical-mechanical" spike-based measure Ms introduced by considering the occupation and the pacing patterns of spikes. The global potential VG is also used to give a reference global cycle for the calculation of Ms. Hence, VG becomes an important collective quantity because it is associated with calculation of both O and Ms. However, it is practically difficult to directly get VG in real experiments. To overcome this difficulty, instead of VG, we employ the instantaneous population spike rate (IPSR) which can be obtained in experiments, and develop realistic thermodynamic and statistical-mechanical measures, based on IPSR, to make practical characterization of the neural synchronization in both computational and experimental neuroscience. Particularly, more accurate characterization of weak sparse spike synchronization can be achieved in terms of realistic statistical-mechanical IPSR-based measure, in comparison with the conventional measure based on VG. Copyright © 2014. Published by Elsevier B.V.

Brain architecture: A design for natural computation

OpenAIRE

Kaiser, Marcus

2008-01-01

Fifty years ago, John von Neumann compared the architecture of the brain with that of computers that he invented and which is still in use today. In those days, the organisation of computers was based on concepts of brain organisation. Here, we give an update on current results on the global organisation of neural systems. For neural systems, we outline how the spatial and topological architecture of neuronal and cortical networks facilitates robustness against failures, fast processing, and ...

Building bridges between perceptual and economic decision-making: neural and computational mechanisms

Directory of Open Access Journals (Sweden)

Christopher eSummerfield

2012-05-01

Full Text Available Investigation into the neural and computational bases of decision-making has proceeded in two parallel but distinct streams. Perceptual decision making (PDM is concerned with how observers detect, discriminate and categorise noisy sensory information. Economic decision making (EDM explores how options are selected on the basis of their reinforcement history. Traditionally, the subfields of PDM and EDM have employed different paradigms, proposed different mechanistic models, explored different brain regions, disagreed about whether decisions approach optimality. Nevertheless, we argue that there is a common framework for understanding decisions made in both domains, under which an agent has to combine sensory information (what is the stimulus with value information (what is it worth. We review computational models of the decision process typically used in PDM, based around the idea that decisions involve a serial integration of evidence, and assess their applicability to decisions between good and gambles. Subsequently, we consider the contribution of three key brain regions – the parietal cortex, the basal ganglia, and the orbitofrontal cortex – to perceptual and economic decision-making, with a focus on the mechanisms by which sensory and reward information are integrated during choice. We find that although the parietal cortex is often implicated in the integration of sensory evidence, there is evidence for its role in encoding the expected value of a decision. Similarly, although much research has emphasised the role of the striatum and orbitofrontal cortex in value-guided choices, they may play an important role in categorisation of perceptual information. In conclusion, we consider how findings from the two fields might be brought together, in order to move towards a general framework for understanding decision-making in humans and other primates.

Boosted Jet Tagging with Jet-Images and Deep Neural Networks

International Nuclear Information System (INIS)

Kagan, Michael; Oliveira, Luke de; Mackey, Lester; Nachman, Benjamin; Schwartzman, Ariel

2016-01-01

Building on the jet-image based representation of high energy jets, we develop computer vision based techniques for jet tagging through the use of deep neural networks. Jet-images enabled the connection between jet substructure and tagging with the fields of computer vision and image processing. We show how applying such techniques using deep neural networks can improve the performance to identify highly boosted W bosons with respect to state-of-the-art substructure methods. In addition, we explore new ways to extract and visualize the discriminating features of different classes of jets, adding a new capability to understand the physics within jets and to design more powerful jet tagging methods

Application of chaos and fractals to computer vision

CERN Document Server

Farmer, Michael E

2014-01-01

This book provides a thorough investigation of the application of chaos theory and fractal analysis to computer vision. The field of chaos theory has been studied in dynamical physical systems, and has been very successful in providing computational models for very complex problems ranging from weather systems to neural pathway signal propagation. Computer vision researchers have derived motivation for their algorithms from biology and physics for many years as witnessed by the optical flow algorithm, the oscillator model underlying graphical cuts and of course neural networks. These algorithm

Multispectral Image classification using the theories of neural networks

International Nuclear Information System (INIS)

Ardisasmita, M.S.; Subki, M.I.R.

1997-01-01

Image classification is the one of the important part of digital image analysis. the objective of image classification is to identify and regroup the features occurring in an image into one or several classes in terms of the object. basic to the understanding of multispectral classification is the concept of the spectral response of an object as a function of the electromagnetic radiation and the wavelength of the spectrum. new approaches to classification has been developed to improve the result of analysis, these state-of-the-art classifiers are based upon the theories of neural networks. Neural network classifiers are algorithmes which mimic the computational abilities of the human brain. Artificial neurons are simple emulation's of biological neurons; they take in information from sensors or other artificial neurons, perform very simple operations on this data, and pass the result to other recognize the spectral signature of each image pixel. Neural network image classification has been divided into supervised and unsupervised training procedures. In the supervised approach, examples of each cover type can be located and the computer can compute spectral signatures to categorize all pixels in a digital image into several land cover classes. In supervised classification, spectral signatures are generated by mathematically grouping and it does not require analyst-specified training data. Thus, in the supervised approach we define useful information categories and then examine their spectral reparability; in the unsupervised approach the computer determines spectrally sapable classes and then we define thei information value

4th International Joint Conference on Computational Intelligence

CERN Document Server

Correia, António; Rosa, Agostinho; Filipe, Joaquim

2015-01-01

The present book includes extended and revised versions of a set of selected papers from the Fourth International Joint Conference on Computational Intelligence (IJCCI 2012)., held in Barcelona, Spain, from 5 to 7 October, 2012. The conference was sponsored by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC) and was organized in cooperation with the Association for the Advancement of Artificial Intelligence (AAAI). The conference brought together researchers, engineers and practitioners in computational technologies, especially those related to the areas of fuzzy computation, evolutionary computation and neural computation. It is composed of three co-located conferences, each one specialized in one of the aforementioned -knowledge areas. Namely: - International Conference on Evolutionary Computation Theory and Applications (ECTA) - International Conference on Fuzzy Computation Theory and Applications (FCTA) - International Conference on Neural Computation Theory a...

Deep neural nets as a method for quantitative structure-activity relationships.

Science.gov (United States)

Ma, Junshui; Sheridan, Robert P; Liaw, Andy; Dahl, George E; Svetnik, Vladimir

2015-02-23

Neural networks were widely used for quantitative structure-activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone to overfitting, etc.), they were superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose in the early 2000s. The last 10 years has witnessed a revival of neural networks in the machine learning community thanks to new methods for preventing overfitting, more efficient training algorithms, and advancements in computer hardware. In particular, deep neural nets (DNNs), i.e. neural nets with more than one hidden layer, have found great successes in many applications, such as computer vision and natural language processing. Here we show that DNNs can routinely make better prospective predictions than RF on a set of large diverse QSAR data sets that are taken from Merck's drug discovery effort. The number of adjustable parameters needed for DNNs is fairly large, but our results show that it is not necessary to optimize them for individual data sets, and a single set of recommended parameters can achieve better performance than RF for most of the data sets we studied. The usefulness of the parameters is demonstrated on additional data sets not used in the calibration. Although training DNNs is still computationally intensive, using graphical processing units (GPUs) can make this issue manageable.

Event-driven simulation of neural population synchronization facilitated by electrical coupling.

Science.gov (United States)

Carrillo, Richard R; Ros, Eduardo; Barbour, Boris; Boucheny, Christian; Coenen, Olivier

2007-02-01

Most neural communication and processing tasks are driven by spikes. This has enabled the application of the event-driven simulation schemes. However the simulation of spiking neural networks based on complex models that cannot be simplified to analytical expressions (requiring numerical calculation) is very time consuming. Here we describe briefly an event-driven simulation scheme that uses pre-calculated table-based neuron characterizations to avoid numerical calculations during a network simulation, allowing the simulation of large-scale neural systems. More concretely we explain how electrical coupling can be simulated efficiently within this computation scheme, reproducing synchronization processes observed in detailed simulations of neural populations.

Emulation of Neural Networks on a Nanoscale Architecture

International Nuclear Information System (INIS)

Eshaghian-Wilner, Mary M; Friesz, Aaron; Khitun, Alex; Navab, Shiva; Parker, Alice C; Wang, Kang L; Zhou, Chongwu

2007-01-01

In this paper, we propose using a nanoscale spin-wave-based architecture for implementing neural networks. We show that this architecture can efficiently realize highly interconnected neural network models such as the Hopfield model. In our proposed architecture, no point-to-point interconnection is required, so unlike standard VLSI design, no fan-in/fan-out constraint limits the interconnectivity. Using spin-waves, each neuron could broadcast to all other neurons simultaneously and similarly a neuron could concurrently receive and process multiple data. Therefore in this architecture, the total weighted sum to each neuron can be computed by the sum of the values from all the incoming waves to that neuron. In addition, using the superposition property of waves, this computation can be done in O(1) time, and neurons can update their states quite rapidly

Projection decomposition algorithm for dual-energy computed tomography via deep neural network.

Science.gov (United States)

Xu, Yifu; Yan, Bin; Chen, Jian; Zeng, Lei; Li, Lei

2018-03-15

Dual-energy computed tomography (DECT) has been widely used to improve identification of substances from different spectral information. Decomposition of the mixed test samples into two materials relies on a well-calibrated material decomposition function. This work aims to establish and validate a data-driven algorithm for estimation of the decomposition function. A deep neural network (DNN) consisting of two sub-nets is proposed to solve the projection decomposition problem. The compressing sub-net, substantially a stack auto-encoder (SAE), learns a compact representation of energy spectrum. The decomposing sub-net with a two-layer structure fits the nonlinear transform between energy projection and basic material thickness. The proposed DNN not only delivers image with lower standard deviation and higher quality in both simulated and real data, and also yields the best performance in cases mixed with photon noise. Moreover, DNN costs only 0.4 s to generate a decomposition solution of 360 × 512 size scale, which is about 200 times faster than the competing algorithms. The DNN model is applicable to the decomposition tasks with different dual energies. Experimental results demonstrated the strong function fitting ability of DNN. Thus, the Deep learning paradigm provides a promising approach to solve the nonlinear problem in DECT.

Deciphering Neural Codes of Memory during Sleep

Science.gov (United States)

Chen, Zhe; Wilson, Matthew A.

2017-01-01

Memories of experiences are stored in the cerebral cortex. Sleep is critical for consolidating hippocampal memory of wake experiences into the neocortex. Understanding representations of neural codes of hippocampal-neocortical networks during sleep would reveal important circuit mechanisms on memory consolidation, and provide novel insights into memory and dreams. Although sleep-associated ensemble spike activity has been investigated, identifying the content of memory in sleep remains challenging. Here, we revisit important experimental findings on sleep-associated memory (i.e., neural activity patterns in sleep that reflect memory processing) and review computational approaches for analyzing sleep-associated neural codes (SANC). We focus on two analysis paradigms for sleep-associated memory, and propose a new unsupervised learning framework (“memory first, meaning later”) for unbiased assessment of SANC. PMID:28390699

Toward exascale computing through neuromorphic approaches.

Energy Technology Data Exchange (ETDEWEB)

James, Conrad D.

2010-09-01

While individual neurons function at relatively low firing rates, naturally-occurring nervous systems not only surpass manmade systems in computing power, but accomplish this feat using relatively little energy. It is asserted that the next major breakthrough in computing power will be achieved through application of neuromorphic approaches that mimic the mechanisms by which neural systems integrate and store massive quantities of data for real-time decision making. The proposed LDRD provides a conceptual foundation for SNL to make unique advances toward exascale computing. First, a team consisting of experts from the HPC, MESA, cognitive and biological sciences and nanotechnology domains will be coordinated to conduct an exercise with the outcome being a concept for applying neuromorphic computing to achieve exascale computing. It is anticipated that this concept will involve innovative extension and integration of SNL capabilities in MicroFab, material sciences, high-performance computing, and modeling and simulation of neural processes/systems.

Recent Advances in Neural Recording Microsystems

Directory of Open Access Journals (Sweden)

Benoit Gosselin

2011-04-01

Full Text Available The accelerating pace of research in neuroscience has created a considerable demand for neural interfacing microsystems capable of monitoring the activity of large groups of neurons. These emerging tools have revealed a tremendous potential for the advancement of knowledge in brain research and for the development of useful clinical applications. They can extract the relevant control signals directly from the brain enabling individuals with severe disabilities to communicate their intentions to other devices, like computers or various prostheses. Such microsystems are self-contained devices composed of a neural probe attached with an integrated circuit for extracting neural signals from multiple channels, and transferring the data outside the body. The greatest challenge facing development of such emerging devices into viable clinical systems involves addressing their small form factor and low-power consumption constraints, while providing superior resolution. In this paper, we survey the recent progress in the design and the implementation of multi-channel neural recording Microsystems, with particular emphasis on the design of recording and telemetry electronics. An overview of the numerous neural signal modalities is given and the existing microsystem topologies are covered. We present energy-efficient sensory circuits to retrieve weak signals from neural probes and we compare them. We cover data management and smart power scheduling approaches, and we review advances in low-power telemetry. Finally, we conclude by summarizing the remaining challenges and by highlighting the emerging trends in the field.

Storage capacity and retrieval time of small-world neural networks

International Nuclear Information System (INIS)

Oshima, Hiraku; Odagaki, Takashi

2007-01-01

To understand the influence of structure on the function of neural networks, we study the storage capacity and the retrieval time of Hopfield-type neural networks for four network structures: regular, small world, random networks generated by the Watts-Strogatz (WS) model, and the same network as the neural network of the nematode Caenorhabditis elegans. Using computer simulations, we find that (1) as the randomness of network is increased, its storage capacity is enhanced; (2) the retrieval time of WS networks does not depend on the network structure, but the retrieval time of C. elegans's neural network is longer than that of WS networks; (3) the storage capacity of the C. elegans network is smaller than that of networks generated by the WS model, though the neural network of C. elegans is considered to be a small-world network

Neural System Prediction and Identification Challenge

Directory of Open Access Journals (Sweden)

Ioannis eVlachos

2013-12-01

Full Text Available Can we infer the function of a biological neural network (BNN if we know the connectivity and activity of all its constituent neurons? This question is at the core of neuroscience and, accordingly, various methods have been developed to record the activity and connectivity of as many neurons as possible. Surprisingly, there is no theoretical or computational demonstration that neuronal activity and connectivity are indeed sufficient to infer the function of a BNN. Therefore, we pose the Neural Systems Identification and Prediction Challenge (nuSPIC. We provide the connectivity and activity of all neurons and invite participants (i to infer the functions implemented (hard-wired in spiking neural networks (SNNs by stimulating and recording the activity of neurons and, (ii to implement predefined mathematical/biological functions using SNNs. The nuSPICs can be accessed via a web-interface to the NEST simulator and the user is not required to know any specific programming language. Furthermore, the nuSPICs can be used as a teaching tool. Finally, nuSPICs use the crowd-sourcing model to address scientific issues. With this computational approach we aim to identify which functions can be inferred by systematic recordings of neuronal activity and connectivity. In addition, nuSPICs will help the design and application of new experimental paradigms based on the structure of the SNN and the presumed function which is to be discovered.

Neural system prediction and identification challenge.

Science.gov (United States)

Vlachos, Ioannis; Zaytsev, Yury V; Spreizer, Sebastian; Aertsen, Ad; Kumar, Arvind

2013-01-01

Can we infer the function of a biological neural network (BNN) if we know the connectivity and activity of all its constituent neurons?This question is at the core of neuroscience and, accordingly, various methods have been developed to record the activity and connectivity of as many neurons as possible. Surprisingly, there is no theoretical or computational demonstration that neuronal activity and connectivity are indeed sufficient to infer the function of a BNN. Therefore, we pose the Neural Systems Identification and Prediction Challenge (nuSPIC). We provide the connectivity and activity of all neurons and invite participants (1) to infer the functions implemented (hard-wired) in spiking neural networks (SNNs) by stimulating and recording the activity of neurons and, (2) to implement predefined mathematical/biological functions using SNNs. The nuSPICs can be accessed via a web-interface to the NEST simulator and the user is not required to know any specific programming language. Furthermore, the nuSPICs can be used as a teaching tool. Finally, nuSPICs use the crowd-sourcing model to address scientific issues. With this computational approach we aim to identify which functions can be inferred by systematic recordings of neuronal activity and connectivity. In addition, nuSPICs will help the design and application of new experimental paradigms based on the structure of the SNN and the presumed function which is to be discovered.

What the success of brain imaging implies about the neural code.

Science.gov (United States)

Guest, Olivia; Love, Bradley C

2017-01-19

The success of fMRI places constraints on the nature of the neural code. The fact that researchers can infer similarities between neural representations, despite fMRI's limitations, implies that certain neural coding schemes are more likely than others. For fMRI to succeed given its low temporal and spatial resolution, the neural code must be smooth at the voxel and functional level such that similar stimuli engender similar internal representations. Through proof and simulation, we determine which coding schemes are plausible given both fMRI's successes and its limitations in measuring neural activity. Deep neural network approaches, which have been forwarded as computational accounts of the ventral stream, are consistent with the success of fMRI, though functional smoothness breaks down in the later network layers. These results have implications for the nature of the neural code and ventral stream, as well as what can be successfully investigated with fMRI.

Low-dimensional recurrent neural network-based Kalman filter for speech enhancement.

Science.gov (United States)

Xia, Youshen; Wang, Jun

2015-07-01

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Neural networks and wavelet analysis in the computer interpretation of pulse oximetry data

Energy Technology Data Exchange (ETDEWEB)

Dowla, F.U.; Skokowski, P.G.; Leach, R.R. Jr.

1996-03-01

Pulse oximeters determine the oxygen saturation level of blood by measuring the light absorption of arterial blood. The sensor consists of red and infrared light sources and photodetectors. A method based on neural networks and wavelet analysis is developed for improved saturation estimation in the presence of sensor motion. Spectral and correlation functions of the dual channel oximetry data are used by a backpropagation neural network to characterize the type of motion. Amplitude ratios of red to infrared signals as a function of time scale are obtained from the multiresolution wavelet decomposition of the two-channel data. Motion class and amplitude ratios are then combined to obtain a short-time estimate of the oxygen saturation level. A final estimate of oxygen saturation is obtained by applying a 15 s smoothing filter on the short-time measurements based on 3.5 s windows sampled every 1.75 s. The design employs two backpropagation neural networks. The first neural network determines the motion characteristics and the second network determines the saturation estimate. Our approach utilizes waveform analysis in contrast to the standard algorithms that are based on the successful detection of peaks and troughs in the signal. The proposed algorithm is numerically efficient and has stable characteristics with a reduced false alarm rate with a small loss in detection. The method can be rapidly developed on a digital signal processing platform.

Neural Networks In Mining Sciences - General Overview And Some Representative Examples

Science.gov (United States)

Tadeusiewicz, Ryszard

2015-12-01

The many difficult problems that must now be addressed in mining sciences make us search for ever newer and more efficient computer tools that can be used to solve those problems. Among the numerous tools of this type, there are neural networks presented in this article - which, although not yet widely used in mining sciences, are certainly worth consideration. Neural networks are a technique which belongs to so called artificial intelligence, and originates from the attempts to model the structure and functioning of biological nervous systems. Initially constructed and tested exclusively out of scientific curiosity, as computer models of parts of the human brain, neural networks have become a surprisingly effective calculation tool in many areas: in technology, medicine, economics, and even social sciences. Unfortunately, they are relatively rarely used in mining sciences and mining technology. The article is intended to convince the readers that neural networks can be very useful also in mining sciences. It contains information how modern neural networks are built, how they operate and how one can use them. The preliminary discussion presented in this paper can help the reader gain an opinion whether this is a tool with handy properties, useful for him, and what it might come in useful for. Of course, the brief introduction to neural networks contained in this paper will not be enough for the readers who get convinced by the arguments contained here, and want to use neural networks. They will still need a considerable portion of detailed knowledge so that they can begin to independently create and build such networks, and use them in practice. However, an interested reader who decides to try out the capabilities of neural networks will also find here links to references that will allow him to start exploration of neural networks fast, and then work with this handy tool efficiently. This will be easy, because there are currently quite a few ready-made computer

Efficient Embedded Decoding of Neural Network Language Models in a Machine Translation System.

Science.gov (United States)

Zamora-Martinez, Francisco; Castro-Bleda, Maria Jose

2018-02-22

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

Automatic Seismic-Event Classification with Convolutional Neural Networks.

Science.gov (United States)

Bueno Rodriguez, A.; Titos Luzón, M.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

2017-12-01

Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and

FIRST Quantum-(1980)-Computing DISCOVERY in Siegel-Rosen-Feynman-...A.-I. Neural-Networks: Artificial(ANN)/Biological(BNN) and Siegel FIRST Semantic-Web and Siegel FIRST ``Page''-``Brin'' ``PageRank'' PRE-Google Search-Engines!!!

Science.gov (United States)

Rosen, Charles; Siegel, Edward Carl-Ludwig; Feynman, Richard; Wunderman, Irwin; Smith, Adolph; Marinov, Vesco; Goldman, Jacob; Brine, Sergey; Poge, Larry; Schmidt, Erich; Young, Frederic; Goates-Bulmer, William-Steven; Lewis-Tsurakov-Altshuler, Thomas-Valerie-Genot; Ibm/Exxon Collaboration; Google/Uw Collaboration; Microsoft/Amazon Collaboration; Oracle/Sun Collaboration; Ostp/Dod/Dia/Nsa/W.-F./Boa/Ubs/Ub Collaboration

2013-03-01

Belew[Finding Out About, Cambridge(2000)] and separately full-decade pre-Page/Brin/Google FIRST Siegel-Rosen(Machine-Intelligence/Atherton)-Feynman-Smith-Marinov(Guzik Enterprises/Exxon-Enterprises/A.-I./Santa Clara)-Wunderman(H.-P.) [IBM Conf. on Computers and Mathematics, Stanford(1986); APS Mtgs.(1980s): Palo Alto/Santa Clara/San Francisco/...(1980s) MRS Spring-Mtgs.(1980s): Palo Alto/San Jose/San Francisco/...(1980-1992) FIRST quantum-computing via Bose-Einstein quantum-statistics(BEQS) Bose-Einstein CONDENSATION (BEC) in artificial-intelligence(A-I) artificial neural-networks(A-N-N) and biological neural-networks(B-N-N) and Siegel[J. Noncrystalline-Solids 40, 453(1980); Symp. on Fractals..., MRS Fall-Mtg., Boston(1989)-5-papers; Symp. on Scaling..., (1990); Symp. on Transport in Geometric-Constraint (1990)

Using Artificial Neural Networks in Educational Research: Some Comparisons with Linear Statistical Models.

Science.gov (United States)

Everson, Howard T.; And Others

This paper explores the feasibility of neural computing methods such as artificial neural networks (ANNs) and abductory induction mechanisms (AIM) for use in educational measurement. ANNs and AIMS methods are contrasted with more traditional statistical techniques, such as multiple regression and discriminant function analyses, for making…

Matching Behavior as a Tradeoff Between Reward Maximization and Demands on Neural Computation [version 2; referees: 2 approved

Directory of Open Access Journals (Sweden)

Jan Kubanek

2015-10-01

Full Text Available When faced with a choice, humans and animals commonly distribute their behavior in proportion to the frequency of payoff of each option. Such behavior is referred to as matching and has been captured by the matching law. However, matching is not a general law of economic choice. Matching in its strict sense seems to be specifically observed in tasks whose properties make matching an optimal or a near-optimal strategy. We engaged monkeys in a foraging task in which matching was not the optimal strategy. Over-matching the proportions of the mean offered reward magnitudes would yield more reward than matching, yet, surprisingly, the animals almost exactly matched them. To gain insight into this phenomenon, we modeled the animals' decision-making using a mechanistic model. The model accounted for the animals' macroscopic and microscopic choice behavior. When the models' three parameters were not constrained to mimic the monkeys' behavior, the model over-matched the reward proportions and in doing so, harvested substantially more reward than the monkeys. This optimized model revealed a marked bottleneck in the monkeys' choice function that compares the value of the two options. The model featured a very steep value comparison function relative to that of the monkeys. The steepness of the value comparison function had a profound effect on the earned reward and on the level of matching. We implemented this value comparison function through responses of simulated biological neurons. We found that due to the presence of neural noise, steepening the value comparison requires an exponential increase in the number of value-coding neurons. Matching may be a compromise between harvesting satisfactory reward and the high demands placed by neural noise on optimal neural computation.

Back propagation and Monte Carlo algorithms for neural network computations

International Nuclear Information System (INIS)

Junczys, R.; Wit, R.

1996-01-01

Results of teaching procedures for neural network for two different algorithms are presented. The first one is based on the well known back-propagation technique, the second is an adopted version of the Monte Carlo global minimum seeking method. Combination of these two, different in nature, approaches provides promising results. (author) nature, approaches provides promising results. (author)

Large-scale simulations of plastic neural networks on neuromorphic hardware

Directory of Open Access Journals (Sweden)

James Courtney Knight

2016-04-01

Full Text Available SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 20000 neurons and 51200000 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models.

Electrocardiogram (ECG Signal Modeling and Noise Reduction Using Hopfield Neural Networks

Directory of Open Access Journals (Sweden)

F. Bagheri

2013-02-01

Full Text Available The Electrocardiogram (ECG signal is one of the diagnosing approaches to detect heart disease. In this study the Hopfield Neural Network (HNN is applied and proposed for ECG signal modeling and noise reduction. The Hopfield Neural Network (HNN is a recurrent neural network that stores the information in a dynamic stable pattern. This algorithm retrieves a pattern stored in memory in response to the presentation of an incomplete or noisy version of that pattern. Computer simulation results show that this method can successfully model the ECG signal and remove high-frequency noise.

A locality aware convolutional neural networks accelerator

NARCIS (Netherlands)

Shi, R.; Xu, Z.; Sun, Z.; Peemen, M.C.J.; Li, A.; Corporaal, H.; Wu, D.

2015-01-01

The advantages of Convolutional Neural Networks (CNNs) with respect to traditional methods for visual pattern recognition have changed the field of machine vision. The main issue that hinders broad adoption of this technique is the massive computing workload in CNN that prevents real-time

Localizing Tortoise Nests by Neural Networks.

Directory of Open Access Journals (Sweden)

Roberto Barbuti

Full Text Available The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating. Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN. We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours, the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition.

Precision Scaling of Neural Networks for Efficient Audio Processing

OpenAIRE

Ko, Jong Hwan; Fromm, Josh; Philipose, Matthai; Tashev, Ivan; Zarar, Shuayb

2017-01-01

While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of neural networks on the performance of two common audio processing tasks, namely, voice-activity detection and single-channel speech enhancement. We determine the optimal pair of weight/neuron bit precision by exploring its impact on both the performance and ...

A neural network based computational model to predict the output power of different types of photovoltaic cells.

Science.gov (United States)

Xiao, WenBo; Nazario, Gina; Wu, HuaMing; Zhang, HuaMing; Cheng, Feng

2017-01-01

In this article, we introduced an artificial neural network (ANN) based computational model to predict the output power of three types of photovoltaic cells, mono-crystalline (mono-), multi-crystalline (multi-), and amorphous (amor-) crystalline. The prediction results are very close to the experimental data, and were also influenced by numbers of hidden neurons. The order of the solar generation power output influenced by the external conditions from smallest to biggest is: multi-, mono-, and amor- crystalline silicon cells. In addition, the dependences of power prediction on the number of hidden neurons were studied. For multi- and amorphous crystalline cell, three or four hidden layer units resulted in the high correlation coefficient and low MSEs. For mono-crystalline cell, the best results were achieved at the hidden layer unit of 8.

A neural network based computational model to predict the output power of different types of photovoltaic cells.

Directory of Open Access Journals (Sweden)

WenBo Xiao

Full Text Available In this article, we introduced an artificial neural network (ANN based computational model to predict the output power of three types of photovoltaic cells, mono-crystalline (mono-, multi-crystalline (multi-, and amorphous (amor- crystalline. The prediction results are very close to the experimental data, and were also influenced by numbers of hidden neurons. The order of the solar generation power output influenced by the external conditions from smallest to biggest is: multi-, mono-, and amor- crystalline silicon cells. In addition, the dependences of power prediction on the number of hidden neurons were studied. For multi- and amorphous crystalline cell, three or four hidden layer units resulted in the high correlation coefficient and low MSEs. For mono-crystalline cell, the best results were achieved at the hidden layer unit of 8.

System and method for determining stability of a neural system

Science.gov (United States)

Curtis, Steven A. (Inventor)

2011-01-01

Disclosed are methods, systems, and computer-readable media for determining stability of a neural system. The method includes tracking a function world line of an N element neural system within at least one behavioral space, determining whether the tracking function world line is approaching a psychological stability surface, and implementing a quantitative solution that corrects instability if the tracked function world line is approaching the psychological stability surface.

Neural networks prove effective at NOx reduction

Energy Technology Data Exchange (ETDEWEB)

Radl, B.J. [Pegasus Technologies, Mentor, OH (USA)

2000-05-01

The availability of low cost computer hardware and software is opening up possibilities for the use of artificial intelligence concepts, notably neural networks, in power plant control applications, delivering lower costs, greater efficiencies and reduced emissions. One example of a neural network system is the NeuSIGHT combustion optimisation system, developed by Pegasus Technologies, a subsidiary of KFx Inc. It can help reduce NOx emissions, improve heat rate and enable either deferral or elimination of capital expenditures. on other NOx control technologies, such as low NOx burners, SNCR and SCR. This paper illustrates these benefits using three recent case studies. 4 figs.

Avoiding object by robot using neural network

International Nuclear Information System (INIS)

Prasetijo, D.W.

1997-01-01

A Self controlling robot is necessary in the robot application in which operator control is difficult. Serial method such as process on the computer of van newman is difficult to be applied for self controlling robot. In this research, Neural network system for robotic control system was developed by performance expanding at the SCARA. In this research, it was shown that SCARA with application at Neural network system can avoid blocking objects without influence by number and density of the blocking objects, also departure and destination paint. robot developed by this study also can control its moving by self

Development of neural network for analysis of local power distributions in BWR fuel bundles

International Nuclear Information System (INIS)

Tanabe, Akira; Yamamoto, Toru; Shinfuku, Kimihiro; Nakamae, Takuji.

1993-01-01

A neural network model has been developed to learn the local power distributions in a BWR fuel bundle. A two layers neural network with total 128 elements is used for this model. The neural network learns 33 cases of local power peaking factors of fuel rods with given enrichment distribution as the teacher signals, which were calculated by a fuel bundle nuclear analysis code based on precise physical models. This neural network model studied well the teacher signals within 1 % error. It is also able to calculate the local power distributions within several % error for the different enrichment distributions from the teacher signals when the average enrichment is close to 2 %. This neural network is simple and the computing speed of this model is 300 times faster than that of the precise nuclear analysis code. This model was applied to survey the enrichment distribution to meet a target local power distribution in a fuel bundle, and the enrichment distribution with flat power shape are obtained within short computing time. (author)

A neural approach for the numerical modeling of two-dimensional magnetic hysteresis

International Nuclear Information System (INIS)

Cardelli, E.; Faba, A.; Laudani, A.; Riganti Fulginei, F.; Salvini, A.

2015-01-01

This paper deals with a neural network approach to model magnetic hysteresis at macro-magnetic scale. Such approach to the problem seems promising in order to couple the numerical treatment of magnetic hysteresis to FEM numerical solvers of the Maxwell's equations in time domain, as in case of the non-linear dynamic analysis of electrical machines, and other similar devices, making possible a full computer simulation in a reasonable time. The neural system proposed consists of four inputs representing the magnetic field and the magnetic inductions components at each time step and it is trained by 2-d measurements performed on the magnetic material to be modeled. The magnetic induction B is assumed as entry point and the output of the neural system returns the predicted value of the field H at the same time step. A suitable partitioning of the neural system, described in the paper, makes the computing process rather fast. Validations with experimental tests and simulations for non-symmetric and minor loops are presented

Face recognition: a convolutional neural-network approach.

Science.gov (United States)

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Neural-fuzzy control of adept one SCARA

International Nuclear Information System (INIS)

Er, M.J.; Toh, B.H.; Toh, B.Y.

1998-01-01

This paper presents an Intelligent Control Strategy for the Adept One SCARA (Selective Compliance Assembly Robot Arm). It covers the design and simulation study of a Neural-Fuzzy Controller (NFC) for the SCARA with a view of tracking a predetermined trajectory of motion in the joint space. The SCARA was simulated as a three-axis manipulator with the dynamics of the tool (fourth link) neglected and the mass of the load incorporated into the mass of the third link. The overall performance of the control system under different conditions, namely variation in playload, variations in coefficients of static, dynamic and viscous friction and different trajectories were studied and comparison made with an existing Neural Network Controller and two Computed Torque Controllers. The NFC was shown to be robust and is able to overcome the drawback of the existing Neural Network Controller

Computational neurogenetic modeling

CERN Document Server

Benuskova, Lubica

2010-01-01

Computational Neurogenetic Modeling is a student text, introducing the scope and problems of a new scientific discipline - Computational Neurogenetic Modeling (CNGM). CNGM is concerned with the study and development of dynamic neuronal models for modeling brain functions with respect to genes and dynamic interactions between genes. These include neural network models and their integration with gene network models. This new area brings together knowledge from various scientific disciplines, such as computer and information science, neuroscience and cognitive science, genetics and molecular biol

Deep Neural Network-Based Chinese Semantic Role Labeling

Institute of Scientific and Technical Information of China (English)

ZHENG Xiaoqing; CHEN Jun; SHANG Guoqiang

2017-01-01

A recent trend in machine learning is to use deep architec-tures to discover multiple levels of features from data, which has achieved impressive results on various natural language processing (NLP) tasks. We propose a deep neural network-based solution to Chinese semantic role labeling (SRL) with its application on message analysis. The solution adopts a six-step strategy: text normalization, named entity recognition (NER), Chinese word segmentation and part-of-speech (POS) tagging, theme classification, SRL, and slot filling. For each step, a novel deep neural network - based model is designed and optimized, particularly for smart phone applications. Ex-periment results on all the NLP sub - tasks of the solution show that the proposed neural networks achieve state-of-the-art performance with the minimal computational cost. The speed advantage of deep neural networks makes them more competitive for large-scale applications or applications requir-ing real-time response, highlighting the potential of the pro-posed solution for practical NLP systems.

Nano-topography Enhances Communication in Neural Cells Networks

KAUST Repository

Onesto, V.

2017-08-23

Neural cells are the smallest building blocks of the central and peripheral nervous systems. Information in neural networks and cell-substrate interactions have been heretofore studied separately. Understanding whether surface nano-topography can direct nerve cells assembly into computational efficient networks may provide new tools and criteria for tissue engineering and regenerative medicine. In this work, we used information theory approaches and functional multi calcium imaging (fMCI) techniques to examine how information flows in neural networks cultured on surfaces with controlled topography. We found that substrate roughness Sa affects networks topology. In the low nano-meter range, S-a = 0-30 nm, information increases with Sa. Moreover, we found that energy density of a network of cells correlates to the topology of that network. This reinforces the view that information, energy and surface nano-topography are tightly inter-connected and should not be neglected when studying cell-cell interaction in neural tissue repair and regeneration.

Architecture and biological applications of artificial neural networks: a tuberculosis perspective.

Science.gov (United States)

Darsey, Jerry A; Griffin, William O; Joginipelli, Sravanthi; Melapu, Venkata Kiran

2015-01-01

Advancement of science and technology has prompted researchers to develop new intelligent systems that can solve a variety of problems such as pattern recognition, prediction, and optimization. The ability of the human brain to learn in a fashion that tolerates noise and error has attracted many researchers and provided the starting point for the development of artificial neural networks: the intelligent systems. Intelligent systems can acclimatize to the environment or data and can maximize the chances of success or improve the efficiency of a search. Due to massive parallelism with large numbers of interconnected processers and their ability to learn from the data, neural networks can solve a variety of challenging computational problems. Neural networks have the ability to derive meaning from complicated and imprecise data; they are used in detecting patterns, and trends that are too complex for humans, or other computer systems. Solutions to the toughest problems will not be found through one narrow specialization; therefore we need to combine interdisciplinary approaches to discover the solutions to a variety of problems. Many researchers in different disciplines such as medicine, bioinformatics, molecular biology, and pharmacology have successfully applied artificial neural networks. This chapter helps the reader in understanding the basics of artificial neural networks, their applications, and methodology; it also outlines the network learning process and architecture. We present a brief outline of the application of neural networks to medical diagnosis, drug discovery, gene identification, and protein structure prediction. We conclude with a summary of the results from our study on tuberculosis data using neural networks, in diagnosing active tuberculosis, and predicting chronic vs. infiltrative forms of tuberculosis.

Proceedings of the Neural Network Workshop for the Hanford Community

Energy Technology Data Exchange (ETDEWEB)

Keller, P.E.

1994-01-01

These proceedings were generated from a series of presentations made at the Neural Network Workshop for the Hanford Community. The abstracts and viewgraphs of each presentation are reproduced in these proceedings. This workshop was sponsored by the Computing and Information Sciences Department in the Molecular Science Research Center (MSRC) at the Pacific Northwest Laboratory (PNL). Artificial neural networks constitute a new information processing technology that is destined within the next few years, to provide the world with a vast array of new products. A major reason for this is that artificial neural networks are able to provide solutions to a wide variety of complex problems in a much simpler fashion than is possible using existing techniques. In recognition of these capabilities, many scientists and engineers are exploring the potential application of this new technology to their fields of study. An artificial neural network (ANN) can be a software simulation, an electronic circuit, optical system, or even an electro-chemical system designed to emulate some of the brain`s rudimentary structure as well as some of the learning processes that are believed to take place in the brain. For a very wide range of applications in science, engineering, and information technology, ANNs offer a complementary and potentially superior approach to that provided by conventional computing and conventional artificial intelligence. This is because, unlike conventional computers, which have to be programmed, ANNs essentially learn from experience and can be trained in a straightforward fashion to carry out tasks ranging from the simple to the highly complex.

Neural substrate expansion for the restoration of brain function

Directory of Open Access Journals (Sweden)

Han-Chiao Isaac Chen

2016-01-01

Full Text Available Restoring neurological and cognitive function in individuals who have suffered brain damage is one of the principal objectives of modern translational neuroscience. Electrical stimulation approaches, such as deep-brain stimulation, have achieved the most clinical success, but they ultimately may be limited by the computational capacity of the residual cerebral circuitry. An alternative strategy is brain substrate expansion, in which the computational capacity of the brain is augmented through the addition of new processing units and the reconstitution of network connectivity. This latter approach has been explored to some degree using both biological and electronic means but thus far has not demonstrated the ability to reestablish the function of large-scale neuronal networks. In this review, we contend that fulfilling the potential of brain substrate expansion will require a significant shift from current methods that emphasize direct manipulations of the brain (e.g., injections of cellular suspensions and the implantation of multi-electrode arrays to the generation of more sophisticated neural tissues and neural-electric hybrids in vitro that are subsequently transplanted into the brain. Drawing from neural tissue engineering, stem cell biology, and neural interface technologies, this strategy makes greater use of the manifold techniques available in the laboratory to create biocompatible constructs that recapitulate brain architecture and thus are more easily recognized and utilized by brain networks.

Neural networks for genetic epidemiology: past, present, and future

Directory of Open Access Journals (Sweden)

Motsinger-Reif Alison A

2008-07-01

Full Text Available Abstract During the past two decades, the field of human genetics has experienced an information explosion. The completion of the human genome project and the development of high throughput SNP technologies have created a wealth of data; however, the analysis and interpretation of these data have created a research bottleneck. While technology facilitates the measurement of hundreds or thousands of genes, statistical and computational methodologies are lacking for the analysis of these data. New statistical methods and variable selection strategies must be explored for identifying disease susceptibility genes for common, complex diseases. Neural networks (NN are a class of pattern recognition methods that have been successfully implemented for data mining and prediction in a variety of fields. The application of NN for statistical genetics studies is an active area of research. Neural networks have been applied in both linkage and association analysis for the identification of disease susceptibility genes. In the current review, we consider how NN have been used for both linkage and association analyses in genetic epidemiology. We discuss both the successes of these initial NN applications, and the questions that arose during the previous studies. Finally, we introduce evolutionary computing strategies, Genetic Programming Neural Networks (GPNN and Grammatical Evolution Neural Networks (GENN, for using NN in association studies of complex human diseases that address some of the caveats illuminated by previous work.

An introduction to neural networks surgery, a field of neuromodulation which is based on advances in neural networks science and digitised brain imaging.

Science.gov (United States)

Sakas, D E; Panourias, I G; Simpson, B A

2007-01-01

Operative Neuromodulation is the field of altering electrically or chemically the signal transmission in the nervous system by implanted devices in order to excite, inhibit or tune the activities of neurons or neural networks and produce therapeutic effects. The present article reviews relevant literature on procedures or devices applied either in contact with the cerebral cortex or cranial nerves or in deep sites inside the brain in order to treat various refractory neurological conditions such as: a) chronic pain (facial, somatic, deafferentation, phantom limb), b) movement disorders (Parkinson's disease, dystonia, Tourette syndrome), c) epilepsy, d) psychiatric disease, e) hearing deficits, and f) visual loss. These data indicate that in operative neuromodulation, a new field emerges that is based on neural networks research and on advances in digitised stereometric brain imaging which allow precise localisation of cerebral neural networks and their relay stations; this field can be described as Neural networks surgery because it aims to act extrinsically or intrinsically on neural networks and to alter therapeutically the neural signal transmission with the use of implantable electrical or electronic devices. The authors also review neurotechnology literature relevant to neuroengineering, nanotechnologies, brain computer interfaces, hybrid cultured probes, neuromimetics, neuroinformatics, neurocomputation, and computational neuromodulation; the latter field is dedicated to the study of the biophysical and mathematical characteristics of electrochemical neuromodulation. The article also brings forward particularly interesting lines of research such as the carbon nanofibers electrode arrays for simultaneous electrochemical recording and stimulation, closed-loop systems for responsive neuromodulation, and the intracortical electrodes for restoring hearing or vision. The present review of cerebral neuromodulatory procedures highlights the transition from the

Novel quantum inspired binary neural network algorithm

Indian Academy of Sciences (India)

This parameter is taken as the threshold of neuron for learning of neural network. This algorithm is tested with three benchmark datasets and ... Author Affiliations. OM PRAKASH PATEL1 ARUNA TIWARI. Department of Computer Science and Engineering, Indian Institute of Technology Indore, Indore 453552, India ...

Neural networks for perception human and machine perception

CERN Document Server

Wechsler, Harry

1991-01-01

Neural Networks for Perception, Volume 1: Human and Machine Perception focuses on models for understanding human perception in terms of distributed computation and examples of PDP models for machine perception. This book addresses both theoretical and practical issues related to the feasibility of both explaining human perception and implementing machine perception in terms of neural network models. The book is organized into two parts. The first part focuses on human perception. Topics on network model ofobject recognition in human vision, the self-organization of functional architecture in t

Artificial Neural Networks and the Mass Appraisal of Real Estate

Directory of Open Access Journals (Sweden)

Gang Zhou

2018-03-01

Full Text Available With the rapid development of computer, artificial intelligence and big data technology, artificial neural networks have become one of the most powerful machine learning algorithms. In the practice, most of the applications of artificial neural networks use back propagation neural network and its variation. Besides the back propagation neural network, various neural networks have been developing in order to improve the performance of standard models. Though neural networks are well known method in the research of real estate, there is enormous space for future research in order to enhance their function. Some scholars combine genetic algorithm, geospatial information, support vector machine model, particle swarm optimization with artificial neural networks to appraise the real estate, which is helpful for the existing appraisal technology. The mass appraisal of real estate in this paper includes the real estate valuation in the transaction and the tax base valuation in the real estate holding. In this study we focus on the theoretical development of artificial neural networks and mass appraisal of real estate, artificial neural networks model evolution and algorithm improvement, artificial neural networks practice and application, and review the existing literature about artificial neural networks and mass appraisal of real estate. Finally, we provide some suggestions for the mass appraisal of China's real estate.

ChainMail based neural dynamics modeling of soft tissue deformation for surgical simulation.

Science.gov (United States)

Zhang, Jinao; Zhong, Yongmin; Smith, Julian; Gu, Chengfan

2017-07-20

Realistic and real-time modeling and simulation of soft tissue deformation is a fundamental research issue in the field of surgical simulation. In this paper, a novel cellular neural network approach is presented for modeling and simulation of soft tissue deformation by combining neural dynamics of cellular neural network with ChainMail mechanism. The proposed method formulates the problem of elastic deformation into cellular neural network activities to avoid the complex computation of elasticity. The local position adjustments of ChainMail are incorporated into the cellular neural network as the local connectivity of cells, through which the dynamic behaviors of soft tissue deformation are transformed into the neural dynamics of cellular neural network. Experiments demonstrate that the proposed neural network approach is capable of modeling the soft tissues' nonlinear deformation and typical mechanical behaviors. The proposed method not only improves ChainMail's linear deformation with the nonlinear characteristics of neural dynamics but also enables the cellular neural network to follow the principle of continuum mechanics to simulate soft tissue deformation.

SOLAR PHOTOVOLTAIC OUTPUT POWER FORECASTING USING BACK PROPAGATION NEURAL NETWORK

Directory of Open Access Journals (Sweden)

B. Jency Paulin

2016-01-01

Full Text Available Solar Energy is an important renewable and unlimited source of energy. Solar photovoltaic power forecasting, is an estimation of the expected power production, that help the grid operators to better manage the electric balance between power demand and supply. Neural network is a computational model that can predict new outcomes from past trends. The artificial neural network is used for photovoltaic plant energy forecasting. The output power for solar photovoltaic cell is predicted on hourly basis. In historical dataset collection process, two dataset was collected and used for analysis. The dataset was provided with three independent attributes and one dependent attributes. The implementation of Artificial Neural Network structure is done by Multilayer Perceptron (MLP and training procedure for neural network is done by error Back Propagation (BP. In order to train and test the neural network, the datasets are divided in the ratio 70:30. The accuracy of prediction can be done by using various error measurement criteria and the performance of neural network is to be noted.

File access prediction using neural networks.

Science.gov (United States)

Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar

2010-06-01

One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors.

Spiking neural networks on high performance computer clusters

Science.gov (United States)

Chen, Chong; Taha, Tarek M.

2011-09-01

In this paper we examine the acceleration of two spiking neural network models on three clusters of multicore processors representing three categories of processors: x86, STI Cell, and NVIDIA GPGPUs. The x86 cluster utilized consists of 352 dualcore AMD Opterons, the Cell cluster consists of 320 Sony Playstation 3s, while the GPGPU cluster contains 32 NVIDIA Tesla S1070 systems. The results indicate that the GPGPU platform can dominate in performance compared to the Cell and x86 platforms examined. From a cost perspective, the GPGPU is more expensive in terms of neuron/s throughput. If the cost of GPGPUs go down in the future, this platform will become very cost effective for these models.

Organic Computing

CERN Document Server

Würtz, Rolf P

2008-01-01

Organic Computing is a research field emerging around the conviction that problems of organization in complex systems in computer science, telecommunications, neurobiology, molecular biology, ethology, and possibly even sociology can be tackled scientifically in a unified way. From the computer science point of view, the apparent ease in which living systems solve computationally difficult problems makes it inevitable to adopt strategies observed in nature for creating information processing machinery. In this book, the major ideas behind Organic Computing are delineated, together with a sparse sample of computational projects undertaken in this new field. Biological metaphors include evolution, neural networks, gene-regulatory networks, networks of brain modules, hormone system, insect swarms, and ant colonies. Applications are as diverse as system design, optimization, artificial growth, task allocation, clustering, routing, face recognition, and sign language understanding.

Medical image segmentation by means of constraint satisfaction neural network

International Nuclear Information System (INIS)

Chen, C.T.; Tsao, C.K.; Lin, W.C.

1990-01-01

This paper applies the concept of constraint satisfaction neural network (CSNN) to the problem of medical image segmentation. Constraint satisfaction (or constraint propagation), the procedure to achieve global consistency through local computation, is an important paradigm in artificial intelligence. CSNN can be viewed as a three-dimensional neural network, with the two-dimensional image matrix as its base, augmented by various constraint labels for each pixel. These constraint labels can be interpreted as the connections and the topology of the neural network. Through parallel and iterative processes, the CSNN will approach a solution that satisfies the given constraints thus providing segmented regions with global consistency

Error Concealment using Neural Networks for Block-Based Image Coding

Directory of Open Access Journals (Sweden)

M. Mokos

2006-06-01

Full Text Available In this paper, a novel adaptive error concealment (EC algorithm, which lowers the requirements for channel coding, is proposed. It conceals errors in block-based image coding systems by using neural network. In this proposed algorithm, only the intra-frame information is used for reconstruction of the image with separated damaged blocks. The information of pixels surrounding a damaged block is used to recover the errors using the neural network models. Computer simulation results show that the visual quality and the MSE evaluation of a reconstructed image are significantly improved using the proposed EC algorithm. We propose also a simple non-neural approach for comparison.

Single neuron computation

CERN Document Server

McKenna, Thomas M; Zornetzer, Steven F

1992-01-01

This book contains twenty-two original contributions that provide a comprehensive overview of computational approaches to understanding a single neuron structure. The focus on cellular-level processes is twofold. From a computational neuroscience perspective, a thorough understanding of the information processing performed by single neurons leads to an understanding of circuit- and systems-level activity. From the standpoint of artificial neural networks (ANNs), a single real neuron is as complex an operational unit as an entire ANN, and formalizing the complex computations performed by real n

Computation and control with neural nets

Energy Technology Data Exchange (ETDEWEB)

Corneliusen, A.; Terdal, P.; Knight, T.; Spencer, J.

1989-10-04

As energies have increased exponentially with time so have the size and complexity of accelerators and control systems. NN may offer the kinds of improvements in computation and control that are needed to maintain acceptable functionality. For control their associative characteristics could provide signal conversion or data translation. Because they can do any computation such as least squares, they can close feedback loops autonomously to provide intelligent control at the point of action rather than at a central location that requires transfers, conversions, hand-shaking and other costly repetitions like input protection. Both computation and control can be integrated on a single chip, printed circuit or an optical equivalent that is also inherently faster through full parallel operation. For such reasons one expects lower costs and better results. Such systems could be optimized by integrating sensor and signal processing functions. Distributed nets of such hardware could communicate and provide global monitoring and multiprocessing in various ways e.g. via token, slotted or parallel rings (or Steiner trees) for compatibility with existing systems. Problems and advantages of this approach such as an optimal, real-time Turing machine are discussed. Simple examples are simulated and hardware implemented using discrete elements that demonstrate some basic characteristics of learning and parallelism. Future microprocessors' are predicted and requested on this basis. 19 refs., 18 figs.

Computation and control with neural nets

International Nuclear Information System (INIS)

Corneliusen, A.; Terdal, P.; Knight, T.; Spencer, J.

1989-01-01

As energies have increased exponentially with time so have the size and complexity of accelerators and control systems. NN may offer the kinds of improvements in computation and control that are needed to maintain acceptable functionality. For control their associative characteristics could provide signal conversion or data translation. Because they can do any computation such as least squares, they can close feedback loops autonomously to provide intelligent control at the point of action rather than at a central location that requires transfers, conversions, hand-shaking and other costly repetitions like input protection. Both computation and control can be integrated on a single chip, printed circuit or an optical equivalent that is also inherently faster through full parallel operation. For such reasons one expects lower costs and better results. Such systems could be optimized by integrating sensor and signal processing functions. Distributed nets of such hardware could communicate and provide global monitoring and multiprocessing in various ways e.g. via token, slotted or parallel rings (or Steiner trees) for compatibility with existing systems. Problems and advantages of this approach such as an optimal, real-time Turing machine are discussed. Simple examples are simulated and hardware implemented using discrete elements that demonstrate some basic characteristics of learning and parallelism. Future 'microprocessors' are predicted and requested on this basis. 19 refs., 18 figs

Diagnostic Neural Network Systems for the Electronic Circuits

International Nuclear Information System (INIS)

Mohamed, A.H.

2014-01-01

Neural Networks is one of the most important artificial intelligent approaches for solving the diagnostic processes. This research concerns with uses the neural networks for diagnosis of the electronic circuits. Modern electronic systems contain both the analog and digital circuits. But, diagnosis of the analog circuits suffers from great complexity due to their nonlinearity. To overcome this problem, the proposed system introduces a diagnostic system that uses the neural network to diagnose both the digital and analog circuits. So, it can face the new requirements for the modern electronic systems. A fault dictionary method was implemented in the system. Experimental results are presented on three electronic systems. They are: artificial kidney, wireless network and personal computer systems. The proposed system has improved the performance of the diagnostic systems when applied for these practical cases

Theoretical Computer Science

DEFF Research Database (Denmark)

2002-01-01

The proceedings contains 8 papers from the Conference on Theoretical Computer Science. Topics discussed include: query by committee, linear separation and random walks; hardness results for neural network approximation problems; a geometric approach to leveraging weak learners; mind change...

Robust Adaptive Neural Control of Morphing Aircraft with Prescribed Performance

Directory of Open Access Journals (Sweden)

Zhonghua Wu

2017-01-01

Full Text Available This study proposes a low-computational composite adaptive neural control scheme for the longitudinal dynamics of a swept-back wing aircraft subject to parameter uncertainties. To efficiently release the constraint often existing in conventional neural designs, whose closed-loop stability analysis always necessitates that neural networks (NNs be confined in the active regions, a smooth switching function is presented to conquer this issue. By integrating minimal learning parameter (MLP technique, prescribed performance control, and a kind of smooth switching strategy into back-stepping design, a new composite switching adaptive neural prescribed performance control scheme is proposed and a new type of adaptive laws is constructed for the altitude subsystem. Compared with previous neural control scheme for flight vehicle, the remarkable feature is that the proposed controller not only achieves the prescribed performance including transient and steady property but also addresses the constraint on NN. Two comparative simulations are presented to verify the effectiveness of the proposed controller.

Neural networks and their potential application in nuclear power plants

International Nuclear Information System (INIS)

Uhrig, R.E.

1991-01-01

A neural network is a data processing system consisting of a number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. Neural networks have emerged in the past few years as an area of unusual opportunity for research, development and application to a variety of real world problems. Indeed, neural networks exhibit characteristics and capabilities not provided by any other technology. Examples include reading Japanese Kanji characters and human handwriting, reading a typewritten manuscript aloud, compensating for alignment errors in robots, interpreting very noise signals (e.g., electroencephalograms), modeling complex systems that cannot be modeled mathematically, and predicting whether proposed loans will be good or fail. This paper presents a brief tutorial on neural networks and describes research on the potential applications to nuclear power plants

Beyond excitation/inhibition imbalance in multidimensional models of neural circuit changes in brain disorders.

Science.gov (United States)

O'Donnell, Cian; Gonçalves, J Tiago; Portera-Cailliau, Carlos; Sejnowski, Terrence J

2017-10-11

A leading theory holds that neurodevelopmental brain disorders arise from imbalances in excitatory and inhibitory (E/I) brain circuitry. However, it is unclear whether this one-dimensional model is rich enough to capture the multiple neural circuit alterations underlying brain disorders. Here, we combined computational simulations with analysis of in vivo two-photon Ca 2+ imaging data from somatosensory cortex of Fmr1 knock-out (KO) mice, a model of Fragile-X Syndrome, to test the E/I imbalance theory. We found that: (1) The E/I imbalance model cannot account for joint alterations in the observed neural firing rates and correlations; (2) Neural circuit function is vastly more sensitive to changes in some cellular components over others; (3) The direction of circuit alterations in Fmr1 KO mice changes across development. These findings suggest that the basic E/I imbalance model should be updated to higher dimensional models that can better capture the multidimensional computational functions of neural circuits.

Synthetic Computation: Chaos Computing, Logical Stochastic Resonance, and Adaptive Computing

Science.gov (United States)

Kia, Behnam; Murali, K.; Jahed Motlagh, Mohammad-Reza; Sinha, Sudeshna; Ditto, William L.

Nonlinearity and chaos can illustrate numerous behaviors and patterns, and one can select different patterns from this rich library of patterns. In this paper we focus on synthetic computing, a field that engineers and synthesizes nonlinear systems to obtain computation. We explain the importance of nonlinearity, and describe how nonlinear systems can be engineered to perform computation. More specifically, we provide an overview of chaos computing, a field that manually programs chaotic systems to build different types of digital functions. Also we briefly describe logical stochastic resonance (LSR), and then extend the approach of LSR to realize combinational digital logic systems via suitable concatenation of existing logical stochastic resonance blocks. Finally we demonstrate how a chaotic system can be engineered and mated with different machine learning techniques, such as artificial neural networks, random searching, and genetic algorithm, to design different autonomous systems that can adapt and respond to environmental conditions.

Identification of generalized state transfer matrix using neural networks

International Nuclear Information System (INIS)

Zhu Changchun

2001-01-01

The research is introduced on identification of generalized state transfer matrix of linear time-invariant (LTI) system by use of neural networks based on LM (Levenberg-Marquart) algorithm. Firstly, the generalized state transfer matrix is defined. The relationship between the identification of state transfer matrix of structural dynamics and the identification of the weight matrix of neural networks has been established in theory. A singular layer neural network is adopted to obtain the structural parameters as a powerful tool that has parallel distributed processing ability and the property of adaptation or learning. The constraint condition of weight matrix of the neural network is deduced so that the learning and training of the designed network can be more effective. The identified neural network can be used to simulate the structural response excited by any other signals. In order to cope with its further application in practical problems, some noise (5% and 10%) is expected to be present in the response measurements. Results from computer simulation studies show that this method is valid and feasible

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.

Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing.

Science.gov (United States)

Kriegeskorte, Nikolaus

2015-11-24

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications. Human-level visual recognition abilities are coming within reach of artificial systems. Artificial neural networks are inspired by the brain, and their computations could be implemented in biological neurons. Convolutional feedforward networks, which now dominate computer vision, take further inspiration from the architecture of the primate visual hierarchy. However, the current models are designed with engineering goals, not to model brain computations. Nevertheless, initial studies comparing internal representations between these models and primate brains find surprisingly similar representational spaces. With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build biologically faithful feedforward and recurrent computational models of how biological brains perform high-level feats of intelligence, including vision.

Modulated error diffusion CGHs for neural nets

Science.gov (United States)

Vermeulen, Pieter J. E.; Casasent, David P.

1990-05-01

New modulated error diffusion CGHs (computer generated holograms) for optical computing are considered. Specific attention is given to their use in optical matrix-vector, associative processor, neural net and optical interconnection architectures. We consider lensless CGH systems (many CGHs use an external Fourier transform (FT) lens), the Fresnel sampling requirements, the effects of finite CGH apertures (sample and hold inputs), dot size correction (for laser recorders), and new applications for this novel encoding method (that devotes attention to quantization noise effects).

Artificial neural network modelling

CERN Document Server

Samarasinghe, Sandhya

2016-01-01

This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .

Identifying Broadband Rotational Spectra with Neural Networks

Science.gov (United States)

Zaleski, Daniel P.; Prozument, Kirill

2017-06-01

A typical broadband rotational spectrum may contain several thousand observable transitions, spanning many species. Identifying the individual spectra, particularly when the dynamic range reaches 1,000:1 or even 10,000:1, can be challenging. One approach is to apply automated fitting routines. In this approach, combinations of 3 transitions can be created to form a "triple", which allows fitting of the A, B, and C rotational constants in a Watson-type Hamiltonian. On a standard desktop computer, with a target molecule of interest, a typical AUTOFIT routine takes 2-12 hours depending on the spectral density. A new approach is to utilize machine learning to train a computer to recognize the patterns (frequency spacing and relative intensities) inherit in rotational spectra and to identify the individual spectra in a raw broadband rotational spectrum. Here, recurrent neural networks have been trained to identify different types of rotational spectra and classify them accordingly. Furthermore, early results in applying convolutional neural networks for spectral object recognition in broadband rotational spectra appear promising. Perez et al. "Broadband Fourier transform rotational spectroscopy for structure determination: The water heptamer." Chem. Phys. Lett., 2013, 571, 1-15. Seifert et al. "AUTOFIT, an Automated Fitting Tool for Broadband Rotational Spectra, and Applications to 1-Hexanal." J. Mol. Spectrosc., 2015, 312, 13-21. Bishop. "Neural networks for pattern recognition." Oxford university press, 1995.

Kernel Function Tuning for Single-Layer Neural Networks

Czech Academy of Sciences Publication Activity Database

Vidnerová, Petra; Neruda, Roman

-, accepted 28.11. 2017 (2018) ISSN 2278-0149 R&D Projects: GA ČR GA15-18108S Institutional support: RVO:67985807 Keywords : single-layer neural networks * kernel methods * kernel function * optimisation Subject RIV: IN - Informatics, Computer Science http://www.ijmerr.com/

Neural Networks for Target Selection in Direct Marketing

NARCIS (Netherlands)

R. Potharst (Rob); U. Kaymak (Uzay); W.H.L.M. Pijls (Wim)

2001-01-01

textabstractPartly due to a growing interest in direct marketing, it has become an important application field for data mining. Many techniques have been applied to select the targets in commercial applications, such as statistical regression, regression trees, neural computing, fuzzy clustering

Neural Point-and-Click Communication by a Person With Incomplete Locked-In Syndrome.

Science.gov (United States)

Bacher, Daniel; Jarosiewicz, Beata; Masse, Nicolas Y; Stavisky, Sergey D; Simeral, John D; Newell, Katherine; Oakley, Erin M; Cash, Sydney S; Friehs, Gerhard; Hochberg, Leigh R

2015-06-01

A goal of brain-computer interface research is to develop fast and reliable means of communication for individuals with paralysis and anarthria. We evaluated the ability of an individual with incomplete locked-in syndrome enrolled in the BrainGate Neural Interface System pilot clinical trial to communicate using neural point-and-click control. A general-purpose interface was developed to provide control of a computer cursor in tandem with one of two on-screen virtual keyboards. The novel BrainGate Radial Keyboard was compared to a standard QWERTY keyboard in a balanced copy-spelling task. The Radial Keyboard yielded a significant improvement in typing accuracy and speed-enabling typing rates over 10 correct characters per minute. The participant used this interface to communicate face-to-face with research staff by using text-to-speech conversion, and remotely using an internet chat application. This study demonstrates the first use of an intracortical brain-computer interface for neural point-and-click communication by an individual with incomplete locked-in syndrome. © The Author(s) 2014.

Spiking Neural P Systems with Communication on Request.

Science.gov (United States)

Pan, Linqiang; Păun, Gheorghe; Zhang, Gexiang; Neri, Ferrante

2017-12-01

Spiking Neural [Formula: see text] Systems are Neural System models characterized by the fact that each neuron mimics a biological cell and the communication between neurons is based on spikes. In the Spiking Neural [Formula: see text] systems investigated so far, the application of evolution rules depends on the contents of a neuron (checked by means of a regular expression). In these [Formula: see text] systems, a specified number of spikes are consumed and a specified number of spikes are produced, and then sent to each of the neurons linked by a synapse to the evolving neuron. [Formula: see text]In the present work, a novel communication strategy among neurons of Spiking Neural [Formula: see text] Systems is proposed. In the resulting models, called Spiking Neural [Formula: see text] Systems with Communication on Request, the spikes are requested from neighboring neurons, depending on the contents of the neuron (still checked by means of a regular expression). Unlike the traditional Spiking Neural [Formula: see text] systems, no spikes are consumed or created: the spikes are only moved along synapses and replicated (when two or more neurons request the contents of the same neuron). [Formula: see text]The Spiking Neural [Formula: see text] Systems with Communication on Request are proved to be computationally universal, that is, equivalent with Turing machines as long as two types of spikes are used. Following this work, further research questions are listed to be open problems.

On the Same Wavelength: Face-to-Face Communication Increases Interpersonal Neural Synchronization

OpenAIRE

Yun, Kyongsik

2013-01-01

Understanding neural mechanisms of social interaction is important for understanding human social nature and for developing treatments for social deficits related to disorders such as autism. However, conventional cognitive and behavioral neuroscience has concentrated on developing novel experimental paradigms and investigating human–computer interactions, rather than studying interpersonal interaction per se. To fully understand neural mechanisms of human interpersonal interaction, we will l...

Response variance in functional maps: neural darwinism revisited.

Directory of Open Access Journals (Sweden)

Hirokazu Takahashi

Full Text Available The mechanisms by which functional maps and map plasticity contribute to cortical computation remain controversial. Recent studies have revisited the theory of neural Darwinism to interpret the learning-induced map plasticity and neuronal heterogeneity observed in the cortex. Here, we hypothesize that the Darwinian principle provides a substrate to explain the relationship between neuron heterogeneity and cortical functional maps. We demonstrate in the rat auditory cortex that the degree of response variance is closely correlated with the size of its representational area. Further, we show that the response variance within a given population is altered through training. These results suggest that larger representational areas may help to accommodate heterogeneous populations of neurons. Thus, functional maps and map plasticity are likely to play essential roles in Darwinian computation, serving as effective, but not absolutely necessary, structures to generate diverse response properties within a neural population.

Response variance in functional maps: neural darwinism revisited.

Science.gov (United States)

Takahashi, Hirokazu; Yokota, Ryo; Kanzaki, Ryohei

2013-01-01

The mechanisms by which functional maps and map plasticity contribute to cortical computation remain controversial. Recent studies have revisited the theory of neural Darwinism to interpret the learning-induced map plasticity and neuronal heterogeneity observed in the cortex. Here, we hypothesize that the Darwinian principle provides a substrate to explain the relationship between neuron heterogeneity and cortical functional maps. We demonstrate in the rat auditory cortex that the degree of response variance is closely correlated with the size of its representational area. Further, we show that the response variance within a given population is altered through training. These results suggest that larger representational areas may help to accommodate heterogeneous populations of neurons. Thus, functional maps and map plasticity are likely to play essential roles in Darwinian computation, serving as effective, but not absolutely necessary, structures to generate diverse response properties within a neural population.

MIEC-SVM: automated pipeline for protein peptide/ligand interaction prediction.

Science.gov (United States)

Li, Nan; Ainsworth, Richard I; Wu, Meixin; Ding, Bo; Wang, Wei

2016-03-15

MIEC-SVM is a structure-based method for predicting protein recognition specificity. Here, we present an automated MIEC-SVM pipeline providing an integrated and user-friendly workflow for construction and application of the MIEC-SVM models. This pipeline can handle standard amino acids and those with post-translational modifications (PTMs) or small molecules. Moreover, multi-threading and support to Sun Grid Engine (SGE) are implemented to significantly boost the computational efficiency. The program is available at http://wanglab.ucsd.edu/MIEC-SVM CONTACT: : wei-wang@ucsd.edu Supplementary data available at Bioinformatics online. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Pattern recognition neural-net by spatial mapping of biology visual field

Science.gov (United States)

Lin, Xin; Mori, Masahiko

2000-05-01

The method of spatial mapping in biology vision field is applied to artificial neural networks for pattern recognition. By the coordinate transform that is called the complex-logarithm mapping and Fourier transform, the input images are transformed into scale- rotation- and shift- invariant patterns, and then fed into a multilayer neural network for learning and recognition. The results of computer simulation and an optical experimental system are described.

Error-resistant distributed quantum computation in a trapped ion chain

International Nuclear Information System (INIS)

Braungardt, Sibylle; Sen, Aditi; Sen, Ujjwal; Lewenstein, Maciej

2007-01-01

We consider experimentally feasible chains of trapped ions with pseudospin 1/2 and find models that can potentially be used to implement error-resistant quantum computation. Similar in spirit to classical neural networks, the error resistance of the system is achieved by encoding the qubits distributed over the whole system. We therefore call our system a quantum neural network and present a quantum neural network model of quantum computation. Qubits are encoded in a few quasi degenerated low-energy levels of the whole system, separated by a large gap from the excited states and large energy barriers between themselves. We investigate protocols for implementing a universal set of quantum logic gates in the system by adiabatic passage of a few low-lying energy levels of the whole system. Naturally appearing and potentially dangerous distributed noise in the system leaves the fidelity of the computation virtually unchanged, if it is not too strong. The computation is also naturally resilient to local perturbations of the spins

Improving the Robustness of Deep Neural Networks via Stability Training

OpenAIRE

Zheng, Stephan; Song, Yang; Leung, Thomas; Goodfellow, Ian

2016-01-01

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-art performance on a wide range of computer vision tasks. We present a general stability training method to stabilize deep networks against small input distortions that result from various types of common image processing, such...

Neural computations underlying social risk sensitivity

Directory of Open Access Journals (Sweden)

Nina eLauharatanahirun

2012-08-01

Full Text Available Under standard models of expected utility, preferences over stochastic events are assumed to be independent of the source of uncertainty. Thus, in decision-making, an agent should exhibit consistent preferences, regardless of whether the uncertainty derives from the unpredictability of a random process or the unpredictability of a social partner. However, when a social partner is the source of uncertainty, social preferences can influence decisions over and above pure risk attitudes. Here, we compared risk-related hemodynamic activity and individual preferences for two sets of options that differ only in the social or non-social nature of the risk. Risk preferences in social and non-social contexts were systematically related to neural activity during decision and outcome phases of each choice. Individuals who were more risk averse in the social context exhibited decreased risk-related activity in the amygdala during non-social decisions, while individuals who were more risk averse in the non-social context exhibited the opposite pattern. Differential risk preferences were similarly associated with hemodynamic activity in ventral striatum at the outcome of these decisions. These findings suggest that social preferences, including aversion to betrayal or exploitation by social partners, may be associated with variability in the response of these subcortical regions to social risk.

Densitometria da vértebra dorsal, osso pleural e osso neural em tartarugas verdes hígidas por tomografia computadorizada quantitativa Densitometry of dorsal vertebrae, pleural bone and neural bone in healthy green sea turtles by quantitative computed tomography

Directory of Open Access Journals (Sweden)

Jannine Forattini de Oliveira

2012-08-01

Full Text Available A tomografia computadorizada quantitativa (TCQ é uma técnica com alta sensibilidade, aplicabilidade e precisão no diagnóstico de perda de massa óssea, entretanto a falta de valores de normalidade para animais silvestres limita a sua aplicação clínica. O presente estudo objetiva estabelecer valores médios de radiodensidade do osso trabecular das vértebras dorsais, osso pleural e osso neural de tartarugas marinhas juvenis hígidas utilizando a TCQ. Para isso, utilizou-se um grupo experimental de cinco animais que foram submetidos a exames de tomografia computadorizada helicoidal, sendo as mensurações da radiodensidade óssea realizadas ao nível da terceira, quarta e quinta vértebras dorsais. Os valores médios de radiodensidade do osso trabecular das vértebras dorsais, osso pleural e osso neural foram, respectivamente, de 287,4±39,1, 1093,74±100,4 e 1089,6±86,5 unidades Hounsfield (HU. Estudos complementares devem ser realizados em diferentes espécies e faixas etárias de quelônios para favorecer a aplicação clínica desta técnica.Quantitative computed tomography (QCT is a technique with high sensitivity, applicability and accuracy in the diagnosis of bone loss; however the lack of normal values for wild animals limits their clinical application. This study aims to establish medium values radiodensity trabecular bone of the dorsal vertebrae, bone pleural and neural bone in healthy juvenile sea turtles using the QTC. For this we used an experimental group of five animals that underwent helical computed tomography, and measurements of bone radiodensity conducted at the level of the third, fourth and fifth dorsal vertebrae. The medium values of radiodensity trabecular bone of the dorsal vertebrae, pleural bone, and neural bone were respectively 287.4±39.1, 1093.74±100.4, and 1089.6±86.5 Hounsfield units (HU. Further studies should be performed in different species and ages of turtles to encourage the clinical application of

The artificial neural networks: An approach to artificial intelligence; Un approccio ``biologico`` all`intelligenza artificiale

Energy Technology Data Exchange (ETDEWEB)

Taraglio, Sergio; Zanela, Andrea [ENEA, Casaccia (Italy). Dipt. Innovazione

1997-05-01

The artificial neural networks try to simulate the functionalities of the nervous system through a complex network of simple computing elements. In this work is presented an introduction to the neural networks and some of their possible applications, especially in the field of Artificial Intelligence.

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.

Application of artificial intelligence to electrofacies identification: neural networks versus discriminant analysis; Aplicacao de inteligencia artificial na identificacao de eletrofacies redes neuroniais versus analise discriminante

Energy Technology Data Exchange (ETDEWEB)

Silva Rodrigues, F da [PETROBRAS, Rio de Janeiro, RJ (Brazil); Queiroz Neto, I.A. de [PETROBRAS, Rio de Janeiro, RJ (Brazil). Centro de Pesquisas

1992-07-01

Electro-facies are identified by neural network trained with well log and core data. Differences between neural network and expert system are discussed. According the author, the combination of neural network computing and traditional computing methods, like discriminant analysis, can help in the solution of many problems in electro-facies identification. 5 figs., 1 tab., 11 refs.

Neural-Network Object-Recognition Program

Science.gov (United States)

Spirkovska, L.; Reid, M. B.

1993-01-01

HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

Implementation of neural networks on 'Connection Machine'

International Nuclear Information System (INIS)

Belmonte, Ghislain

1990-12-01

This report is a first approach to the notion of neural networks and their possible applications within the framework of artificial intelligence activities of the Department of Applied Mathematics of the Limeil-Valenton Research Center. The first part is an introduction to the field of neural networks; the main neural network models are described in this section. The applications of neural networks in the field of classification have mainly been studied because they could more particularly help to solve some of the decision support problems dealt with by the C.E.A. As the neural networks perform a large number of parallel operations, it was therefore logical to use a parallel architecture computer: the Connection Machine (which uses 16384 processors and is located at E.T.C.A. Arcueil). The second part presents some generalities on the parallelism and the Connection Machine, and two implementations of neural networks on Connection Machine. The first of these implementations concerns one of the most used algorithms to realize the learning of neural networks: the Gradient Retro-propagation algorithm. The second one, less common, concerns a network of neurons destined mainly to the recognition of forms: the Fukushima Neocognitron. The latter is studied by the C.E.A. of Bruyeres-le-Chatel in order to realize an embedded system (including hardened circuits) for the fast recognition of forms [fr

Application of artificial neural networks with backpropagation technique in the financial data

Science.gov (United States)

Jaiswal, Jitendra Kumar; Das, Raja

2017-11-01

The propensity of applying neural networks has been proliferated in multiple disciplines for research activities since the past recent decades because of its powerful control with regulatory parameters for pattern recognition and classification. It is also being widely applied for forecasting in the numerous divisions. Since financial data have been readily available due to the involvement of computers and computing systems in the stock market premises throughout the world, researchers have also developed numerous techniques and algorithms to analyze the data from this sector. In this paper we have applied neural network with backpropagation technique to find the data pattern from finance section and prediction for stock values as well.

Foraging for brain stimulation: toward a neurobiology of computation.

Science.gov (United States)

Gallistel, C R

1994-01-01

The self-stimulating rat performs foraging tasks mediated by simple computations that use interreward intervals and subjective reward magnitudes to determine stay durations. This is a simplified preparation in which to study the neurobiology of the elementary computational operations that make cognition possible, because the neural signal specifying the value of a computationally relevant variable is produced by direct electrical stimulation of a neural pathway. Newly developed measurement methods yield functions relating the subjective reward magnitude to the parameters of the neural signal. These measurements also show that the decision process that governs foraging behavior divides the subjective reward magnitude by the most recent interreward interval to determine the preferability of an option (a foraging patch). The decision process sets the parameters that determine stay durations (durations of visits to foraging patches) so that the ratios of the stay durations match the ratios of the preferabilities.

Using Neural Networks to Improve the Performance of Radiative Transfer Modeling Used for Geometry Dependent LER Calculations

Science.gov (United States)

Fasnacht, Z.; Qin, W.; Haffner, D. P.; Loyola, D. G.; Joiner, J.; Krotkov, N. A.; Vasilkov, A. P.; Spurr, R. J. D.

2017-12-01

In order to estimate surface reflectance used in trace gas retrieval algorithms, radiative transfer models (RTM) such as the Vector Linearized Discrete Ordinate Radiative Transfer Model (VLIDORT) can be used to simulate the top of the atmosphere (TOA) radiances with advanced models of surface properties. With large volumes of satellite data, these model simulations can become computationally expensive. Look up table interpolation can improve the computational cost of the calculations, but the non-linear nature of the radiances requires a dense node structure if interpolation errors are to be minimized. In order to reduce our computational effort and improve the performance of look-up tables, neural networks can be trained to predict these radiances. We investigate the impact of using look-up table interpolation versus a neural network trained using the smart sampling technique, and show that neural networks can speed up calculations and reduce errors while using significantly less memory and RTM calls. In future work we will implement a neural network in operational processing to meet growing demands for reflectance modeling in support of high spatial resolution satellite missions.

Fuzzy Entropy： Axiomatic Definition and Neural Networks Model

Institute of Scientific and Technical Information of China (English)

QINGMing; CAOYue; HUANGTian-min

2004-01-01

The measure of uncertainty is adopted as a measure of information. The measures of fuzziness are known as fuzzy information measures. The measure of a quantity of fuzzy information gained from a fuzzy set or fuzzy system is known as fuzzy entropy. Fuzzy entropy has been focused and studied by many researchers in various fields. In this paper, firstly, the axiomatic definition of fuzzy entropy is discussed. Then, neural networks model of fuzzy entropy is proposed, based on the computing capability of neural networks. In the end, two examples are discussed to show the efficiency of the model.

Static human face recognition using artificial neural networks

International Nuclear Information System (INIS)

Qamar, R.; Shah, S.H.; Javed-ur-Rehman

2003-01-01

This paper presents a novel method of human face recognition using digital computers. A digital PC camera is used to take the BMP images of the human faces. An artificial neural network using Back Propagation Algorithm is developed as a recognition engine. The BMP images of the faces serve as the input patterns for this engine. A software 'Face Recognition' has been developed to recognize the human faces for which it is trained. Once the neural network is trained for patterns of the faces, the software is able to detect and recognize them with success rate of about 97%. (author)

Neural Computation of Surface Border Ownership and Relative Surface Depth from Ambiguous Contrast Inputs.

Science.gov (United States)

Dresp-Langley, Birgitta; Grossberg, Stephen

2016-01-01

The segregation of image parts into foreground and background is an important aspect of the neural computation of 3D scene perception. To achieve such segregation, the brain needs information about border ownership; that is, the belongingness of a contour to a specific surface represented in the image. This article presents psychophysical data derived from 3D percepts of figure and ground that were generated by presenting 2D images composed of spatially disjoint shapes that pointed inward or outward relative to the continuous boundaries that they induced along their collinear edges. The shapes in some images had the same contrast (black or white) with respect to the background gray. Other images included opposite contrasts along each induced continuous boundary. Psychophysical results demonstrate conditions under which figure-ground judgment probabilities in response to these ambiguous displays are determined by the orientation of contrasts only, not by their relative contrasts, despite the fact that many border ownership cells in cortical area V2 respond to a preferred relative contrast. Studies are also reviewed in which both polarity-specific and polarity-invariant properties obtain. The FACADE and 3D LAMINART models are used to explain these data.

Neural computation of surface border ownership and relative surface depth from ambiguous contrast inputs

Directory of Open Access Journals (Sweden)

Birgitta Dresp-Langley

2016-07-01

Full Text Available The segregation of image parts into foreground and background is an important aspect of the neural computation of 3D scene perception. To achieve such segregation, the brain needs information about border ownership; that is, the belongingness of a contour to a specific surface represented in the image. This article presents psychophysical data derived from 3D percepts of figure and ground that were generated by presenting 2D images composed of spatially disjoint shapes that pointed inward or outward relative to the continuous boundaries that they induced along their collinear edges. The shapes in some images had the same contrast (black or white with respect to the background gray. Other images included opposite contrasts along each induced continuous boundary. Results demonstrate conditions under which figure-ground judgment probabilities in response to these ambiguous displays are determined by the orientation of contrasts only, not by their relative contrasts, despite the fact that many border ownership cells in cortical area V2 respond to a preferred relative contrast. Studies are also reviewed in which both polarity-specific and polarity-invariant properties obtain. The FACADE and 3D LAMINART models are used to explain these data.

Neural Computation of Surface Border Ownership and Relative Surface Depth from Ambiguous Contrast Inputs

Science.gov (United States)

Dresp-Langley, Birgitta; Grossberg, Stephen

2016-01-01

The segregation of image parts into foreground and background is an important aspect of the neural computation of 3D scene perception. To achieve such segregation, the brain needs information about border ownership; that is, the belongingness of a contour to a specific surface represented in the image. This article presents psychophysical data derived from 3D percepts of figure and ground that were generated by presenting 2D images composed of spatially disjoint shapes that pointed inward or outward relative to the continuous boundaries that they induced along their collinear edges. The shapes in some images had the same contrast (black or white) with respect to the background gray. Other images included opposite contrasts along each induced continuous boundary. Psychophysical results demonstrate conditions under which figure-ground judgment probabilities in response to these ambiguous displays are determined by the orientation of contrasts only, not by their relative contrasts, despite the fact that many border ownership cells in cortical area V2 respond to a preferred relative contrast. Studies are also reviewed in which both polarity-specific and polarity-invariant properties obtain. The FACADE and 3D LAMINART models are used to explain these data. PMID:27516746

Neural network feedforward control of a closed-circuit wind tunnel

Science.gov (United States)

Sutcliffe, Peter

Accurate control of wind-tunnel test conditions can be dramatically enhanced using feedforward control architectures which allow operating conditions to be maintained at a desired setpoint through the use of mathematical models as the primary source of prediction. However, as the desired accuracy of the feedforward prediction increases, the model complexity also increases, so that an ever increasing computational load is incurred. This drawback can be avoided by employing a neural network that is trained offline using the output of a high fidelity wind-tunnel mathematical model, so that the neural network can rapidly reproduce the predictions of the model with a greatly reduced computational overhead. A novel neural network database generation method, developed through the use of fractional factorial arrays, was employed such that a neural network can accurately predict wind-tunnel parameters across a wide range of operating conditions whilst trained upon a highly efficient database. The subsequent network was incorporated into a Neural Network Model Predictive Control (NNMPC) framework to allow an optimised output schedule capable of providing accurate control of the wind-tunnel operating parameters. Facilitation of an optimised path through the solution space is achieved through the use of a chaos optimisation algorithm such that a more globally optimum solution is likely to be found with less computational expense than the gradient descent method. The parameters associated with the NNMPC such as the control horizon are determined through the use of a Taguchi methodology enabling the minimum number of experiments to be carried out to determine the optimal combination. The resultant NNMPC scheme was employed upon the Hessert Low Speed Wind Tunnel at the University of Notre Dame to control the test-section temperature such that it follows a pre-determined reference trajectory during changes in the test-section velocity. Experimental testing revealed that the

Neural networks and its application in biomedical engineering

International Nuclear Information System (INIS)

Husnain, S.K.; Bhatti, M.I.

2002-01-01

Artificial network (ANNs) is an information processing system that has certain performance characteristics in common with biological neural networks. A neural network is characterized by connections between the neurons, method of determining the weights on the connections and its activation functions while a biological neuron has three types of components that are of particular interest in understanding an artificial neuron: its dendrites, soma, and axon. The actin of the chemical transmitter modifies the incoming signal. The study of neural networks is an extremely interdisciplinary field. Computer-based diagnosis is an increasingly used method that tries to improve the quality of health care. Systems on Neural Networks have been developed extensively in the last ten years with the hope that medical diagnosis and therefore medical care would improve dramatically. The addition of a symbolic processing layer enhances the ANNs in a number of ways. It is, for instance, possible to supplement a network that is purely diagnostic with a level that recommends or nodes in order to more closely simulate the nervous system. (author)

Neural model of gene regulatory network: a survey on supportive meta-heuristics.

Science.gov (United States)

Biswas, Surama; Acharyya, Sriyankar

2016-06-01

Gene regulatory network (GRN) is produced as a result of regulatory interactions between different genes through their coded proteins in cellular context. Having immense importance in disease detection and drug finding, GRN has been modelled through various mathematical and computational schemes and reported in survey articles. Neural and neuro-fuzzy models have been the focus of attraction in bioinformatics. Predominant use of meta-heuristic algorithms in training neural models has proved its excellence. Considering these facts, this paper is organized to survey neural modelling schemes of GRN and the efficacy of meta-heuristic algorithms towards parameter learning (i.e. weighting connections) within the model. This survey paper renders two different structure-related approaches to infer GRN which are global structure approach and substructure approach. It also describes two neural modelling schemes, such as artificial neural network/recurrent neural network based modelling and neuro-fuzzy modelling. The meta-heuristic algorithms applied so far to learn the structure and parameters of neutrally modelled GRN have been reviewed here.

Linear and nonlinear ARMA model parameter estimation using an artificial neural network

Science.gov (United States)

Chon, K. H.; Cohen, R. J.

1997-01-01

This paper addresses parametric system identification of linear and nonlinear dynamic systems by analysis of the input and output signals. Specifically, we investigate the relationship between estimation of the system using a feedforward neural network model and estimation of the system by use of linear and nonlinear autoregressive moving-average (ARMA) models. By utilizing a neural network model incorporating a polynomial activation function, we show the equivalence of the artificial neural network to the linear and nonlinear ARMA models. We compare the parameterization of the estimated system using the neural network and ARMA approaches by utilizing data generated by means of computer simulations. Specifically, we show that the parameters of a simulated ARMA system can be obtained from the neural network analysis of the simulated data or by conventional least squares ARMA analysis. The feasibility of applying neural networks with polynomial activation functions to the analysis of experimental data is explored by application to measurements of heart rate (HR) and instantaneous lung volume (ILV) fluctuations.

Computation and brain processes, with special reference to neuroendocrine systems.

Science.gov (United States)

Toni, Roberto; Spaletta, Giulia; Casa, Claudia Della; Ravera, Simone; Sandri, Giorgio

2007-01-01

The development of neural networks and brain automata has made neuroscientists aware that the performance limits of these brain-like devices lies, at least in part, in their computational power. The computational basis of a. standard cybernetic design, in fact, refers to that of a discrete and finite state machine or Turing Machine (TM). In contrast, it has been suggested that a number of human cerebral activites, from feedback controls up to mental processes, rely on a mixing of both finitary, digital-like and infinitary, continuous-like procedures. Therefore, the central nervous system (CNS) of man would exploit a form of computation going beyond that of a TM. This "non conventional" computation has been called hybrid computation. Some basic structures for hybrid brain computation are believed to be the brain computational maps, in which both Turing-like (digital) computation and continuous (analog) forms of calculus might occur. The cerebral cortex and brain stem appears primary candidate for this processing. However, also neuroendocrine structures like the hypothalamus are believed to exhibit hybrid computional processes, and might give rise to computational maps. Current theories on neural activity, including wiring and volume transmission, neuronal group selection and dynamic evolving models of brain automata, bring fuel to the existence of natural hybrid computation, stressing a cooperation between discrete and continuous forms of communication in the CNS. In addition, the recent advent of neuromorphic chips, like those to restore activity in damaged retina and visual cortex, suggests that assumption of a discrete-continuum polarity in designing biocompatible neural circuitries is crucial for their ensuing performance. In these bionic structures, in fact, a correspondence exists between the original anatomical architecture and synthetic wiring of the chip, resulting in a correspondence between natural and cybernetic neural activity. Thus, chip "form

Weed Growth Stage Estimator Using Deep Convolutional Neural Networks

DEFF Research Database (Denmark)

Teimouri, Nima; Dyrmann, Mads; Nielsen, Per Rydahl

2018-01-01

conditions with regards to soil types, resolution and light settings. Then, 9649 of these images were used for training the computer, which automatically divided the weeds into nine growth classes. The performance of this proposed convolutional neural network approach was evaluated on a further set of 2516...... in estimating the number of leaves and 96% accuracy when accepting a deviation of two leaves. These results show that this new method of using deep convolutional neural networks has a relatively high ability to estimate early growth stages across a wide variety of weed species....

Neural networks prove effective at NO{sub x} reduction

Energy Technology Data Exchange (ETDEWEB)

Radl, B.J. [Pegasus Technologies, Mentor, OH (United States)

2000-05-01

The virtues of the Pegasus NeuSIGHT combustion optimisation software are extolled. It has been installed at more than 25 power plants and operates mostly in closed loop control. The software uses the leading neural network technology from Computer associates. The system is said to reduce emissions of nitrogen oxides, increase plant efficiency and has the potential for saving millions of dollars in capital and operating costs. The value of the system is illustrated by case studies from three coal-fired power plants. The meaning of 'neural network' is explained.

Applying neural networks as software sensors for enzyme engineering.

Science.gov (United States)

Linko, S; Zhu, Y H; Linko, P

1999-04-01

The on-line control of enzyme-production processes is difficult, owing to the uncertainties typical of biological systems and to the lack of suitable on-line sensors for key process variables. For example, intelligent methods to predict the end point of fermentation could be of great economic value. Computer-assisted control based on artificial-neural-network models offers a novel solution in such situations. Well-trained feedforward-backpropagation neural networks can be used as software sensors in enzyme-process control; their performance can be affected by a number of factors.

High speed digital interfacing for a neural data acquisition system

Directory of Open Access Journals (Sweden)

Bahr Andreas

2016-09-01

Full Text Available Diseases like schizophrenia and genetic epilepsy are supposed to be caused by disorders in the early development of the brain. For the further investigation of these relationships a custom designed application specific integrated circuit (ASIC was developed that is optimized for the recording from neonatal mice [Bahr A, Abu-Saleh L, Schroeder D, Krautschneider W. 16 Channel Neural Recording Integrated Circuit with SPI Interface and Error Correction Coding. Proc. 9th BIOSTEC 2016. Biodevices: Rome, Italy, 2016; 1: 263; Bahr A, Abu-Saleh L, Schroeder D, Krautschneider W. Development of a neural recording mixed signal integrated circuit for biomedical signal acquisition. Biomed Eng Biomed Tech Abstracts 2015; 60(S1: 298–299; Bahr A, Abu-Saleh L, Schroeder D, Krautschneider WH. 16 Channel Neural Recording Mixed Signal ASIC. CDNLive EMEA 2015 Conference Proceedings, 2015.]. To enable the live display of the neural signals a multichannel neural data acquisition system with live display functionality is presented. It implements a high speed data transmission from the ASIC to a computer with a live display functionality. The system has been successfully implemented and was used in a neural recording of a head-fixed mouse.

Modelling collective cell migration of neural crest.

Science.gov (United States)

Szabó, András; Mayor, Roberto

2016-10-01

Collective cell migration has emerged in the recent decade as an important phenomenon in cell and developmental biology and can be defined as the coordinated and cooperative movement of groups of cells. Most studies concentrate on tightly connected epithelial tissues, even though collective migration does not require a constant physical contact. Movement of mesenchymal cells is more independent, making their emergent collective behaviour less intuitive and therefore lending importance to computational modelling. Here we focus on such modelling efforts that aim to understand the collective migration of neural crest cells, a mesenchymal embryonic population that migrates large distances as a group during early vertebrate development. By comparing different models of neural crest migration, we emphasize the similarity and complementary nature of these approaches and suggest a future direction for the field. The principles derived from neural crest modelling could aid understanding the collective migration of other mesenchymal cell types. Copyright © 2016 Elsevier Ltd. All rights reserved.

Multiscale Methods, Parallel Computation, and Neural Networks for Real-Time Computer Vision.