WorldWideScience

Sample records for training cooperative neural

  1. Cooperating attackers in neural cryptography.

    Science.gov (United States)

    Shacham, Lanir N; Klein, Einat; Mislovaty, Rachel; Kanter, Ido; Kinzel, Wolfgang

    2004-06-01

    A successful attack strategy in neural cryptography is presented. The neural cryptosystem, based on synchronization of neural networks by mutual learning, has been recently shown to be secure under different attack strategies. The success of the advanced attacker presented here, called the "majority-flipping attacker," does not decay with the parameters of the model. This attacker's outstanding success is due to its using a group of attackers which cooperate throughout the synchronization process, unlike any other attack strategy known. An analytical description of this attack is also presented, and fits the results of simulations.

  2. Cooperation in regional nuclear training

    International Nuclear Information System (INIS)

    Newstead, C.M.; Lee, D.S.; Spitalnik, J.

    1985-01-01

    This paper presents an overview of the nuclear training currently being undertaken in the countries of the co-authors, and considers the degree to which training problems are amenable to common solutions such as cooperative regional training programs. Different types of cooperation are discussed including the development of regional and international training centers, cooperative bilateral and multilateral training, and the proposed US International Nuclear Safety Training Academy. The paper provides suggestions of ways for enhancing regional cooperation

  3. Cooperative and supportive neural networks

    International Nuclear Information System (INIS)

    Sree Hari Rao, V.; Raja Sekhara Rao, P.

    2007-01-01

    This Letter deals with the concepts of co-operation and support among neurons existing in a network which contribute to their collective capabilities and distributed operations. Activational dynamical properties of these networks are discussed

  4. Diversified Cooperative Training. A Bibliography.

    Science.gov (United States)

    Florida State Univ., Tallahassee. Center for Instructional Development and Services.

    This bibliography describes 52 materials available for use in cooperative education classes and career and guidance counseling. The materials include books, pamphlets, and brochures, films, curriculum guides, study guides, and workbooks. A few are suited for use with special needs students. Materials for inclusion in the bibliography were located…

  5. Automatic gain control of neural coupling during cooperative hand movements.

    Science.gov (United States)

    Thomas, F A; Dietz, V; Schrafl-Altermatt, M

    2018-04-13

    Cooperative hand movements (e.g. opening a bottle) are controlled by a task-specific neural coupling, reflected in EMG reflex responses contralateral to the stimulation site. In this study the contralateral reflex responses in forearm extensor muscles to ipsilateral ulnar nerve stimulation was analyzed at various resistance and velocities of cooperative hand movements. The size of contralateral reflex responses was closely related to the level of forearm muscle activation required to accomplish the various cooperative hand movement tasks. This indicates an automatic gain control of neural coupling that allows a rapid matching of corrective forces exerted at both sides of an object with the goal 'two hands one action'.

  6. Dynamic training algorithm for dynamic neural networks

    International Nuclear Information System (INIS)

    Tan, Y.; Van Cauwenberghe, A.; Liu, Z.

    1996-01-01

    The widely used backpropagation algorithm for training neural networks based on the gradient descent has a significant drawback of slow convergence. A Gauss-Newton method based recursive least squares (RLS) type algorithm with dynamic error backpropagation is presented to speed-up the learning procedure of neural networks with local recurrent terms. Finally, simulation examples concerning the applications of the RLS type algorithm to identification of nonlinear processes using a local recurrent neural network are also included in this paper

  7. Neural adaptations to electrical stimulation strength training

    NARCIS (Netherlands)

    Hortobagyi, Tibor; Maffiuletti, Nicola A.

    2011-01-01

    This review provides evidence for the hypothesis that electrostimulation strength training (EST) increases the force of a maximal voluntary contraction (MVC) through neural adaptations in healthy skeletal muscle. Although electrical stimulation and voluntary effort activate muscle differently, there

  8. 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.

  9. 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.

  10. Effective, Efficient Online Training in Cooperative Extension

    Directory of Open Access Journals (Sweden)

    Jane Chin Young

    2014-09-01

    Full Text Available In order to keep pace with media and communications trends in education, Cooperative Extension (CE faces the need to shift from traditional face-to-face delivery to online alternatives. This exploratory study focused on evaluating the effectiveness of on-demand, interactive online training compared to its face-to-face counterpart. Targeted for CE staff and volunteers whose work impacts youth, families and communities, the design centered on the university’s cost-effective in-house technology tools. The study results make the case for online delivery as effective and efficient. Strategies for developing a process for online delivery in CE are also offered.

  11. Training Needs of Cooperative Members and Marketing of ...

    African Journals Online (AJOL)

    Training Needs of Cooperative Members and Marketing of Agricultural Products in Akwa Ibom State, Nigeria. ... of multi-purpose cooperative society members and the marketing of agricultural products ... EMAIL FULL TEXT EMAIL FULL TEXT

  12. 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.

  13. Neural correlates of social cooperation and non-cooperation as a function of psychopathy.

    Science.gov (United States)

    Rilling, James K; Glenn, Andrea L; Jairam, Meeta R; Pagnoni, Giuseppe; Goldsmith, David R; Elfenbein, Hanie A; Lilienfeld, Scott O

    2007-06-01

    Psychopathy is a disorder involving a failure to experience many emotions that are necessary for appropriate social behavior. In this study, we probed the behavioral, emotional, and neural correlates of psychopathic traits within the context of a dyadic social interaction. Thirty subjects were imaged with functional magnetic resonance imaging while playing an iterated Prisoner's Dilemma game with human confederates who were outside the scanner. Subjects also completed two self-report psychopathy questionnaires. Subjects scoring higher on psychopathy, particularly males, defected more often and were less likely to continue cooperating after establishing mutual cooperation with a partner. Further, they experienced more outcomes in which their cooperation was not reciprocated (cooperate-defect outcome). After such outcomes, subjects scoring high in psychopathy showed less amygdala activation, suggesting weaker aversive conditioning to those outcomes. Compared with low-psychopathy subjects, subjects higher in psychopathy also showed weaker activation within orbitofrontal cortex when choosing to cooperate and showed weaker activation within dorsolateral prefrontal and rostral anterior cingulate cortex when choosing to defect. These findings suggest that whereas subjects scoring low on psychopathy have emotional biases toward cooperation that can only be overcome with effortful cognitive control, subjects scoring high on psychopathy have an opposing bias toward defection that likewise can only be overcome with cognitive effort.

  14. Character Recognition Using Genetically Trained Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.

    1998-10-01

    Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the

  15. Applications of neural networks in training science.

    Science.gov (United States)

    Pfeiffer, Mark; Hohmann, Andreas

    2012-04-01

    Training science views itself as an integrated and applied science, developing practical measures founded on scientific method. Therefore, it demands consideration of a wide spectrum of approaches and methods. Especially in the field of competitive sports, research questions are usually located in complex environments, so that mainly field studies are drawn upon to obtain broad external validity. Here, the interrelations between different variables or variable sets are mostly of a nonlinear character. In these cases, methods like neural networks, e.g., the pattern recognizing methods of Self-Organizing Kohonen Feature Maps or similar instruments to identify interactions might be successfully applied to analyze data. Following on from a classification of data analysis methods in training-science research, the aim of the contribution is to give examples of varied sports in which network approaches can be effectually used in training science. First, two examples are given in which neural networks are employed for pattern recognition. While one investigation deals with the detection of sporting talent in swimming, the other is located in game sports research, identifying tactical patterns in team handball. The third and last example shows how an artificial neural network can be used to predict competitive performance in swimming. Copyright © 2011 Elsevier B.V. All rights reserved.

  16. Mindfulness training increases cooperative decision making in economic exchanges: Evidence from fMRI.

    Science.gov (United States)

    Kirk, Ulrich; Gu, Xiaosi; Sharp, Carla; Hula, Andreas; Fonagy, Peter; Montague, P Read

    2016-09-01

    Emotions have been shown to exert influences on decision making during economic exchanges. Here we investigate the underlying neural mechanisms of a training regimen which is hypothesized to promote emotional awareness, specifically mindfulness training (MT). We test the hypothesis that MT increases cooperative economic decision making using fMRI in a randomized longitudinal design involving 8weeks of either MT or active control training (CT). We find that MT results in an increased willingness to cooperate indexed by higher acceptance rates to unfair monetary offers in the Ultimatum Game. While controlling for acceptance rates of monetary offers between intervention groups, subjects in the MT and CT groups show differential brain activation patterns. Specifically, a subset of more cooperative MT subjects displays increased activation in the septal region, an area linked to social attachment, which may drive the increased willingness to express cooperative behavior in the MT cohort. Furthermore, MT resulted in attenuated activity in anterior insula compared with the CT group in response to unfair monetary offers post-training, which may suggest that MT enables greater ability to effectively regulate the anterior insula and thereby promotes social cooperation. Finally, functional connectivity analyses show a coupling between the septal region and posterior insula in the MT group, suggesting an integration of interoceptive inputs. Together, these results highlight that MT may be employed in contexts where emotional regulation is required to promote social cooperation. Copyright © 2016 Elsevier Inc. All rights reserved.

  17. Temporal Correlations and Neural Spike Train Entropy

    International Nuclear Information System (INIS)

    Schultz, Simon R.; Panzeri, Stefano

    2001-01-01

    Sampling considerations limit the experimental conditions under which information theoretic analyses of neurophysiological data yield reliable results. We develop a procedure for computing the full temporal entropy and information of ensembles of neural spike trains, which performs reliably for limited samples of data. This approach also yields insight to the role of correlations between spikes in temporal coding mechanisms. The method, when applied to recordings from complex cells of the monkey primary visual cortex, results in lower rms error information estimates in comparison to a 'brute force' approach

  18. Adaptive training of feedforward neural networks by Kalman filtering

    International Nuclear Information System (INIS)

    Ciftcioglu, Oe.

    1995-02-01

    Adaptive training of feedforward neural networks by Kalman filtering is described. Adaptive training is particularly important in estimation by neural network in real-time environmental where the trained network is used for system estimation while the network is further trained by means of the information provided by the experienced/exercised ongoing operation. As result of this, neural network adapts itself to a changing environment to perform its mission without recourse to re-training. The performance of the training method is demonstrated by means of actual process signals from a nuclear power plant. (orig.)

  19. Cooperative Training Partnership in Aquatic Toxicology and Ecosystem Research

    Science.gov (United States)

    EPA-ORD seeks applications to enter into a cooperative agreement with EPA that will provide training opportunities for undergraduate, graduate, and post-doctoral trainees on-site at ORD’s Mid-Continent Ecology Division (MED) research

  20. Parallelization of Neural Network Training for NLP with Hogwild!

    Directory of Open Access Journals (Sweden)

    Deyringer Valentin

    2017-10-01

    Full Text Available Neural Networks are prevalent in todays NLP research. Despite their success for different tasks, training time is relatively long. We use Hogwild! to counteract this phenomenon and show that it is a suitable method to speed up training Neural Networks of different architectures and complexity. For POS tagging and translation we report considerable speedups of training, especially for the latter. We show that Hogwild! can be an important tool for training complex NLP architectures.

  1. 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.

  2. Co-Operative Training in the Sheffield Forging Industry

    Science.gov (United States)

    Duncan, R.

    2008-01-01

    Purpose: The purpose of this paper is to give details of an operation carried out in Sheffield to increase the recruitment of young men into the steel forging industry. Design/methodology/approach: The Sheffield Forges Co-operative Training Scheme was designed to encourage boys to enter the forging industry and to provide them with training and…

  3. Hospitality Occupational Skills Training Cooperative. Project HOST Final Report.

    Science.gov (United States)

    Northwest Educational Cooperative, Des Plaines, IL.

    Project HOST (Hospitality Occupational Skills Training) provided vocational training and employment opportunities in the hotel industry to disadvantaged adult minority populations in Chicago. It demonstrated a model for successful cooperation between the business sector and a public vocational education agency and developed and piloted a…

  4. A decomposition approach to analysis of competitive-cooperative neural networks with delay

    International Nuclear Information System (INIS)

    Chu Tianguang; Zhang Zongda; Wang Zhaolin

    2003-01-01

    Competitive-cooperative or inhibitory-excitatory configurations abound in neural networks. It is demonstrated here how such a configuration may be exploited to give a detailed characterization of the fixed point dynamics in general neural networks with time delay. The idea is to divide the connection weights into inhibitory and excitatory types and thereby to embed a competitive-cooperative delay neural network into an augmented cooperative delay system through a symmetric transformation. This allows for the use of the powerful monotone properties of cooperative systems. By the method, we derive several simple necessary and sufficient conditions on guaranteed trapping regions and guaranteed componentwise (exponential) convergence of the neural networks. The results relate specific decay rate and trajectory bounds to system parameters and are therefore of practical significance in designing a network with desired performance

  5. Quality assurance technical cooperation and training

    International Nuclear Information System (INIS)

    Chen, C.K.

    1993-01-01

    An IAEA Manual (TRS 340) which provides guidance for establishing training programme covering Quality Assurance principles and practices was published in 1992. The document is mainly based on the experience and material collected through the performance of some 50 interregional, regional and national training courses, seminars and workshops on Quality Assurance organized by the IAEA in about 20 countries. The purpose of this document is to provide a systematic approach for use by the responsible management in developing an overall QA training programme and lecture material for all personnel of a nuclear power plant. The document can be suitably adjusted for various management levels and adapted to the national variables and needs

  6. Discriminative training of self-structuring hidden control neural models

    DEFF Research Database (Denmark)

    Sørensen, Helge Bjarup Dissing; Hartmann, Uwe; Hunnerup, Preben

    1995-01-01

    This paper presents a new training algorithm for self-structuring hidden control neural (SHC) models. The SHC models were trained non-discriminatively for speech recognition applications. Better recognition performance can generally be achieved, if discriminative training is applied instead. Thus...... we developed a discriminative training algorithm for SHC models, where each SHC model for a specific speech pattern is trained with utterances of the pattern to be recognized and with other utterances. The discriminative training of SHC neural models has been tested on the TIDIGITS database...

  7. Towards dropout training for convolutional neural networks.

    Science.gov (United States)

    Wu, Haibing; Gu, Xiaodong

    2015-11-01

    Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weighted pooling. We also empirically show that the effect of convolutional dropout is not trivial, despite the dramatically reduced possibility of over-fitting due to the convolutional architecture. Elaborately designing dropout training simultaneously in max-pooling and fully-connected layers, we achieve state-of-the-art performance on MNIST, and very competitive results on CIFAR-10 and CIFAR-100, relative to other approaches without data augmentation. Finally, we compare max-pooling dropout and stochastic pooling, both of which introduce stochasticity based on multinomial distributions at pooling stage. Copyright © 2015 Elsevier Ltd. All rights reserved.

  8. How to increase the benefits of cooperation: Effects of training in transactive communication on cooperative learning.

    Science.gov (United States)

    Jurkowski, Susanne; Hänze, Martin

    2015-09-01

    Transactive communication means referring to and building on a learning partner's idea, by, for example, extending the partner's idea or interlinking the partner's idea with an idea of one's own. This transforms the partner's idea into a more elaborate one. Previous research found a positive relationship between students' transactive communication and their learning results when working in small groups. To increase the benefits of cooperation, we developed and tested a module for training students in transactive communication. We assumed that this training would enhance students' transactive communication and also increase their knowledge acquisition during cooperative learning. Further, we distinguished between an actor's transactive communication and a learning partner's transactive communication and expected both to be positively associated with an actor's knowledge acquisition. Participants were 80 university students. In an experiment with pre- and post-test measurements, transactive communication was measured by coding students' communication in a cooperative learning situation before training and in another cooperative learning situation after training. For the post-test cooperative learning situation, knowledge was pre-tested and post-tested. Trained students outperformed controls in transactive communication and in knowledge acquisition. Positive training effects on actors' knowledge acquisition were partially mediated by the improved actors' transactive communication. Moreover, actors' knowledge acquisition was positively influenced by learning partners' transactive communication. Results show a meaningful increase in the benefits of cooperation through the training in transactive communication. Furthermore, findings indicate that students benefit from both elaborating on their partner's ideas and having their own ideas elaborated on. © 2015 The British Psychological Society.

  9. Inferring oscillatory modulation in neural spike trains.

    Science.gov (United States)

    Arai, Kensuke; Kass, Robert E

    2017-10-01

    Oscillations are observed at various frequency bands in continuous-valued neural recordings like the electroencephalogram (EEG) and local field potential (LFP) in bulk brain matter, and analysis of spike-field coherence reveals that spiking of single neurons often occurs at certain phases of the global oscillation. Oscillatory modulation has been examined in relation to continuous-valued oscillatory signals, and independently from the spike train alone, but behavior or stimulus triggered firing-rate modulation, spiking sparseness, presence of slow modulation not locked to stimuli and irregular oscillations with large variability in oscillatory periods, present challenges to searching for temporal structures present in the spike train. In order to study oscillatory modulation in real data collected under a variety of experimental conditions, we describe a flexible point-process framework we call the Latent Oscillatory Spike Train (LOST) model to decompose the instantaneous firing rate in biologically and behaviorally relevant factors: spiking refractoriness, event-locked firing rate non-stationarity, and trial-to-trial variability accounted for by baseline offset and a stochastic oscillatory modulation. We also extend the LOST model to accommodate changes in the modulatory structure over the duration of the experiment, and thereby discover trial-to-trial variability in the spike-field coherence of a rat primary motor cortical neuron to the LFP theta rhythm. Because LOST incorporates a latent stochastic auto-regressive term, LOST is able to detect oscillations when the firing rate is low, the modulation is weak, and when the modulating oscillation has a broad spectral peak.

  10. Cooperative and Competitive Contextual Effects on Social Cognitive and Empathic Neural Responses

    Directory of Open Access Journals (Sweden)

    Minhye Lee

    2018-06-01

    Full Text Available We aimed to differentiate the neural responses to cooperative and competitive contexts, which are the two of the most important social contexts in human society. Healthy male college students were asked to complete a Tetris-like task requiring mental rotation skills under individual, cooperative, and competitive contexts in an fMRI scanner. While the participants completed the task, pictures of others experiencing pain evoking emotional empathy randomly appeared to capture contextual effects on empathic neural responses. Behavioral results indicated that, in the presence of cooperation, participants solved the tasks more accurately and quickly than what they did when in the presence of competition. The fMRI results revealed activations in the dorsolateral prefrontal cortex (dlPFC and dorsomedial prefrontal cortex (dmPFC related to executive functions and theory of mind when participants performed the task under both cooperative and competitive contexts, whereas no activation of such areas was observed in the individual context. Cooperation condition exhibited stronger neural responses in the ventromedial prefrontal cortex (vmPFC and dmPFC than competition condition. Competition condition, however, showed marginal neural responses in the cerebellum and anterior insular cortex (AIC. The two social contexts involved stronger empathic neural responses to other’s pain than the individual context, but no substantial differences between cooperation and competition were present. Regions of interest analyses revealed that individual’s trait empathy modulated the neural activity in the state empathy network, the AIC, and the dorsal anterior cingulate cortex (dACC depending on the social context. These results suggest that cooperation improves task performance and activates neural responses associated with reward and mentalizing. Furthermore, the interaction between trait- and state-empathy was explored by correlation analyses between individual

  11. Behaviour in O of the Neural Networks Training Cost

    DEFF Research Database (Denmark)

    Goutte, Cyril

    1998-01-01

    We study the behaviour in zero of the derivatives of the cost function used when training non-linear neural networks. It is shown that a fair number offirst, second and higher order derivatives vanish in zero, validating the belief that 0 is a peculiar and potentially harmful location. These calc......We study the behaviour in zero of the derivatives of the cost function used when training non-linear neural networks. It is shown that a fair number offirst, second and higher order derivatives vanish in zero, validating the belief that 0 is a peculiar and potentially harmful location....... These calculations arerelated to practical and theoretical aspects of neural networks training....

  12. International cooperation experiences of Korea in nuclear education and training

    International Nuclear Information System (INIS)

    Suh, In-Suk

    1996-01-01

    Man power development is an essential key to success in implementing nuclear projects, especially when maximum local participation is an important issue in every sector of nuclear industry. Bearing this in mind, the Korean Atomic Energy Research Institute (KAERI) founded the Nuclear Training Center (NTC). The Center began to train technical personnel in the fields of radioisotope utilization and radiation protection in 1960s. During the first stage of nuclear power project in ROK in 1970s, the main effort was exerted to the training of those in nuclear power and nuclear engineering sectors. During the stage of increased technical self-reliance in 1980s, its training role was extended to the implementation of more specific training courses on nuclear power and safety fields. As of the end of 1995, about 23,000 people received the training courses. In an attempt to upgrade the nuclear technology, the advanced training courses at the NTC by invited foreign experts and by IAEA technical cooperation program have been implemented. Also the training under IAEA Regional Cooperative Agreement in Asia Pacific Region has been offered. The change of the NTC to the International Training Center is recommended. (K.I.)

  13. Enhancing Expectations of Cooperative Learning Use through Initial Teacher Training

    Science.gov (United States)

    Duran Gisbert, David; Corcelles Seuba, Mariona; Flores Coll, Marta

    2017-01-01

    Despite its relevance and evidence support, Cooperative Learning (CL) is a challenge for all educational systems due to the difficulties in its implementation. The objective of this study is to identify the effect of Primary Education initial teacher training in the prediction of future CL use. Two groups of 44 and 45 students were conceptually…

  14. Prefreshman and Cooperative Education Program. [PREFACE training

    Science.gov (United States)

    1976-01-01

    Of the 93 students enrolled in the PREFACE program over its four-year history, 70 are still in engineering school. Tables show profiles of student placement and participation from 1973 to 1977 (first semester completed). During the 1977 summer, 10 students were placed at NASA Goddard, 8 at DOE-Brookhaven, and 2 at American Can. Eleven students with less high school math preparation remained on campus for formal precalculus classes. Majors of the students in the program include civil, chemical, electrical, and mechanical engineering. Student satisfaction with their training experiences is summarized.

  15. Neural network training by Kalman filtering in process system monitoring

    International Nuclear Information System (INIS)

    Ciftcioglu, Oe.

    1996-03-01

    Kalman filtering approach for neural network training is described. Its extended form is used as an adaptive filter in a nonlinear environment of the form a feedforward neural network. Kalman filtering approach generally provides fast training as well as avoiding excessive learning which results in enhanced generalization capability. The network is used in a process monitoring application where the inputs are measurement signals. Since the measurement errors are also modelled in Kalman filter the approach yields accurate training with the implication of accurate neural network model representing the input and output relationships in the application. As the process of concern is a dynamic system, the input source of information to neural network is time dependent so that the training algorithm presents an adaptive form for real-time operation for the monitoring task. (orig.)

  16. Periodic oscillatory solution in delayed competitive-cooperative neural networks: A decomposition approach

    International Nuclear Information System (INIS)

    Yuan Kun; Cao Jinde

    2006-01-01

    In this paper, the problems of exponential convergence and the exponential stability of the periodic solution for a general class of non-autonomous competitive-cooperative neural networks are analyzed via the decomposition approach. The idea is to divide the connection weights into inhibitory or excitatory types and thereby to embed a competitive-cooperative delayed neural network into an augmented cooperative delay system through a symmetric transformation. Some simple necessary and sufficient conditions are derived to ensure the componentwise exponential convergence and the exponential stability of the periodic solution of the considered neural networks. These results generalize and improve the previous works, and they are easy to check and apply in practice

  17. The Neural Responses to Social Cooperation in Gain and Loss Context.

    Directory of Open Access Journals (Sweden)

    Peng Sun

    Full Text Available Cooperation is pervasive and constitutes the core behavioral principle of human social life. Previous studies have revealed that mutual cooperation was reliably correlated with two reward-related brain regions, the ventral striatum and the orbitofrontal cortex. Using functional magnetic resonance imaging (fMRI, this study sought to investigate how the loss and gain contexts modulated the neural responses to mutual cooperation. Twenty-five female participants were scanned when they played a series of one-shot prisoner's dilemma games in the loss and gain contexts. Specifically, participants and partners independently chose to either cooperate with each other or not, and each was awarded or deprived of (in the gain context or the loss context, respectively a sum of money which depended upon the interaction of their choices. Behavioral results indicated that participants cooperated in nearly half of the experiment trials and reported higher level of positive emotions for mutual cooperation in both contexts, but they cooperated more in the gain than in the loss context. At the neural level, stronger activities in the orbitofrontal cortex were observed for mutual cooperation compared with the other three outcomes in both contexts, while stronger activation in ventral striatum associated with mutual cooperation was observed in the gain context only. Together, our data indicated that, even in the one-shot interaction under loss context, participants still exhibited preference for cooperation and the rewarding experience from a mutually cooperative social interaction activated the ventral striatum and the orbitofrontal cortex, but the loss context weakened the association between the ventral striatum activation and mutual cooperation.

  18. Teamwork, taxes, and training: A case for cooperation and quality

    International Nuclear Information System (INIS)

    Hayward, G.B.

    1993-01-01

    Training to ensure compliance with the myriad of laws and regulations imposed by federal, state, and local governments is a trend that will continue well into the 1990s. The cost of this training increasingly takes away from the bottom line of many companies and adds additional costs to the products and services being developed and sold. This cost is passed on to the consumer. When the government or one of its contractors incurs additional costs, they are passed on to the taxpayer. As budgets shrink and requirements go up it makes sense to find a way to maintain high quality and cut costs. The Quality Training and Resource Center was established at Hanford by the US Department of Energy to do just that; cut costs and maintain quality. This paper will explore the methodology used to establish a model based on contractor cooperation, teamwork, and resource sharing to improve training while Towering costs

  19. Variation in Behavioral Reactivity Is Associated with Cooperative Restraint Training Efficiency

    OpenAIRE

    Bliss-Moreau, Eliza; Moadab, Gilda

    2016-01-01

    Training techniques that prepare laboratory animals to participate in testing via cooperation are useful tools that have the potential to benefit animal wellbeing. Understanding how animals systematically vary in their cooperative training trajectories will help trainers to design effective and efficient training programs. In the present report we document an updated method for training rhesus monkeys to cooperatively participate in restraint in a ‘primate chair.’ We trained 14 adult male mac...

  20. 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...

  1. Sex differences in neural and behavioral signatures of cooperation revealed by fNIRS hyperscanning

    Science.gov (United States)

    Baker, Joseph M.; Liu, Ning; Cui, Xu; Vrticka, Pascal; Saggar, Manish; Hosseini, S. M. Hadi; Reiss, Allan L.

    2016-01-01

    Researchers from multiple fields have sought to understand how sex moderates human social behavior. While over 50 years of research has revealed differences in cooperation behavior of males and females, the underlying neural correlates of these sex differences have not been explained. A missing and fundamental element of this puzzle is an understanding of how the sex composition of an interacting dyad influences the brain and behavior during cooperation. Using fNIRS-based hyperscanning in 111 same- and mixed-sex dyads, we identified significant behavioral and neural sex-related differences in association with a computer-based cooperation task. Dyads containing at least one male demonstrated significantly higher behavioral performance than female/female dyads. Individual males and females showed significant activation in the right frontopolar and right inferior prefrontal cortices, although this activation was greater in females compared to males. Female/female dyad’s exhibited significant inter-brain coherence within the right temporal cortex, while significant coherence in male/male dyads occurred in the right inferior prefrontal cortex. Significant coherence was not observed in mixed-sex dyads. Finally, for same-sex dyads only, task-related inter-brain coherence was positively correlated with cooperation task performance. Our results highlight multiple important and previously undetected influences of sex on concurrent neural and behavioral signatures of cooperation. PMID:27270754

  2. Method Accelerates Training Of Some Neural Networks

    Science.gov (United States)

    Shelton, Robert O.

    1992-01-01

    Three-layer networks trained faster provided two conditions are satisfied: numbers of neurons in layers are such that majority of work done in synaptic connections between input and hidden layers, and number of neurons in input layer at least as great as number of training pairs of input and output vectors. Based on modified version of back-propagation method.

  3. Neural Plastic Effects of Cognitive Training on Aging Brain

    Directory of Open Access Journals (Sweden)

    Natalie T. Y. Leung

    2015-01-01

    Full Text Available Increasing research has evidenced that our brain retains a capacity to change in response to experience until late adulthood. This implies that cognitive training can possibly ameliorate age-associated cognitive decline by inducing training-specific neural plastic changes at both neural and behavioral levels. This longitudinal study examined the behavioral effects of a systematic thirteen-week cognitive training program on attention and working memory of older adults who were at risk of cognitive decline. These older adults were randomly assigned to the Cognitive Training Group (n=109 and the Active Control Group (n=100. Findings clearly indicated that training induced improvement in auditory and visual-spatial attention and working memory. The training effect was specific to the experience provided because no significant difference in verbal and visual-spatial memory between the two groups was observed. This pattern of findings is consistent with the prediction and the principle of experience-dependent neuroplasticity. Findings of our study provided further support to the notion that the neural plastic potential continues until older age. The baseline cognitive status did not correlate with pre- versus posttraining changes to any cognitive variables studied, suggesting that the initial cognitive status may not limit the neuroplastic potential of the brain at an old age.

  4. Neural Plastic Effects of Cognitive Training on Aging Brain.

    Science.gov (United States)

    Leung, Natalie T Y; Tam, Helena M K; Chu, Leung W; Kwok, Timothy C Y; Chan, Felix; Lam, Linda C W; Woo, Jean; Lee, Tatia M C

    2015-01-01

    Increasing research has evidenced that our brain retains a capacity to change in response to experience until late adulthood. This implies that cognitive training can possibly ameliorate age-associated cognitive decline by inducing training-specific neural plastic changes at both neural and behavioral levels. This longitudinal study examined the behavioral effects of a systematic thirteen-week cognitive training program on attention and working memory of older adults who were at risk of cognitive decline. These older adults were randomly assigned to the Cognitive Training Group (n = 109) and the Active Control Group (n = 100). Findings clearly indicated that training induced improvement in auditory and visual-spatial attention and working memory. The training effect was specific to the experience provided because no significant difference in verbal and visual-spatial memory between the two groups was observed. This pattern of findings is consistent with the prediction and the principle of experience-dependent neuroplasticity. Findings of our study provided further support to the notion that the neural plastic potential continues until older age. The baseline cognitive status did not correlate with pre- versus posttraining changes to any cognitive variables studied, suggesting that the initial cognitive status may not limit the neuroplastic potential of the brain at an old age.

  5. Competition and Cooperation in Neural Nets : U.S.-Japan Joint Seminar

    CERN Document Server

    Arbib, Michael

    1982-01-01

    The human brain, wi th its hundred billion or more neurons, is both one of the most complex systems known to man and one of the most important. The last decade has seen an explosion of experimental research on the brain, but little theory of neural networks beyond the study of electrical properties of membranes and small neural circuits. Nonetheless, a number of workers in Japan, the United States and elsewhere have begun to contribute to a theory which provides techniques of mathematical analysis and computer simulation to explore properties of neural systems containing immense numbers of neurons. Recently, it has been gradually recognized that rather independent studies of the dynamics of pattern recognition, pattern format::ion, motor control, self-organization, etc. , in neural systems do in fact make use of common methods. We find that a "competition and cooperation" type of interaction plays a fundamental role in parallel information processing in the brain. The present volume brings together 23 papers ...

  6. Bayesian model ensembling using meta-trained recurrent neural networks

    NARCIS (Netherlands)

    Ambrogioni, L.; Berezutskaya, Y.; Gü ç lü , U.; Borne, E.W.P. van den; Gü ç lü tü rk, Y.; Gerven, M.A.J. van; Maris, E.G.G.

    2017-01-01

    In this paper we demonstrate that a recurrent neural network meta-trained on an ensemble of arbitrary classification tasks can be used as an approximation of the Bayes optimal classifier. This result is obtained by relying on the framework of e-free approximate Bayesian inference, where the Bayesian

  7. Neural mirroring and social interaction: Motor system involvement during action observation relates to early peer cooperation.

    Science.gov (United States)

    Endedijk, H M; Meyer, M; Bekkering, H; Cillessen, A H N; Hunnius, S

    2017-04-01

    Whether we hand over objects to someone, play a team sport, or make music together, social interaction often involves interpersonal action coordination, both during instances of cooperation and entrainment. Neural mirroring is thought to play a crucial role in processing other's actions and is therefore considered important for social interaction. Still, to date, it is unknown whether interindividual differences in neural mirroring play a role in interpersonal coordination during different instances of social interaction. A relation between neural mirroring and interpersonal coordination has particularly relevant implications for early childhood, since successful early interaction with peers is predictive of a more favorable social development. We examined the relation between neural mirroring and children's interpersonal coordination during peer interaction using EEG and longitudinal behavioral data. Results showed that 4-year-old children with higher levels of motor system involvement during action observation (as indicated by lower beta-power) were more successful in early peer cooperation. This is the first evidence for a relation between motor system involvement during action observation and interpersonal coordination during other instances of social interaction. The findings suggest that interindividual differences in neural mirroring are related to interpersonal coordination and thus successful social interaction. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

  8. Novel maximum-margin training algorithms for supervised neural networks.

    Science.gov (United States)

    Ludwig, Oswaldo; Nunes, Urbano

    2010-06-01

    This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by

  9. Training strategy for convolutional neural networks in pedestrian gender classification

    Science.gov (United States)

    Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min

    2017-06-01

    In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.

  10. Training Feedforward Neural Networks Using Symbiotic Organisms Search Algorithm

    Directory of Open Access Journals (Sweden)

    Haizhou Wu

    2016-01-01

    Full Text Available Symbiotic organisms search (SOS is a new robust and powerful metaheuristic algorithm, which stimulates the symbiotic interaction strategies adopted by organisms to survive and propagate in the ecosystem. In the supervised learning area, it is a challenging task to present a satisfactory and efficient training algorithm for feedforward neural networks (FNNs. In this paper, SOS is employed as a new method for training FNNs. To investigate the performance of the aforementioned method, eight different datasets selected from the UCI machine learning repository are employed for experiment and the results are compared among seven metaheuristic algorithms. The results show that SOS performs better than other algorithms for training FNNs in terms of converging speed. It is also proven that an FNN trained by the method of SOS has better accuracy than most algorithms compared.

  11. Supervised learning in spiking neural networks with FORCE training.

    Science.gov (United States)

    Nicola, Wilten; Clopath, Claudia

    2017-12-20

    Populations of neurons display an extraordinary diversity in the behaviors they affect and display. Machine learning techniques have recently emerged that allow us to create networks of model neurons that display behaviors of similar complexity. Here we demonstrate the direct applicability of one such technique, the FORCE method, to spiking neural networks. We train these networks to mimic dynamical systems, classify inputs, and store discrete sequences that correspond to the notes of a song. Finally, we use FORCE training to create two biologically motivated model circuits. One is inspired by the zebra finch and successfully reproduces songbird singing. The second network is motivated by the hippocampus and is trained to store and replay a movie scene. FORCE trained networks reproduce behaviors comparable in complexity to their inspired circuits and yield information not easily obtainable with other techniques, such as behavioral responses to pharmacological manipulations and spike timing statistics.

  12. Training for Micrographia Alters Neural Connectivity in Parkinson's Disease

    Directory of Open Access Journals (Sweden)

    Evelien Nackaerts

    2018-01-01

    Full Text Available Despite recent advances in clarifying the neural networks underlying rehabilitation in Parkinson's disease (PD, the impact of prolonged motor learning interventions on brain connectivity in people with PD is currently unknown. Therefore, the objective of this study was to compare cortical network changes after 6 weeks of visually cued handwriting training (= experimental with a placebo intervention to address micrographia, a common problem in PD. Twenty seven early Parkinson's patients on dopaminergic medication performed a pre-writing task in both the presence and absence of visual cues during behavioral tests and during fMRI. Subsequently, patients were randomized to the experimental (N = 13 or placebo intervention (N = 14 both lasting 6 weeks, after which they underwent the same testing procedure. We used dynamic causal modeling to compare the neural network dynamics in both groups before and after training. Most importantly, intensive writing training propagated connectivity via the left hemispheric visuomotor stream to an increased coupling with the supplementary motor area, not witnessed in the placebo group. Training enhanced communication in the left visuomotor integration system in line with the learned visually steered training. Notably, this pattern was apparent irrespective of the presence of cues, suggesting transfer from cued to uncued handwriting. We conclude that in early PD intensive motor skill learning, which led to clinical improvement, alters cortical network functioning. We showed for the first time in a placebo-controlled design that it remains possible to enhance the drive to the supplementary motor area through motor learning.

  13. Accelerating deep neural network training with inconsistent stochastic gradient descent.

    Science.gov (United States)

    Wang, Linnan; Yang, Yi; Min, Renqiang; Chakradhar, Srimat

    2017-09-01

    Stochastic Gradient Descent (SGD) updates Convolutional Neural Network (CNN) with a noisy gradient computed from a random batch, and each batch evenly updates the network once in an epoch. This model applies the same training effort to each batch, but it overlooks the fact that the gradient variance, induced by Sampling Bias and Intrinsic Image Difference, renders different training dynamics on batches. In this paper, we develop a new training strategy for SGD, referred to as Inconsistent Stochastic Gradient Descent (ISGD) to address this problem. The core concept of ISGD is the inconsistent training, which dynamically adjusts the training effort w.r.t the loss. ISGD models the training as a stochastic process that gradually reduces down the mean of batch's loss, and it utilizes a dynamic upper control limit to identify a large loss batch on the fly. ISGD stays on the identified batch to accelerate the training with additional gradient updates, and it also has a constraint to penalize drastic parameter changes. ISGD is straightforward, computationally efficient and without requiring auxiliary memories. A series of empirical evaluations on real world datasets and networks demonstrate the promising performance of inconsistent training. Copyright © 2017 Elsevier Ltd. All rights reserved.

  14. Trust as commodity: social value orientation affects the neural substrates of learning to cooperate.

    Science.gov (United States)

    Lambert, Bruno; Declerck, Carolyn H; Emonds, Griet; Boone, Christophe

    2017-04-01

    Individuals differ in their motives and strategies to cooperate in social dilemmas. These differences are reflected by an individual's social value orientation: proselfs are strategic and motivated to maximize self-interest, while prosocials are more trusting and value fairness. We hypothesize that when deciding whether or not to cooperate with a random member of a defined group, proselfs, more than prosocials, adapt their decisions based on past experiences: they 'learn' instrumentally to form a base-line expectation of reciprocity. We conducted an fMRI experiment where participants (19 proselfs and 19 prosocials) played 120 sequential prisoner's dilemmas against randomly selected, anonymous and returning partners who cooperated 60% of the time. Results indicate that cooperation levels increased over time, but that the rate of learning was steeper for proselfs than for prosocials. At the neural level, caudate and precuneus activation were more pronounced for proselfs relative to prosocials, indicating a stronger reliance on instrumental learning and self-referencing to update their trust in the cooperative strategy. © The Author (2017). Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

  15. Consistently Trained Artificial Neural Network for Automatic Ship Berthing Control

    Directory of Open Access Journals (Sweden)

    Y.A. Ahmed

    2015-09-01

    Full Text Available In this paper, consistently trained Artificial Neural Network controller for automatic ship berthing is discussed. Minimum time course changing manoeuvre is utilised to ensure such consistency and a new concept named ‘virtual window’ is introduced. Such consistent teaching data are then used to train two separate multi-layered feed forward neural networks for command rudder and propeller revolution output. After proper training, several known and unknown conditions are tested to judge the effectiveness of the proposed controller using Monte Carlo simulations. After getting acceptable percentages of success, the trained networks are implemented for the free running experiment system to judge the network’s real time response for Esso Osaka 3-m model ship. The network’s behaviour during such experiments is also investigated for possible effect of initial conditions as well as wind disturbances. Moreover, since the final goal point of the proposed controller is set at some distance from the actual pier to ensure safety, therefore a study on automatic tug assistance is also discussed for the final alignment of the ship with actual pier.

  16. Shakeout: A New Approach to Regularized Deep Neural Network Training.

    Science.gov (United States)

    Kang, Guoliang; Li, Jun; Tao, Dacheng

    2018-05-01

    Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines , and regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

  17. Modelling electric trains energy consumption using Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Martinez Fernandez, P.; Garcia Roman, C.; Insa Franco, R.

    2016-07-01

    Nowadays there is an evident concern regarding the efficiency and sustainability of the transport sector due to both the threat of climate change and the current financial crisis. This concern explains the growth of railways over the last years as they present an inherent efficiency compared to other transport means. However, in order to further expand their role, it is necessary to optimise their energy consumption so as to increase their competitiveness. Improving railways energy efficiency requires both reliable data and modelling tools that will allow the study of different variables and alternatives. With this need in mind, this paper presents the development of consumption models based on neural networks that calculate the energy consumption of electric trains. These networks have been trained based on an extensive set of consumption data measured in line 1 of the Valencia Metro Network. Once trained, the neural networks provide a reliable estimation of the vehicles consumption along a specific route when fed with input data such as train speed, acceleration or track longitudinal slope. These networks represent a useful modelling tool that may allow a deeper study of railway lines in terms of energy expenditure with the objective of reducing the costs and environmental impact associated to railways. (Author)

  18. An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks.

    Science.gov (United States)

    Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen

    2016-01-01

    The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper.

  19. Audio-Visual Aids for Cooperative Education and Training.

    Science.gov (United States)

    Botham, C. N.

    Within the context of cooperative education, audiovisual aids may be used for spreading the idea of cooperatives and helping to consolidate study groups; for the continuous process of education, both formal and informal, within the cooperative movement; for constant follow up purposes; and for promoting loyalty to the movement. Detailed…

  20. Training feed-forward neural networks with gain constraints

    Science.gov (United States)

    Hartman

    2000-04-01

    Inaccurate input-output gains (partial derivatives of outputs with respect to inputs) are common in neural network models when input variables are correlated or when data are incomplete or inaccurate. Accurate gains are essential for optimization, control, and other purposes. We develop and explore a method for training feedforward neural networks subject to inequality or equality-bound constraints on the gains of the learned mapping. Gain constraints are implemented as penalty terms added to the objective function, and training is done using gradient descent. Adaptive and robust procedures are devised for balancing the relative strengths of the various terms in the objective function, which is essential when the constraints are inconsistent with the data. The approach has the virtue that the model domain of validity can be extended via extrapolation training, which can dramatically improve generalization. The algorithm is demonstrated here on artificial and real-world problems with very good results and has been advantageously applied to dozens of models currently in commercial use.

  1. Deep Convolutional Neural Networks: Structure, Feature Extraction and Training

    Directory of Open Access Journals (Sweden)

    Namatēvs Ivars

    2017-12-01

    Full Text Available Deep convolutional neural networks (CNNs are aimed at processing data that have a known network like topology. They are widely used to recognise objects in images and diagnose patterns in time series data as well as in sensor data classification. The aim of the paper is to present theoretical and practical aspects of deep CNNs in terms of convolution operation, typical layers and basic methods to be used for training and learning. Some practical applications are included for signal and image classification. Finally, the present paper describes the proposed block structure of CNN for classifying crucial features from 3D sensor data.

  2. Training and validation of the ATLAS pixel clustering neural networks

    CERN Document Server

    The ATLAS collaboration

    2018-01-01

    The high centre-of-mass energy of the LHC gives rise to dense environments, such as the core of high-pT jets, in which the charge clusters left by ionising particles in the silicon sensors of the pixel detector can merge, compromising the tracking and vertexing efficiency. To recover optimal performance, a neural network-based approach is used to separate clusters originating from single and multiple particles and to estimate all hit positions within clusters. This note presents the training strategy employed and a set of benchmark performance measurements on a Monte Carlo sample of high-pT dijet events.

  3. A Phenomenological Study of Experienced Teacher Perceptions Regarding Cooperative Learning Training and Cooperative Learning Implementation in the Classroom

    Science.gov (United States)

    Robinson, Susan Rubino

    2012-01-01

    This qualitative phenomenological study sought to explore the perceptions of experienced teachers regarding cooperative learning training and its implementation in the classroom. Twelve total participants, nine teachers and three administrators, volunteered for this six-week study at a private, K3-12 school in Broward County, Florida. The study's…

  4. [Multiprofessional family-system training programme in psychiatry--effects on team cooperation and staff strain].

    Science.gov (United States)

    Zwack, Julika; Schweitzer, Jochen

    2008-01-01

    How does the interdisciplinary cooperation of psychiatric staff members change after a multiprofessional family systems training programme? Semi-structured interviews were conducted with 49 staff members. Quantitative questionnaires were used to assess burnout (Maslach Burnout Inventory, MBI) and team climate (Team-Klima-Inventar, TKI). The multiprofessional training intensifies interdisciplinary cooperation. It results in an increased appreciation of the nurses involved and in a redistribution of therapeutic tasks between nurses, psychologists and physicians. Staff burnout decreased during the research period, while task orientation and participative security within teams increased. The multiprofessional family systems training appears suitable to improve quality of patient care and interdisciplinary cooperation and to reduce staff burnout.

  5. Safety Training Parks – Cooperative Contribution to Safety and Health Trainings

    DEFF Research Database (Denmark)

    Reiman, Arto; Pedersen, Louise Møller; Väyrynen, Seppo

    2017-01-01

    . The concept of Safety Training Park (STP) has been developed to meet these challenges. Eighty stakeholders from the Finnish construction industry have been involved in the construction and financing of the STP in northern Finland (STPNF). This unique cooperation has contributed to the immediate success......, and evidence from the literature are presented with a focus on the pros and cons of the STPNF. The STP is a new and innovative method for safety training that stimulates different learning styles and inspires changes in individuals’ behavior and in the organizations’ safety climate. The stakeholders’ high...... commitment, a long-term perspective, and a strong safety climate are identified as preconditions for the STP concept to work....

  6. Stereo-vision-based cooperative-vehicle positioning using OCC and neural networks

    Science.gov (United States)

    Ifthekhar, Md. Shareef; Saha, Nirzhar; Jang, Yeong Min

    2015-10-01

    Vehicle positioning has been subjected to extensive research regarding driving safety measures and assistance as well as autonomous navigation. The most common positioning technique used in automotive positioning is the global positioning system (GPS). However, GPS is not reliably accurate because of signal blockage caused by high-rise buildings. In addition, GPS is error prone when a vehicle is inside a tunnel. Moreover, GPS and other radio-frequency-based approaches cannot provide orientation information or the position of neighboring vehicles. In this study, we propose a cooperative-vehicle positioning (CVP) technique by using the newly developed optical camera communications (OCC). The OCC technique utilizes image sensors and cameras to receive and decode light-modulated information from light-emitting diodes (LEDs). A vehicle equipped with an OCC transceiver can receive positioning and other information such as speed, lane change, driver's condition, etc., through optical wireless links of neighboring vehicles. Thus, the target vehicle position that is too far away to establish an OCC link can be determined by a computer-vision-based technique combined with the cooperation of neighboring vehicles. In addition, we have devised a back-propagation (BP) neural-network learning method for positioning and range estimation for CVP. The proposed neural-network-based technique can estimate target vehicle position from only two image points of target vehicles using stereo vision. For this, we use rear LEDs on target vehicles as image points. We show from simulation results that our neural-network-based method achieves better accuracy than that of the computer-vision method.

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

    Science.gov (United States)

    Chen, Weisheng; Hua, Shaoyong; Zhang, Huaguang

    2015-02-01

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

  8. A Cooperative Training Program for Students with Severe Behavior Problems: Description and Comparative Evaluation.

    Science.gov (United States)

    Reganick, Karol A.

    The Cooperative Training Program was implemented with 20 students having severe behavior problems, to augment a classroom employability curriculum. Educators and business managers at a local Perkins restaurant worked cooperatively to design a new curriculum and recruitment procedure to benefit both students and the business. A continuous and…

  9. Training of reverse propagation neural networks applied to neutron dosimetry

    International Nuclear Information System (INIS)

    Hernandez P, C. F.; Martinez B, M. R.; Leon P, A. A.; Espinoza G, J. G.; Castaneda M, V. H.; Solis S, L. O.; Castaneda M, R.; Ortiz R, M.; Vega C, H. R.; Mendez V, R.; Gallego, E.; De Sousa L, M. A.

    2016-10-01

    Neutron dosimetry is of great importance in radiation protection as aims to provide dosimetric quantities to assess the magnitude of detrimental health effects due to exposure of neutron radiation. To quantify detriment to health is necessary to evaluate the dose received by the occupationally exposed personnel using different detection systems called dosimeters, which have very dependent responses to the energy distribution of neutrons. The neutron detection is a much more complex problem than the detection of charged particles, since it does not carry an electric charge, does not cause direct ionization and has a greater penetration power giving the possibility of interacting with matter in a different way. Because of this, various neutron detection systems have been developed, among which the Bonner spheres spectrometric system stands out due to the advantages that possesses, such as a wide range of energy, high sensitivity and easy operation. However, once obtained the counting rates, the problem lies in the neutron spectrum deconvolution, necessary for the calculation of the doses, using different mathematical methods such as Monte Carlo, maximum entropy, iterative methods among others, which present various difficulties that have motivated the development of new technologies. Nowadays, methods based on artificial intelligence technologies are being used to perform neutron dosimetry, mainly using the theory of artificial neural networks. In these new methods the need for spectrum reconstruction can be eliminated for the calculation of the doses. In this work an artificial neural network or reverse propagation was trained for the calculation of 15 equivalent doses from the counting rates of the Bonner spheres spectrometric system using a set of 7 spheres, one of 2 spheres and two of a single sphere of different sizes, testing different error values until finding the most appropriate. The optimum network topology was obtained through the robust design

  10. Promoting Cooperative Learning in the Classroom: Comparing Explicit and Implicit Training Techniques

    Directory of Open Access Journals (Sweden)

    Anne Elliott

    2003-07-01

    Full Text Available In this study, we investigated whether providing 4th and 5th-grade students with explicit instruction in prerequisite cooperative-learning skills and techniques would enhance their academic performance and promote in them positive attitudes towards cooperative learning. Overall, students who received explicit training outperformed their peers on both the unit project and test and presented more favourable attitudes towards cooperative learning. The findings of this study support the use of explicitly instructing students about the components of cooperative learning prior to engaging in collaborative activities. Implications for teacher-education are discussed.

  11. Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction.

    Science.gov (United States)

    Watanabe, Eiji; Kitaoka, Akiyoshi; Sakamoto, Kiwako; Yasugi, Masaki; Tanaka, Kenta

    2018-01-01

    The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning) predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research.

  12. Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction

    Directory of Open Access Journals (Sweden)

    Eiji Watanabe

    2018-03-01

    Full Text Available The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research.

  13. The Industrial Vocational High School Teacher Training Program Cooperating with the Enterprises.

    Science.gov (United States)

    Chi, Cheng-Feng

    Training of vocational education teachers should be closely linked to the industries in which the teachers are preparing to instruct students. A teacher training program in Taiwan has been designed with the cooperation of the metals manufacturing industry. In this four-year program, students are assigned to the industry to learn the product…

  14. Artificial Neural Network with Hardware Training and Hardware Refresh

    Science.gov (United States)

    Duong, Tuan A. (Inventor)

    2003-01-01

    A neural network circuit is provided having a plurality of circuits capable of charge storage. Also provided is a plurality of circuits each coupled to at least one of the plurality of charge storage circuits and constructed to generate an output in accordance with a neuron transfer function. Each of a plurality of circuits is coupled to one of the plurality of neuron transfer function circuits and constructed to generate a derivative of the output. A weight update circuit updates the charge storage circuits based upon output from the plurality of transfer function circuits and output from the plurality of derivative circuits. In preferred embodiments, separate training and validation networks share the same set of charge storage circuits and may operate concurrently. The validation network has a separate transfer function circuits each being coupled to the charge storage circuits so as to replicate the training network s coupling of the plurality of charge storage to the plurality of transfer function circuits. The plurality of transfer function circuits may be constructed each having a transconductance amplifier providing differential currents combined to provide an output in accordance with a transfer function. The derivative circuits may have a circuit constructed to generate a biased differential currents combined so as to provide the derivative of the transfer function.

  15. Training Spiking Neural Models Using Artificial Bee Colony

    Science.gov (United States)

    Vazquez, Roberto A.; Garro, Beatriz A.

    2015-01-01

    Spiking neurons are models designed to simulate, in a realistic manner, the behavior of biological neurons. Recently, it has been proven that this type of neurons can be applied to solve pattern recognition problems with great efficiency. However, the lack of learning strategies for training these models do not allow to use them in several pattern recognition problems. On the other hand, several bioinspired algorithms have been proposed in the last years for solving a broad range of optimization problems, including those related to the field of artificial neural networks (ANNs). Artificial bee colony (ABC) is a novel algorithm based on the behavior of bees in the task of exploring their environment to find a food source. In this paper, we describe how the ABC algorithm can be used as a learning strategy to train a spiking neuron aiming to solve pattern recognition problems. Finally, the proposed approach is tested on several pattern recognition problems. It is important to remark that to realize the powerfulness of this type of model only one neuron will be used. In addition, we analyze how the performance of these models is improved using this kind of learning strategy. PMID:25709644

  16. The Effect of Training Data Set Composition on the Performance of a Neural Image Caption Generator

    Science.gov (United States)

    2017-09-01

    REPORT TYPE Technical Report 3. DATES COVERED (From - To) 4. TITLE AND SUBTITLE The Effect of Training Data Set Composition on the Performance of a...ARL-TR-8124 ● SEP 2017 US Army Research Laboratory The Effect of Training Data Set Composition on the Performance of a Neural...Laboratory The Effect of Training Data Set Composition on the Performance of a Neural Image Caption Generator by Abigail Wilson Montgomery Blair

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

    International Nuclear Information System (INIS)

    Proriol, J.

    1994-01-01

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

  18. Neural and morphological adaptations of vastus lateralis and vastus medialis muscles to isokinetic eccentric training

    Directory of Open Access Journals (Sweden)

    Rodrigo de Azevedo Franke

    2014-09-01

    Full Text Available Vastus lateralis (VL and vastus medialis (VM are frequently targeted in conditioning/rehabilitation programs due to their role in patellar stabilization during knee extension. This study assessed neural and muscular adaptations in these two muscles after an isokinetic eccentric training program. Twenty healthy men underwent a four-week control period followed by a 12-week period of isokinetic eccentric training. Ultrasound evaluations of VL and VM muscle thickness at rest and electromyographic evaluations during maximal isometric tests were used to assess the morphological and neural properties, respectively. No morphological and neural changes were found throughout the control period, whereas both muscles showed significant increases in thickness (VL = 6.9%; p .05 post-training. Isokinetic eccentric training produces neural and greater morphological adaptations in VM compared to VL, which shows that synergistic muscles respond differently to an eccentric isokinetic strength training program

  19. Smart Training, Smart Learning: The Role of Cooperative Learning in Training for Youth Services.

    Science.gov (United States)

    Doll, Carol A.

    1997-01-01

    Examines cooperative learning in youth services and adult education. Discusses characteristics of cooperative learning techniques; specific cooperative learning techniques (brainstorming, mini-lecture, roundtable technique, send-a-problem problem solving, talking chips technique, and three-step interview); and the role of the trainer. (AEF)

  20. Strategy of formation and training for the basic units of cooperative production. Actions for their implementation

    Directory of Open Access Journals (Sweden)

    Iriadna Marín de León

    2014-06-01

    The implementation of the strategy of Formation and Training had great importance since applying the same one, they could get rich our cooperatives, of elements that contribute to the obtaining of a bigger level of efficiency and effectiveness of the human resources, given by the knowledge that they can acquire the same ones.   The article approaches the topics of Administration of human resources, formation and training theoretically, the elements of the functional strategy, and lastly a journey for the Cooperative Sector leaving of its emergence until specifying the characteristics of the Basic Units of Cooperative Production as part of the same one.   He is also carried out a valuation of the current situation as for Formation and Training of the human resources in the UBPC of the County of Pinar del Ro. This is made going to different diagnosis techniques. Later on they intend the actions that allow the implementation of this strategy.

  1. A Telescopic Binary Learning Machine for Training Neural Networks.

    Science.gov (United States)

    Brunato, Mauro; Battiti, Roberto

    2017-03-01

    This paper proposes a new algorithm based on multiscale stochastic local search with binary representation for training neural networks [binary learning machine (BLM)]. We study the effects of neighborhood evaluation strategies, the effect of the number of bits per weight and that of the maximum weight range used for mapping binary strings to real values. Following this preliminary investigation, we propose a telescopic multiscale version of local search, where the number of bits is increased in an adaptive manner, leading to a faster search and to local minima of better quality. An analysis related to adapting the number of bits in a dynamic way is presented. The control on the number of bits, which happens in a natural manner in the proposed method, is effective to increase the generalization performance. The learning dynamics are discussed and validated on a highly nonlinear artificial problem and on real-world tasks in many application domains; BLM is finally applied to a problem requiring either feedforward or recurrent architectures for feedback control.

  2. Metadynamics for training neural network model chemistries: A competitive assessment

    Science.gov (United States)

    Herr, John E.; Yao, Kun; McIntyre, Ryker; Toth, David W.; Parkhill, John

    2018-06-01

    Neural network model chemistries (NNMCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail, especially long-range forces. At short range, however, these models are data driven and data limited. Little is systematically known about how data should be sampled, and "test data" chosen randomly from some sampling techniques can provide poor information about generality. If the sampling method is narrow, "test error" can appear encouragingly tiny while the model fails catastrophically elsewhere. In this manuscript, we competitively evaluate two common sampling methods: molecular dynamics (MD), normal-mode sampling, and one uncommon alternative, Metadynamics (MetaMD), for preparing training geometries. We show that MD is an inefficient sampling method in the sense that additional samples do not improve generality. We also show that MetaMD is easily implemented in any NNMC software package with cost that scales linearly with the number of atoms in a sample molecule. MetaMD is a black-box way to ensure samples always reach out to new regions of chemical space, while remaining relevant to chemistry near kbT. It is a cheap tool to address the issue of generalization.

  3. Adaptive training of neural networks for control of autonomous mobile robots

    NARCIS (Netherlands)

    Steur, E.; Vromen, T.; Nijmeijer, H.; Fossen, T.I.; Nijmeijer, H.; Pettersen, K.Y.

    2017-01-01

    We present an adaptive training procedure for a spiking neural network, which is used for control of a mobile robot. Because of manufacturing tolerances, any hardware implementation of a spiking neural network has non-identical nodes, which limit the performance of the controller. The adaptive

  4. Cooperative Learning and Soft Skills Training in an IT Course

    Science.gov (United States)

    Zhang, Aimao

    2012-01-01

    Pedagogy of higher education is shifting from passive to active and deep learning. At the same time, the information technology (IT) industry and the Accreditation Board for Engineering and Technology (ABET) are demanding soft skills training. Thus, in designing an IT course, we devised group teaching projects where students learn to work with…

  5. Establishment of the International Nuclear Education/Training and its Cooperation Framework for Nuclear Transparency

    International Nuclear Information System (INIS)

    Min, B. J.; Han, K. W.; Lee, E. J.

    2009-02-01

    This project covered development and implementation of international nuclear education/training programs, cooperation for nuclear human resource development and education/training. provision of MS and PhD courses for qualified students from developing countries, and strengthening of infrastructure for the nuclear education/training. The WNU one week summer course was held for domestic future generation in nuclear field. NTC operated the ANENT web portal and cyber platform, supported training on their use, and prepared a KAERI-IAEA Practical Arrangement for the promotion of web-base nuclear education/training. For FNCA, an analysis was conducted on the need of nuclear education/training in South East Asian countries. The bilateral cooperation included cooperation with Vietnam. provision of Korean experience for nuclear power personnel from Egypt, and commencing of cooperation with South Africa. Also, NTC participated in GENEP for sharing Korean experience in the nuclear human resource development project. KAERI-UST MA and PhD courses with 3 foreign students started in spring 2008 and implemented. The courses were advance nuclear reactor system engineering, accelerator and nano-beam engineering, and radiation measurement science. 13 international nuclear education/training courses (IAEA, KOICA, RCARO and bilateral) were implemented for 226 foreign trainees. A reference education/training program was developed, which consisted of 15 courses that can be customized to learner levels and project stages of countries in question (e.g. Middle East. Africa). A textbook entitled 'Research Reactor Design, Management and Utilization' was developed presenting Korean experience with research reactors

  6. On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation

    OpenAIRE

    He, Tianxing; Zhang, Yu; Droppo, Jasha; Yu, Kai

    2016-01-01

    We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It is shown that NCE-trained bi-directional NNLM outperformed the one trained by conventional maximum likelihood training. But still(regretfully), it did not out-perform the baseline uni-directional NNLM.

  7. Cooperative learning neural network output feedback control of uncertain nonlinear multi-agent systems under directed topologies

    Science.gov (United States)

    Wang, W.; Wang, D.; Peng, Z. H.

    2017-09-01

    Without assuming that the communication topologies among the neural network (NN) weights are to be undirected and the states of each agent are measurable, the cooperative learning NN output feedback control is addressed for uncertain nonlinear multi-agent systems with identical structures in strict-feedback form. By establishing directed communication topologies among NN weights to share their learned knowledge, NNs with cooperative learning laws are employed to identify the uncertainties. By designing NN-based κ-filter observers to estimate the unmeasurable states, a new cooperative learning output feedback control scheme is proposed to guarantee that the system outputs can track nonidentical reference signals with bounded tracking errors. A simulation example is given to demonstrate the effectiveness of the theoretical results.

  8. A neural network driving curve generation method for the heavy-haul train

    Directory of Open Access Journals (Sweden)

    Youneng Huang

    2016-05-01

    Full Text Available The heavy-haul train has a series of characteristics, such as the locomotive traction properties, the longer length of train, and the nonlinear train pipe pressure during train braking. When the train is running on a continuous long and steep downgrade railway line, the safety of the train is ensured by cycle braking, which puts high demands on the driving skills of the driver. In this article, a driving curve generation method for the heavy-haul train based on a neural network is proposed. First, in order to describe the nonlinear characteristics of train braking, the neural network model is constructed and trained by practical driving data. In the neural network model, various nonlinear neurons are interconnected to work for information processing and transmission. The target value of train braking pressure reduction and release time is achieved by modeling the braking process. The equation of train motion is computed to obtain the driving curve. Finally, in four typical operation scenarios, comparing the curve data generated by the method with corresponding practical data of the Shuohuang heavy-haul railway line, the results show that the method is effective.

  9. C-RNN-GAN: Continuous recurrent neural networks with adversarial training

    OpenAIRE

    Mogren, Olof

    2016-01-01

    Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and let the reader judge the quality by downloading the generated songs.

  10. Cognitive flexibility modulates maturation and music-training-related changes in neural sound discrimination.

    Science.gov (United States)

    Saarikivi, Katri; Putkinen, Vesa; Tervaniemi, Mari; Huotilainen, Minna

    2016-07-01

    Previous research has demonstrated that musicians show superior neural sound discrimination when compared to non-musicians, and that these changes emerge with accumulation of training. Our aim was to investigate whether individual differences in executive functions predict training-related changes in neural sound discrimination. We measured event-related potentials induced by sound changes coupled with tests for executive functions in musically trained and non-trained children aged 9-11 years and 13-15 years. High performance in a set-shifting task, indexing cognitive flexibility, was linked to enhanced maturation of neural sound discrimination in both musically trained and non-trained children. Specifically, well-performing musically trained children already showed large mismatch negativity (MMN) responses at a young age as well as at an older age, indicating accurate sound discrimination. In contrast, the musically trained low-performing children still showed an increase in MMN amplitude with age, suggesting that they were behind their high-performing peers in the development of sound discrimination. In the non-trained group, in turn, only the high-performing children showed evidence of an age-related increase in MMN amplitude, and the low-performing children showed a small MMN with no age-related change. These latter results suggest an advantage in MMN development also for high-performing non-trained individuals. For the P3a amplitude, there was an age-related increase only in the children who performed well in the set-shifting task, irrespective of music training, indicating enhanced attention-related processes in these children. Thus, the current study provides the first evidence that, in children, cognitive flexibility may influence age-related and training-related plasticity of neural sound discrimination. © 2016 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

  11. Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

    OpenAIRE

    Tajbakhsh, Nima; Shin, Jae Y.; Gurudu, Suryakanth R.; Hurst, R. Todd; Kendall, Christopher B.; Gotway, Michael B.; Liang, Jianming

    2017-01-01

    Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following centr...

  12. Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

    International Nuclear Information System (INIS)

    Zemouri, Ryad; Racoceanu, Daniel; Zerhouni, Noureddine; Minca, Eugenia; Filip, Florin

    2009-01-01

    In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

  13. IAEA Technical Co-operation activities: Asia and the Pacific. Workshop on training nuclear laboratory technicians

    International Nuclear Information System (INIS)

    Roeed, S.S.

    1976-01-01

    The workshop was held to exchange information on existing facilities and programmes in Asia and the Pacific for training nuclear laboratory technicians, to identify future training needs and to assess the need for IAEA's involvement in this field. As the participants outlined the requirements for nuclear laboratory technician training and the facilities available in their respective countries, it became evident that, in addition to the training of radioisotope laboratory technicians, they also wished to review the need for technician training for the operation of nuclear power plants and industrial application of atomic energy. The terms of reference of the workshop were extended accordingly. The opening address by Chang Suk Lee, the Korean Vice Minister of Science and Technology, noted the valuable contribution to quality control and other industrial uses that nuclear techniques have made in his country. He also reviewed the application of nuclear techniques in Korean agriculture and medicine. The participants explored various forms of co-operation that could be established between countries of the region. Exchange programmes, not only for students but also for expert teachers, and the exchange or loan of equipment were suggested. It was felt that some generalized training courses could be organized on a regional basis, and two countries advocated the setting up of a regional training centre. One suggestion was to arrange regional training courses in special fields that would move from one country to another. The need was felt for periodic regional meetings on training methods, course content and other questions relating to training of laboratory technicians. The IAEA was requested to act as a clearinghouse for information on available training facilities in the region and to advise on the curricula for technician training courses. The Agency was also asked to organize short courses for the training of instructors of technicians in the various fields of atomic

  14. A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing

    Directory of Open Access Journals (Sweden)

    Yi-Qing Wang

    2015-09-01

    Full Text Available Recent years have seen a surge of interest in multilayer neural networks fueled by their successful applications in numerous image processing and computer vision tasks. In this article, we describe a C++ implementation of the stochastic gradient descent to train a multilayer neural network, where a fast and accurate acceleration of tanh(· is achieved with linear interpolation. As an example of application, we present a neural network able to deliver state-of-the-art performance in image demosaicing.

  15. 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.

  16. Reward-based training of recurrent neural networks for cognitive and value-based tasks.

    Science.gov (United States)

    Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing

    2017-01-13

    Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal's internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task.

  17. Potential Cost Savings and Cost Avoidances Associated With Security Cooperation Training Programs

    Science.gov (United States)

    2015-12-01

    difficult to establish a risk premium to include into the military pricing strategy that would adequately capture the risk the contractor assumed...significant difference between the contractor and government pricing strategy is in the handling of the hazardous duty risk premium . U.S. military...Cooperation Agency. Using the Department of Defense’s Financial Management Regulation, I priced the contractor provided training as if uniformed

  18. Development and Operation of International Nuclear Education/Training Program and HRD Cooperation Network

    International Nuclear Information System (INIS)

    Lee, E. J.; Min, B. J.; Han, K. W.

    2006-12-01

    The primary result of the project is the establishment of a concept of International Nuclear R and D Academy that integrates the on-going long term activity for international nuclear education/training and a new activity to establish an international cooperation network for nuclear human resources development. For this, the 2007 WNU Summer Institute was hosted with the establishment of an MOU and subsequent preparations. Also, ANENT was promoted through development of a cyber platform for the ANENT web-portal, hosting the third ANENT Coordination Committee meeting, etc. Then a cooperation with universities in Vietnam was launched resulting in preparation of an MOU for the cooperation. Finally, a relevant system framework was established and required procedures were drafted especially for providing students from developing countries with long term education/training programs (e.g. MS and Ph D. courses). The international nuclear education/training programs have offered 13 courses to 182 people from 43 countries. The overall performance of the courses was evaluated to be outstanding. In parallel, the establishment of an MOU for the cooperation of KOICA-IAEA-KAERI courses to ensure their stable and systematic operation. Also, an effort was made to participate in FNCA. Atopia Hall of the International Nuclear Training and Education Center (INTEC) hosted 477 events (corresponding to 18,521 participants) and Nuri Hall (guesthouse) accommodated 4,616 people in 2006. This shows a steady increase of the use rate since the opening of the center, along with a continuous improvement of the equipment

  19. Development and Operation of International Nuclear Education/Training Program and HRD Cooperation Network

    Energy Technology Data Exchange (ETDEWEB)

    Lee, E J; Min, B J; Han, K W [and others

    2006-12-15

    The primary result of the project is the establishment of a concept of International Nuclear R and D Academy that integrates the on-going long term activity for international nuclear education/training and a new activity to establish an international cooperation network for nuclear human resources development. For this, the 2007 WNU Summer Institute was hosted with the establishment of an MOU and subsequent preparations. Also, ANENT was promoted through development of a cyber platform for the ANENT web-portal, hosting the third ANENT Coordination Committee meeting, etc. Then a cooperation with universities in Vietnam was launched resulting in preparation of an MOU for the cooperation. Finally, a relevant system framework was established and required procedures were drafted especially for providing students from developing countries with long term education/training programs (e.g. MS and Ph D. courses). The international nuclear education/training programs have offered 13 courses to 182 people from 43 countries. The overall performance of the courses was evaluated to be outstanding. In parallel, the establishment of an MOU for the cooperation of KOICA-IAEA-KAERI courses to ensure their stable and systematic operation. Also, an effort was made to participate in FNCA. Atopia Hall of the International Nuclear Training and Education Center (INTEC) hosted 477 events (corresponding to 18,521 participants) and Nuri Hall (guesthouse) accommodated 4,616 people in 2006. This shows a steady increase of the use rate since the opening of the center, along with a continuous improvement of the equipment.

  20. Training Convolutional Neural Networks for Translational Invariance on SAR ATR

    DEFF Research Database (Denmark)

    Malmgren-Hansen, David; Engholm, Rasmus; Østergaard Pedersen, Morten

    2016-01-01

    In this paper we present a comparison of the robustness of Convolutional Neural Networks (CNN) to other classifiers in the presence of uncertainty of the objects localization in SAR image. We present a framework for simulating simple SAR images, translating the object of interest systematically...

  1. Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

    Science.gov (United States)

    Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

    1990-01-01

    Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

  2. NIRS-Based Hyperscanning Reveals Inter-brain Neural Synchronization during Cooperative Jenga Game with Face-to-Face Communication.

    Science.gov (United States)

    Liu, Ning; Mok, Charis; Witt, Emily E; Pradhan, Anjali H; Chen, Jingyuan E; Reiss, Allan L

    2016-01-01

    Functional near-infrared spectroscopy (fNIRS) is an increasingly popular technology for studying social cognition. In particular, fNIRS permits simultaneous measurement of hemodynamic activity in two or more individuals interacting in a naturalistic setting. Here, we used fNIRS hyperscanning to study social cognition and communication in human dyads engaged in cooperative and obstructive interaction while they played the game of Jenga™. Novel methods were developed to identify synchronized channels for each dyad and a structural node-based spatial registration approach was utilized for inter-dyad analyses. Strong inter-brain neural synchrony (INS) was observed in the posterior region of the right middle and superior frontal gyrus, in particular Brodmann area 8 (BA8), during cooperative and obstructive interaction. This synchrony was not observed during the parallel game play condition and the dialog section, suggesting that BA8 was involved in goal-oriented social interaction such as complex interactive movements and social decision-making. INS was also observed in the dorsomedial prefrontal cortex (dmPFC), in particular Brodmann 9, during cooperative interaction only. These additional findings suggest that BA9 may be particularly engaged when theory-of-mind (ToM) is required for cooperative social interaction. The new methods described here have the potential to significantly extend fNIRS applications to social cognitive research.

  3. Pap-smear Classification Using Efficient Second Order Neural Network Training Algorithms

    DEFF Research Database (Denmark)

    Ampazis, Nikolaos; Dounias, George; Jantzen, Jan

    2004-01-01

    In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier. The alg......In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier...

  4. The CRC Contribution to Research Training: Report of a Scoping Study for the Cooperative Research Centres Association

    Science.gov (United States)

    Palmer, Nigel

    2012-01-01

    This report summarises findings from a scoping study conducted for the Cooperative Research Centres Association (CRCA) by the Centre for the Study of Higher Education. The purpose of the scoping study is to inform the research training activities of Cooperative Research Centres (CRCs). While previous studies have focussed on the outcomes supported…

  5. Neural Plasticity following Abacus Training in Humans: A Review and Future Directions

    Directory of Open Access Journals (Sweden)

    Yongxin Li

    2016-01-01

    Full Text Available The human brain has an enormous capacity to adapt to a broad variety of environmental demands. Previous studies in the field of abacus training have shown that this training can induce specific changes in the brain. However, the neural mechanism underlying these changes remains elusive. Here, we reviewed the behavioral and imaging findings of comparisons between abacus experts and average control subjects and focused on changes in activation patterns and changes in brain structure. Finally, we noted the limitations and the future directions of this field. We concluded that although current studies have provided us with information about the mechanisms of abacus training, more research on abacus training is needed to understand its neural impact.

  6. Oxytocin and vasopressin effects on the neural response to social cooperation are modulated by sex in humans.

    Science.gov (United States)

    Feng, Chunliang; Hackett, Patrick D; DeMarco, Ashley C; Chen, Xu; Stair, Sabrina; Haroon, Ebrahim; Ditzen, Beate; Pagnoni, Giuseppe; Rilling, James K

    2015-12-01

    Recent research has examined the effects of oxytocin (OT) and vasopressin (AVP) on human social behavior and brain function. However, most participants have been male, while previous research in our lab demonstrated sexually differentiated effects of OT and AVP on the neural response to reciprocated cooperation. Here we extend our previous work by significantly increasing the number of participants to enable the use of more stringent statistical thresholds that permit more precise localization of OT and AVP effects in the brain. In a double-blind, placebo-controlled study, 153 men and 151 women were randomized to receive 24 IU intranasal OT, 20 IU intranasal AVP or placebo. Afterwards, they were imaged with fMRI while playing an iterated Prisoner's Dilemma Game with same-sex partners. Sex differences were observed for effects of OT on the neural response to reciprocated cooperation, such that OT increased the caduate/putamen response among males, whereas it decreased this response among females. Thus, 24 IU OT may increase the reward or salience of positive social interactions among men, while decreasing their reward or salience among women. Similar sex differences were also observed for AVP effects within bilateral insula and right supramarginal gyrus when a more liberal statistical threshold was employed. While our findings support previous suggestions that exogenous nonapeptides may be effective treatments for disorders such as depression and autism spectrum disorder, they caution against uniformly extending such treatments to men and women alike.

  7. A common oxytocin receptor gene (OXTR) polymorphism modulates intranasal oxytocin effects on the neural response to social cooperation in humans.

    Science.gov (United States)

    Feng, C; Lori, A; Waldman, I D; Binder, E B; Haroon, E; Rilling, J K

    2015-09-01

    Intranasal oxytocin (OT) can modulate social-emotional functioning and related brain activity in humans. Consequently, OT has been discussed as a potential treatment for psychiatric disorders involving social behavioral deficits. However, OT effects are often heterogeneous across individuals. Here we explore individual differences in OT effects on the neural response to social cooperation as a function of the rs53576 polymorphism of the oxytocin receptor gene (OXTR). Previously, we conducted a double-blind, placebo-controlled study in which healthy men and women were randomized to treatment with intranasal OT or placebo. Afterwards, they were imaged with functional magnetic resonance imaging while playing an iterated Prisoner's Dilemma Game with same-sex partners. Within the left ventral caudate nucleus, intranasal OT treatment increased activation to reciprocated cooperation in men, but tended to decrease activation in women. Here, we show that these sex differences in OT effects are specific to individuals with the rs53576 GG genotype, and are not found for other genotypes (rs53576 AA/AG). Thus, OT may increase the reward or salience of positive social interactions for male GG homozygotes, while decreasing those processes for female GG homozygotes. These results suggest that rs53576 genotype is an important variable to consider in future investigations of the clinical efficacy of intranasal OT treatment. © 2015 John Wiley & Sons Ltd and International Behavioural and Neural Genetics Society.

  8. Gradual DropIn of Layers to Train Very Deep Neural Networks

    OpenAIRE

    Smith, Leslie N.; Hand, Emily M.; Doster, Timothy

    2015-01-01

    We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow network and newly added layers are slowly, organically added during training, thereby increasing the network's depth. This is accomplished by a new layer, which we call DropIn. The DropIn layer starts by passing the output from a previous layer (effectively skipping over the newly added layers), then increasingly including units from the ne...

  9. Non-Linear State Estimation Using Pre-Trained Neural Networks

    DEFF Research Database (Denmark)

    Bayramoglu, Enis; Andersen, Nils Axel; Ravn, Ole

    2010-01-01

    effecting the transformation. This function is approximated by a neural network using offline training. The training is based on monte carlo sampling. A way to obtain parametric distributions of flexible shape to be used easily with these networks is also presented. The method can also be used to improve...... other parametric methods around regions with strong non-linearities by including them inside the network....

  10. Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

    OpenAIRE

    Hwang, Kyuyeon; Sung, Wonyong

    2015-01-01

    Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including end-to-end speech and handwritten character recognition. For the CTC training, however, it is required to unroll (or unfold) the RNN by the length of an input sequence. This unrolling requires a lot of memory and hinders a small footprint implementation of online learning or adaptation. Furthermore, the length of tr...

  11. Short-term Music Training Enhances Complex, Distributed Neural Communication during Music and Linguistic Tasks.

    Science.gov (United States)

    Carpentier, Sarah M; Moreno, Sylvain; McIntosh, Anthony R

    2016-10-01

    Musical training is frequently associated with benefits to linguistic abilities, and recent focus has been placed on possible benefits of bilingualism to lifelong executive functions; however, the neural mechanisms for such effects are unclear. The aim of this study was to gain better understanding of the whole-brain functional effects of music and second-language training that could support such previously observed cognitive transfer effects. We conducted a 28-day longitudinal study of monolingual English-speaking 4- to 6-year-old children randomly selected to receive daily music or French language training, excluding weekends. Children completed passive EEG music note and French vowel auditory oddball detection tasks before and after training. Brain signal complexity was measured on source waveforms at multiple temporal scales as an index of neural information processing and network communication load. Comparing pretraining with posttraining, musical training was associated with increased EEG complexity at coarse temporal scales during the music and French vowel tasks in widely distributed cortical regions. Conversely, very minimal decreases in complexity at fine scales and trends toward coarse-scale increases were displayed after French training during the tasks. Spectral analysis failed to distinguish between training types and found overall theta (3.5-7.5 Hz) power increases after all training forms, with spatially fewer decreases in power at higher frequencies (>10 Hz). These findings demonstrate that musical training increased diversity of brain network states to support domain-specific music skill acquisition and music-to-language transfer effects.

  12. Diagnostics of Nuclear Reactor Accidents Based on Particle Swarm Optimization Trained Neural Networks

    International Nuclear Information System (INIS)

    Abdel-Aal, M.M.Z.

    2004-01-01

    Automation in large, complex systems such as chemical plants, electrical power generation, aerospace and nuclear plants has been steadily increasing in the recent past. automated diagnosis and control forms a necessary part of these systems,this contains thousands of alarms processing in every component, subsystem and system. so the accurate and speed of diagnosis of faults is an important factors in operation and maintaining their health and continued operation and in reducing of repair and recovery time. using of artificial intelligence facilitates the alarm classifications and faults diagnosis to control any abnormal events during the operation cycle of the plant. thesis work uses the artificial neural network as a powerful classification tool. the work basically is has two components, the first is to effectively train the neural network using particle swarm optimization, which non-derivative based technique. to achieve proper training of the neural network to fault classification problem and comparing this technique to already existing techniques

  13. PARTICLE SWARM OPTIMIZATION (PSO FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN

    Directory of Open Access Journals (Sweden)

    Arie Rachmad Syulistyo

    2016-02-01

    Full Text Available Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO in Convolutional Neural Networks (CNNs, which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN.  The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.

  14. Musical Training during Early Childhood Enhances the Neural Encoding of Speech in Noise

    Science.gov (United States)

    Strait, Dana L.; Parbery-Clark, Alexandra; Hittner, Emily; Kraus, Nina

    2012-01-01

    For children, learning often occurs in the presence of background noise. As such, there is growing desire to improve a child's access to a target signal in noise. Given adult musicians' perceptual and neural speech-in-noise enhancements, we asked whether similar effects are present in musically-trained children. We assessed the perception and…

  15. Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback.

    Science.gov (United States)

    Orhan, A Emin; Ma, Wei Ji

    2017-07-26

    Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task specific operations.

  16. Internal measuring models in trained neural networks for parameter estimation from images

    NARCIS (Netherlands)

    Feng, Tian-Jin; Feng, T.J.; Houkes, Z.; Korsten, Maarten J.; Spreeuwers, Lieuwe Jan

    1992-01-01

    The internal representations of 'learned' knowledge in neural networks are still poorly understood, even for backpropagation networks. The paper discusses a possible interpretation of learned knowledge of a network trained for parameter estimation from images. The outputs of the hidden layer are the

  17. Internal-state analysis in layered artificial neural network trained to categorize lung sounds

    NARCIS (Netherlands)

    Oud, M

    2002-01-01

    In regular use of artificial neural networks, only input and output states of the network are known to the user. Weight and bias values can be extracted but are difficult to interpret. We analyzed internal states of networks trained to map asthmatic lung sound spectra onto lung function parameters.

  18. Neural activity during emotion recognition after combined cognitive plus social cognitive training in schizophrenia.

    Science.gov (United States)

    Hooker, Christine I; Bruce, Lori; Fisher, Melissa; Verosky, Sara C; Miyakawa, Asako; Vinogradov, Sophia

    2012-08-01

    Cognitive remediation training has been shown to improve both cognitive and social cognitive deficits in people with schizophrenia, but the mechanisms that support this behavioral improvement are largely unknown. One hypothesis is that intensive behavioral training in cognition and/or social cognition restores the underlying neural mechanisms that support targeted skills. However, there is little research on the neural effects of cognitive remediation training. This study investigated whether a 50 h (10-week) remediation intervention which included both cognitive and social cognitive training would influence neural function in regions that support social cognition. Twenty-two stable, outpatient schizophrenia participants were randomized to a treatment condition consisting of auditory-based cognitive training (AT) [Brain Fitness Program/auditory module ~60 min/day] plus social cognition training (SCT) which was focused on emotion recognition [~5-15 min per day] or a placebo condition of non-specific computer games (CG) for an equal amount of time. Pre and post intervention assessments included an fMRI task of positive and negative facial emotion recognition, and standard behavioral assessments of cognition, emotion processing, and functional outcome. There were no significant intervention-related improvements in general cognition or functional outcome. fMRI results showed the predicted group-by-time interaction. Specifically, in comparison to CG, AT+SCT participants had a greater pre-to-post intervention increase in postcentral gyrus activity during emotion recognition of both positive and negative emotions. Furthermore, among all participants, the increase in postcentral gyrus activity predicted behavioral improvement on a standardized test of emotion processing (MSCEIT: Perceiving Emotions). Results indicate that combined cognition and social cognition training impacts neural mechanisms that support social cognition skills. Copyright © 2012 Elsevier B.V. All

  19. Neural activity during emotion recognition after combined cognitive plus social-cognitive training in schizophrenia

    Science.gov (United States)

    Hooker, Christine I.; Bruce, Lori; Fisher, Melissa; Verosky, Sara C.; Miyakawa, Asako; Vinogradov, Sophia

    2012-01-01

    Cognitive remediation training has been shown to improve both cognitive and social-cognitive deficits in people with schizophrenia, but the mechanisms that support this behavioral improvement are largely unknown. One hypothesis is that intensive behavioral training in cognition and/or social-cognition restores the underlying neural mechanisms that support targeted skills. However, there is little research on the neural effects of cognitive remediation training. This study investigated whether a 50 hour (10-week) remediation intervention which included both cognitive and social-cognitive training would influence neural function in regions that support social-cognition. Twenty-two stable, outpatient schizophrenia participants were randomized to a treatment condition consisting of auditory-based cognitive training (AT) [Brain Fitness Program/auditory module ~60 minutes/day] plus social-cognition training (SCT) which was focused on emotion recognition [~5–15 minutes per day] or a placebo condition of non-specific computer games (CG) for an equal amount of time. Pre and post intervention assessments included an fMRI task of positive and negative facial emotion recognition, and standard behavioral assessments of cognition, emotion processing, and functional outcome. There were no significant intervention-related improvements in general cognition or functional outcome. FMRI results showed the predicted group-by-time interaction. Specifically, in comparison to CG, AT+SCT participants had a greater pre-to-post intervention increase in postcentral gyrus activity during emotion recognition of both positive and negative emotions. Furthermore, among all participants, the increase in postcentral gyrus activity predicted behavioral improvement on a standardized test of emotion processing (MSCEIT: Perceiving Emotions). Results indicate that combined cognition and social-cognition training impacts neural mechanisms that support social-cognition skills. PMID:22695257

  20. Cycle Training Using Implanted Neural Prostheses: Team Cleveland.

    Science.gov (United States)

    McDaniel, John; Lombardo, Lisa M; Foglyano, Kevin M; Marasco, Paul D; J Triolo, Ronald

    2017-12-05

    Recently our laboratory team focused on training five individuals with complete spinal cord injuries for an overground FES bike race in the 2016 Cybathlon held in Zurich Switzerland. A unique advantage team Cleveland had over other teams was the use of implanted pulse generators that provide more selective activation of muscles compared to standard surface stimulation. The advancements in muscle strength and endurance and ultimately cycling power our pilots made during this training period helped propel our competing pilot to win gold at the Cybathlon and allowed our pilots to ride their bikes outside within their communities. Such positive outcomes has encouraged us to further explore more widespread use of FES overground cycling as a rehabilitative tool for those with spinal cord injuries. This review will describes our approach to this race including information on the pilots, stimulation strategy, bike details and training program.

  1. Cycle Training Using Implanted Neural Prostheses: Team Cleveland

    Directory of Open Access Journals (Sweden)

    John McDaniel

    2017-12-01

    Full Text Available Recently our laboratory team focused on training five individuals with complete spinal cord injuries for an overground FES bike race in the 2016 Cybathlon held in Zurich Switzerland. A unique advantage team Cleveland had over other teams was the use of implanted pulse generators that provide more selective activation of muscles compared to standard surface stimulation. The advancements in muscle strength and endurance and ultimately cycling power our pilots made during this training period helped propel our competing pilot to win gold at the Cybathlon and allowed our pilots to ride their bikes outside within their communities. Such positive outcomes has encouraged us to further explore more widespread use of FES overground cycling as a rehabilitative tool for those with spinal cord injuries. This review will describes our approach to this race including information on the pilots, stimulation strategy, bike details and training program.

  2. Neuro-Fuzzy Prediction of Cooperation Interaction Profile of Flexible Road Train Based on Hybrid Automaton Modeling

    Directory of Open Access Journals (Sweden)

    Banjanovic-Mehmedovic Lejla

    2016-01-01

    Full Text Available Accurate prediction of traffic information is important in many applications in relation to Intelligent Transport systems (ITS, since it reduces the uncertainty of future traffic states and improves traffic mobility. There is a lot of research done in the field of traffic information predictions such as speed, flow and travel time. The most important research was done in the domain of cooperative intelligent transport system (C-ITS. The goal of this paper is to introduce the novel cooperation behaviour profile prediction through the example of flexible Road Trains useful road cooperation parameter, which contributes to the improvement of traffic mobility in Intelligent Transportation Systems. This paper presents an approach towards the control and cooperation behaviour modelling of vehicles in the flexible Road Train based on hybrid automaton and neuro-fuzzy (ANFIS prediction of cooperation profile of the flexible Road Train. Hybrid automaton takes into account complex dynamics of each vehicle as well as discrete cooperation approach. The ANFIS is a particular class of the ANN family with attractive estimation and learning potentials. In order to provide statistical analysis, RMSE (root mean square error, coefficient of determination (R2 and Pearson coefficient (r, were utilized. The study results suggest that ANFIS would be an efficient soft computing methodology, which could offer precise predictions of cooperative interactions between vehicles in Road Train, which is useful for prediction mobility in Intelligent Transport systems.

  3. Cooperative learning in third graders' jigsaw groups for mathematics and science with and without questioning training.

    Science.gov (United States)

    Souvignier, Elmar; Kronenberger, Julia

    2007-12-01

    There is much support for using cooperative methods, since important instructional aspects, such as elaboration of new information, can easily be realized by methods like 'jigsaw'. However, the impact of providing students with additional help like a questioning training and potential limitations of the method concerning the (minimum) age of the students have rarely been investigated. The study investigated the effects of cooperative methods at elementary school level. Three conditions of instruction were compared: jigsaw, jigsaw with a supplementary questioning training and teacher-guided instruction. Nine third grade classes from three schools with 208 students participated in the study. In each school, all the three instructional conditions were realized in three different classes. All classes studied three units on geometry and one unit on astronomy using the assigned instructional method. Each learning unit comprised six lessons. For each unit, an achievement test was administered as pre-test, post-test and delayed test. In the math units, no differences between the three conditions could be detected. In the astronomy unit, students benefited more from teacher-guided instruction. Differential analyses revealed that 'experts' learned more than students in teacher-guided instruction, whereas 'novices' were outperformed by the students in the control classes. Even third graders used the jigsaw method with satisfactory learning results. The modest impact of the questioning training and the low learning gains of the cooperative classes in the astronomy unit as well as high discrepancies between learning outcomes of experts and novices show that explicit instruction of explaining skills in combination with well-structured material are key issues in using the jigsaw method with younger students.

  4. Effect of training algorithms on neural networks aided pavement ...

    African Journals Online (AJOL)

    Especially, the use of Finite Element (FE) based pavement modeling results for training the NN aided inverse analysis is considered to be accurate in realistically characterizing the non-linear stress-sensitive response of underlying pavement layers in real-time. Efficient NN learning algorithms have been developed and ...

  5. Imaging the neural effects of cognitive bias modification training

    NARCIS (Netherlands)

    Wiers, C.E.; Wiers, R.W.

    Cognitive bias modification (CBM) was first developed as an experimental tool to examine the causal role of cognitive biases, and later developed into complementary interventions in experimental psychopathology research. CBM involves the "re-training" of implicit biases by means of multiple trials

  6. Planning music-based amelioration and training in infancy and childhood based on neural evidence.

    Science.gov (United States)

    Huotilainen, Minna; Tervaniemi, Mari

    2018-05-04

    Music-based amelioration and training of the developing auditory system has a long tradition, and recent neuroscientific evidence supports using music in this manner. Here, we present the available evidence showing that various music-related activities result in positive changes in brain structure and function, becoming helpful for auditory cognitive processes in everyday life situations for individuals with typical neural development and especially for individuals with hearing, learning, attention, or other deficits that may compromise auditory processing. We also compare different types of music-based training and show how their effects have been investigated with neural methods. Finally, we take a critical position on the multitude of error sources found in amelioration and training studies and on publication bias in the field. We discuss some future improvements of these issues in the field of music-based training and their potential results at the neural and behavioral levels in infants and children for the advancement of the field and for a more complete understanding of the possibilities and significance of the training. © 2018 The Authors. Annals of the New York Academy of Sciences published by Wiley Periodicals, Inc. on behalf of New York Academy of Sciences.

  7. Physiological and Neural Adaptations to Eccentric Exercise: Mechanisms and Considerations for Training

    Directory of Open Access Journals (Sweden)

    Nosratollah Hedayatpour

    2015-01-01

    Full Text Available Eccentric exercise is characterized by initial unfavorable effects such as subcellular muscle damage, pain, reduced fiber excitability, and initial muscle weakness. However, stretch combined with overload, as in eccentric contractions, is an effective stimulus for inducing physiological and neural adaptations to training. Eccentric exercise-induced adaptations include muscle hypertrophy, increased cortical activity, and changes in motor unit behavior, all of which contribute to improved muscle function. In this brief review, neuromuscular adaptations to different forms of exercise are reviewed, the positive training effects of eccentric exercise are presented, and the implications for training are considered.

  8. Pap-smear Classification Using Efficient Second Order Neural Network Training Algorithms

    DEFF Research Database (Denmark)

    Ampazis, Nikolaos; Dounias, George; Jantzen, Jan

    2004-01-01

    In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier. The alg......In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier....... The algorithms are methodologically similar, and are based on iterations of the form employed in the Levenberg-Marquardt (LM) method for non-linear least squares problems with the inclusion of an additional adaptive momentum term arising from the formulation of the training task as a constrained optimization...

  9. Statistical and optimization methods to expedite neural network training for transient identification

    International Nuclear Information System (INIS)

    Reifman, J.; Vitela, E.J.; Lee, J.C.

    1993-01-01

    Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network

  10. Cooperation in education and training in nuclear- and radiochemistry in Europe

    International Nuclear Information System (INIS)

    Jan John; Jukka Lehto; Teija Koivula; Jon Petter Omtvedt

    2015-01-01

    The motivation, history and status of coordination of education and training in nuclear- and radiochemistry in Europe are reviewed. The achievements of the Euratom FP7 project 'Cooperation In education in Nuclear CHemistry (CINCH)' are described. Attention is paid to the results of the survey of universities teaching nuclear chemistry and their respective curricula evaluation, to the plan to introduce the EuroMaster in nuclear- and radiochemistry quality label recognized and guaranteed by the European Association for Chemical and Molecular Sciences (EuCheMS), and to CINCH NucWik - an interactive database proposed and implemented as an open structure in the form of a 'Wiki'. (author)

  11. On the use of harmony search algorithm in the training of wavelet neural networks

    Science.gov (United States)

    Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

    2015-10-01

    Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.

  12. A biologically inspired neural model for visual and proprioceptive integration including sensory training.

    Science.gov (United States)

    Saidi, Maryam; Towhidkhah, Farzad; Gharibzadeh, Shahriar; Lari, Abdolaziz Azizi

    2013-12-01

    Humans perceive the surrounding world by integration of information through different sensory modalities. Earlier models of multisensory integration rely mainly on traditional Bayesian and causal Bayesian inferences for single causal (source) and two causal (for two senses such as visual and auditory systems), respectively. In this paper a new recurrent neural model is presented for integration of visual and proprioceptive information. This model is based on population coding which is able to mimic multisensory integration of neural centers in the human brain. The simulation results agree with those achieved by casual Bayesian inference. The model can also simulate the sensory training process of visual and proprioceptive information in human. Training process in multisensory integration is a point with less attention in the literature before. The effect of proprioceptive training on multisensory perception was investigated through a set of experiments in our previous study. The current study, evaluates the effect of both modalities, i.e., visual and proprioceptive training and compares them with each other through a set of new experiments. In these experiments, the subject was asked to move his/her hand in a circle and estimate its position. The experiments were performed on eight subjects with proprioception training and eight subjects with visual training. Results of the experiments show three important points: (1) visual learning rate is significantly more than that of proprioception; (2) means of visual and proprioceptive errors are decreased by training but statistical analysis shows that this decrement is significant for proprioceptive error and non-significant for visual error, and (3) visual errors in training phase even in the beginning of it, is much less than errors of the main test stage because in the main test, the subject has to focus on two senses. The results of the experiments in this paper is in agreement with the results of the neural model

  13. Neural Spike Train Synchronisation Indices: Definitions, Interpretations and Applications.

    Science.gov (United States)

    Halliday, D M; Rosenberg, J R

    2017-04-24

    A comparison of previously defined spike train syncrhonization indices is undertaken within a stochastic point process framework. The second order cumulant density (covariance density) is shown to be common to all the indices. Simulation studies were used to investigate the sampling variability of a single index based on the second order cumulant. The simulations used a paired motoneurone model and a paired regular spiking cortical neurone model. The sampling variability of spike trains generated under identical conditions from the paired motoneurone model varied from 50% { 160% of the estimated value. On theoretical grounds, and on the basis of simulated data a rate dependence is present in all synchronization indices. The application of coherence and pooled coherence estimates to the issue of synchronization indices is considered. This alternative frequency domain approach allows an arbitrary number of spike train pairs to be evaluated for statistically significant differences, and combined into a single population measure. The pooled coherence framework allows pooled time domain measures to be derived, application of this to the simulated data is illustrated. Data from the cortical neurone model is generated over a wide range of firing rates (1 - 250 spikes/sec). The pooled coherence framework correctly characterizes the sampling variability as not significant over this wide operating range. The broader applicability of this approach to multi electrode array data is briefly discussed.

  14. Military Training and Education: an Opportunity for V4 Co-Operation

    Directory of Open Access Journals (Sweden)

    Milan ŠUPLATA

    2015-03-01

    Full Text Available The Visegrad Group needs success stories if its defence co-operation is to develop. The recent differences between Poland and the rest of the region, as well as the closing window of opportunity to improve interoperability through the ISAF mission, make the hunger for concrete examples of co-operation even more urgent. Education and training projects are not only comparatively easily to implement in terms of time and money, but also represent a way of bringing the region’s civilian and military leaders closer together in terms of strategic thinking. Regional defence collaboration is also one of the ways to materialize NATO’s Smart Defence agenda. For the whole region, the way to keep Visegrad defence cooperation alive is not straightforward and certain, but it is likely to prove rewarding in the long term. It presents not only a chance to keep the whole region better prepared militarily, but also to build a more cohesive strategic awareness, thanks to intensive communication at all levels.

  15. Parametric models to relate spike train and LFP dynamics with neural information processing.

    Science.gov (United States)

    Banerjee, Arpan; Dean, Heather L; Pesaran, Bijan

    2012-01-01

    Spike trains and local field potentials (LFPs) resulting from extracellular current flows provide a substrate for neural information processing. Understanding the neural code from simultaneous spike-field recordings and subsequent decoding of information processing events will have widespread applications. One way to demonstrate an understanding of the neural code, with particular advantages for the development of applications, is to formulate a parametric statistical model of neural activity and its covariates. Here, we propose a set of parametric spike-field models (unified models) that can be used with existing decoding algorithms to reveal the timing of task or stimulus specific processing. Our proposed unified modeling framework captures the effects of two important features of information processing: time-varying stimulus-driven inputs and ongoing background activity that occurs even in the absence of environmental inputs. We have applied this framework for decoding neural latencies in simulated and experimentally recorded spike-field sessions obtained from the lateral intraparietal area (LIP) of awake, behaving monkeys performing cued look-and-reach movements to spatial targets. Using both simulated and experimental data, we find that estimates of trial-by-trial parameters are not significantly affected by the presence of ongoing background activity. However, including background activity in the unified model improves goodness of fit for predicting individual spiking events. Uncovering the relationship between the model parameters and the timing of movements offers new ways to test hypotheses about the relationship between neural activity and behavior. We obtained significant spike-field onset time correlations from single trials using a previously published data set where significantly strong correlation was only obtained through trial averaging. We also found that unified models extracted a stronger relationship between neural response latency and trial

  16. The Evaluation on Data Mining Methods of Horizontal Bar Training Based on BP Neural Network

    Directory of Open Access Journals (Sweden)

    Zhang Yanhui

    2015-01-01

    Full Text Available With the rapid development of science and technology, data analysis has become an indispensable part of people’s work and life. Horizontal bar training has multiple categories. It is an emphasis for the re-search of related workers that categories of the training and match should be reduced. The application of data mining methods is discussed based on the problem of reducing categories of horizontal bar training. The BP neural network is applied to the cluster analysis and the principal component analysis, which are used to evaluate horizontal bar training. Two kinds of data mining methods are analyzed from two aspects, namely the operational convenience of data mining and the rationality of results. It turns out that the principal component analysis is more suitable for data processing of horizontal bar training.

  17. SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method.

    Science.gov (United States)

    Bernal, Javier; Torres-Jimenez, Jose

    2015-01-01

    SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller's scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller's algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller's algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller's algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data.

  18. Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework.

    Directory of Open Access Journals (Sweden)

    H Francis Song

    2016-02-01

    Full Text Available The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, "trained" networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale's principle, which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural

  19. Training verb argument structure production in agrammatic aphasia: Behavioral and neural recovery patterns

    Science.gov (United States)

    Thompson, Cynthia K.; Riley, Ellyn A.; den Ouden, Dirk-Bart; Meltzer-Asscher, Aya; Lukic, Sladjana

    2013-01-01

    Introduction Neuroimaging and lesion studies indicate a left hemisphere network for verb and verb argument structure processing, involving both frontal and temporoparietal brain regions. Although their verb comprehension is generally unimpaired, it is well known that individuals with agrammatic aphasia often present with verb production deficits, characterized by an argument structure complexity hierarchy, indicating faulty access to argument structure representations for production and integration into syntactic contexts. Recovery of verb processing in agrammatism, however, has received little attention and no studies have examined the neural mechanisms associated with improved verb and argument structure processing. In the present study we trained agrammatic individuals on verbs with complex argument structure in sentence contexts and examined generalization to verbs with less complex argument structure. The neural substrates of improved verb production were examined using functional magnetic resonance imaging (fMRI). Methods Eight individuals with chronic agrammatic aphasia participated in the study (four experimental and four control participants). Production of three-argument verbs in active sentences was trained using a sentence generation task emphasizing the verb’s argument structure and the thematic roles of sentential noun phrases. Before and after training, production of trained and untrained verbs was tested in naming and sentence production and fMRI scans were obtained, using an action naming task. Results Significant pre- to post-training improvement in trained and untrained (one- and two-argument) verbs was found for treated, but not control, participants, with between-group differences found for verb naming, production of verbs in sentences, and production of argument structure. fMRI activation derived from post-treatment compared to pre-treatment scans revealed upregulation in cortical regions implicated for verb and argument structure processing

  20. Immersive Environment Development for Training: Opportunities for Cooperation, Coordination, and Cost Savings

    International Nuclear Information System (INIS)

    Tackentien, J.; Hoffheins, B.; Brown, R.

    2015-01-01

    Immersive environments are increasingly demonstrating their utility for a number of nuclear safeguards, nuclear safety, and nuclear and physical security applications. Although training is an obvious use, the immersive (or sometimes called virtual) environment allows the user to ''visit'' nuclear facilities and sites that might have access restrictions because of security, high radiation or other hazards; are difficult and expensive to visit. An immersive environment can also be reconfigured to study various scenarios, processes, and other what-if situations, which can aid planning and design of new facilities or evaluate safeguards, safety and/or security measures before they are implemented. As the International Atomic Energy Agency, other international organizations, State Authorities, industry, and academia continue development and use of immersive environments and other electronic training technologies, more and more applications can be envisioned. Immersive environments are not a direct or always a desirable replacement for hands-on learning; however, the demand for electronic training media, particularly immersive environments, will grow. The resulting increase of system features and libraries presents opportunities to shorten development time frames, reduce costs and increase availability of immersive environments for a wider audience looking to balance the need for quality training with limited resources. Substantial time and cost savings can be realized by the sharing of raw assets among developers and organizations. This paper will explore potential guidelines, criteria, and mechanisms for such cooperation, including a prototype asset repository website. (author)

  1. Swiss-Slovak cooperation program: a training strategy for safety analyses

    International Nuclear Information System (INIS)

    Husarcek, J.

    2000-01-01

    During the 1996-1999 period, a new training strategy for safety analyses was implemented at the Slovak Nuclear Regulatory Authority (UJD) within the Swiss-Slovak cooperation programme in nuclear safety (SWISSLOVAK). The SWISSLOVAK project involved the recruitment, training, and integration of the newly established team into UJD's organizational structure. The training strategy consisted primarily of the following two elements: a) Probabilistic Safety Analysis (PSA) applications (regulatory review and technical evaluation of Level-1/Level-2 PSAs; PSA-based operational events analysis, PSA applications to assessment of Technical Specifications; and PSA-based hardware and/or procedure modifications) and b) Deterministic accident analyses (analysis of accidents and regulatory review of licensee Safety Analysis Reports; analysis of severe accidents/radiological releases and the potential impact of the containment and engineered safety systems, including the development of technical bases for emergency response planning; and application of deterministic methods for evaluation of accident management strategies/procedure modifications). The paper discusses the specific aspects of the training strategy performed at UJD in both the probabilistic and deterministic areas. The integration of team into UJD's organizational structure is described and examples of contributions of the team to UJD's statutory responsibilities are provided. (author)

  2. Neural correlates of training and transfer effects in working memory in older adults.

    Science.gov (United States)

    Heinzel, Stephan; Lorenz, Robert C; Pelz, Patricia; Heinz, Andreas; Walter, Henrik; Kathmann, Norbert; Rapp, Michael A; Stelzel, Christine

    2016-07-01

    As indicated by previous research, aging is associated with a decline in working memory (WM) functioning, related to alterations in fronto-parietal neural activations. At the same time, previous studies showed that WM training in older adults may improve the performance in the trained task (training effect), and more importantly, also in untrained WM tasks (transfer effects). However, neural correlates of these transfer effects that would improve understanding of its underlying mechanisms, have not been shown in older participants as yet. In this study, we investigated blood-oxygen-level-dependent (BOLD) signal changes during n-back performance and an untrained delayed recognition (Sternberg) task following 12sessions (45min each) of adaptive n-back training in older adults. The Sternberg task used in this study allowed to test for neural training effects independent of specific task affordances of the trained task and to separate maintenance from updating processes. Thirty-two healthy older participants (60-75years) were assigned either to an n-back training or a no-contact control group. Before (t1) and after (t2) training/waiting period, both the n-back task and the Sternberg task were conducted while BOLD signal was measured using functional Magnetic Resonance Imaging (fMRI) in all participants. In addition, neuropsychological tests were performed outside the scanner. WM performance improved with training and behavioral transfer to tests measuring executive functions, processing speed, and fluid intelligence was found. In the training group, BOLD signal in the right lateral middle frontal gyrus/caudal superior frontal sulcus (Brodmann area, BA 6/8) decreased in both the trained n-back and the updating condition of the untrained Sternberg task at t2, compared to the control group. fMRI findings indicate a training-related increase in processing efficiency of WM networks, potentially related to the process of WM updating. Performance gains in untrained tasks

  3. An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning

    Directory of Open Access Journals (Sweden)

    Esmond Mok

    2013-09-01

    Full Text Available Ubiquitous positioning provides continuous positional information in both indoor and outdoor environments for a wide spectrum of location based service (LBS applications. With the rapid development of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals propagated from the Wi-Fi access points (APs namely received signal strength (RSS have been cleverly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is proposed. This algorithm is based on the correlation between the initial parameter setting for neural network training and output of the mean square error to obtain better modeling of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can significantly improve the neural network training surface to achieve the highest possible accuracy of the Wi-Fi fingerprinting positioning method.

  4. A modified backpropagation algorithm for training neural networks on data with error bars

    International Nuclear Information System (INIS)

    Gernoth, K.A.; Clark, J.W.

    1994-08-01

    A method is proposed for training multilayer feedforward neural networks on data contaminated with noise. Specifically, we consider the case that the artificial neural system is required to learn a physical mapping when the available values of the target variable are subject to experimental uncertainties, but are characterized by error bars. The proposed method, based on maximum likelihood criterion for parameter estimation, involves simple modifications of the on-line backpropagation learning algorithm. These include incorporation of the error-bar assignments in a pattern-specific learning rate, together with epochal updating of a new measure of model accuracy that replaces the usual mean-square error. The extended backpropagation algorithm is successfully tested on two problems relevant to the modelling of atomic-mass systematics by neural networks. Provided the underlying mapping is reasonably smooth, neural nets trained with the new procedure are able to learn the true function to a good approximation even in the presence of high levels of Gaussian noise. (author). 26 refs, 2 figs, 5 tabs

  5. LAI inversion from optical reflectance using a neural network trained with a multiple scattering model

    Science.gov (United States)

    Smith, James A.

    1992-01-01

    The inversion of the leaf area index (LAI) canopy parameter from optical spectral reflectance measurements is obtained using a backpropagation artificial neural network trained using input-output pairs generated by a multiple scattering reflectance model. The problem of LAI estimation over sparse canopies (LAI 1000 percent for low LAI. Minimization methods applied to merit functions constructed from differences between measured reflectances and predicted reflectances using multiple-scattering models are unacceptably sensitive to a good initial guess for the desired parameter. In contrast, the neural network reported generally yields absolute percentage errors of <30 percent when weighting coefficients trained on one soil type were applied to predicted canopy reflectance at a different soil background.

  6. Activities and cooperation opportunities at Cekmece Nuclear Research and Training Center

    International Nuclear Information System (INIS)

    Can, S.

    2004-01-01

    Turkey's familiarization with nuclear energy began in July 1955, when it signed a bilateral agreement with the USA to cooperate in the 'peaceful uses of nuclear energy'. In 1956, the Turkish Atomic Energy Commission (TAEK) was created. Cekmece Nuclear Research and Training Center (CNAEM) was formally established in 1962. Turkey's first research reactor, a pool-type 1 MW reactor at CNAEM site, known as TR-1, went critical in 1962 and was shut down in September 1977. Strong collaborations with national and international organizations have been achieved for the promotion of the peaceful uses of nuclear energy and its applications in Turkey. Meanwhile the TR-2 reactor (5 MW) was commissioned in 1984 in order to meet the increasing demand of radioisotopes.CNAEM as a subsidiary of TAEK is charged to perform R and D activities on whole area of nuclear science and technology, such as research reactor, nuclear safety, nuclear fuel technology and fuel analysis codes, nuclear materials, NDT, nuclear electronics, accelerator, radiobiology, cytogenetics (bio dosimetry), radioecology, marine radioactivity, radiation safety, dosimetry, radioactive waste management, calibration of nuclear instruments, environmental monitoring. Possible cooperation fields between CNAEM and other institutions are as follows: measurements of radioactivity in the environment, radioecological studies of radioactivity levels in environmental samples, indoor radon measurements, development and production of radiopharmaceuticals, radiation cytogenetics (bio dosimetry), training in NDT, certification of industrial workers who use non-destructive testing devices, production of UO 2 and (U,Th)O 2 based fuel material, development and construction of radiation measurement instrument, analysis of all kind of uranium and thorium, training on processing and storage of low level radioactive waste

  7. Activities and cooperation opportunities at Cekmece nuclear research and training center

    International Nuclear Information System (INIS)

    Can, S.

    2004-01-01

    Full text: Turkey's familiarization with nuclear energy began in July 1955, when it signed a bilateral agreement with the USA to cooperate in the p eaceful uses of nuclear energy . In 1956, the Turkish Atomic Energy Commission (TAEK) was created. Cekmece Nuclear Research and Training Center (CNAEM) was formally established in 1962. Turkey's first research reactor, a pool-type 1 MW reactor at CNAEM site, known as TR-1, went critical in 1962 and was shut down in September 1977. Strong collaborations with national and international organizations have been achieved for the promotion of the peaceful uses of nuclear energy and its applications in Turkey. Meanwhile the TR-2 reactor (5 MW) was commissioned in 1984 in order to meet the increasing demand of radioisotopes.CNAEM as a subsidiary of TAEK is charged to perform R and D activities on whole area of nuclear science and technology, such as research reactor, nuclear safety, nuclear fuel technology and fuel analysis codes, nuclear materials, NDT, nuclear electronics, accelerator, radiobiology, cytogenetics (bio dosimetry), radioecology, marine radioactivity, radiation safety, dosimetry, radioactive waste management, calibration of nuclear instruments, environmental monitoring. Possible cooperation fields between CNAEM and other institutions are as follows: measurements of radioactivity in the environment, radioecological studies of radioactivity levels in environmental samples, indoor radon measurements, development and production of radiopharmaceuticals, radiation cytogenetics (bio dosimetry), training in NDT, certification of industrial workers who use non-destructive testing devices, production of UO 2 and (U,Th)O 2 based fuel material, development and construction of radiation measurement instrument, analysis of all kind of uranium and thorium, training on processing and storage of low level radioactive waste

  8. Examining neural correlates of skill acquisition in a complex videogame training program.

    Science.gov (United States)

    Prakash, Ruchika S; De Leon, Angeline A; Mourany, Lyla; Lee, Hyunkyu; Voss, Michelle W; Boot, Walter R; Basak, Chandramallika; Fabiani, Monica; Gratton, Gabriele; Kramer, Arthur F

    2012-01-01

    Acquisition of complex skills is a universal feature of human behavior that has been conceptualized as a process that starts with intense resource dependency, requires effortful cognitive control, and ends in relative automaticity on the multi-faceted task. The present study examined the effects of different theoretically based training strategies on cortical recruitment during acquisition of complex video game skills. Seventy-five participants were recruited and assigned to one of three training groups: (1) Fixed Emphasis Training (FET), in which participants practiced the game, (2) Hybrid Variable-Priority Training (HVT), in which participants practiced using a combination of part-task training and variable priority training, or (3) a Control group that received limited game play. After 30 h of training, game data indicated a significant advantage for the two training groups relative to the control group. The HVT group demonstrated enhanced benefits of training, as indexed by an improvement in overall game score and a reduction in cortical recruitment post-training. Specifically, while both groups demonstrated a significant reduction of activation in attentional control areas, namely the right middle frontal gyrus, right superior frontal gyrus, and the ventral medial prefrontal cortex, participants in the control group continued to engage these areas post-training, suggesting a sustained reliance on attentional regions during challenging task demands. The HVT group showed a further reduction in neural resources post-training compared to the FET group in these cognitive control regions, along with reduced activation in the motor and sensory cortices and the posteromedial cortex. Findings suggest that training, specifically one that emphasizes cognitive flexibility can reduce the attentional demands of a complex cognitive task, along with reduced reliance on the motor network.

  9. Examining neural correlates of skill acquisition in a complex videogame training program

    Directory of Open Access Journals (Sweden)

    Ruchika S Prakash

    2012-05-01

    Full Text Available Acquisition of complex skills is a universal feature of human behavior that has been conceptualized as a process that starts with intense resource dependency, requires effortful cognitive control, and ends in relative automaticity on the multi-faceted task. The present study examined the effects of different theoretically-based training strategies on cortical recruitment during acquisition of complex videogame skills. Seventy-five participants were recruited and assigned to one of three training groups: Fixed Emphasis Training (FET, in which participants practiced the game, Hybrid Variable Priority Training (HVT, in which participants practiced using a combination of part-task training and variable priority training, or a Control group that received limited game play. After 30 hours of training, game data indicated a significant advantage for the two training groups relative to the control group. The HVT group demonstrated enhanced benefits of training, as indexed by an improvement in overall game score and a reduction in cortical recruitment post-training. Specifically, while both groups demonstrated a significant reduction of activation in attentional control areas, namely the right middle frontal gyrus, right superior frontal gyrus, and the ventral medial prefrontal cortex, participants in the control group continued to engage these areas post-training, suggesting a sustained reliance on attentional regions during challenging task demands. The HVT group showed a further reduction in neural resources post-training compared to the FET group in these cognitive control regions, along with reduced activation in the motor and sensory cortices and the posteromedial cortex. Findings suggest that training, specifically one that emphasizes cognitive flexibility can reduce the attentional demands of a complex cognitive task, along with reduced reliance on the motor network.

  10. Optimal Parameter for the Training of Multilayer Perceptron Neural Networks by Using Hierarchical Genetic Algorithm

    International Nuclear Information System (INIS)

    Orozco-Monteagudo, Maykel; Taboada-Crispi, Alberto; Gutierrez-Hernandez, Liliana

    2008-01-01

    This paper deals with the controversial topic of the selection of the parameters of a genetic algorithm, in this case hierarchical, used for training of multilayer perceptron neural networks for the binary classification. The parameters to select are the crossover and mutation probabilities of the control and parametric genes and the permanency percent. The results can be considered as a guide for using this kind of algorithm.

  11. SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

    OpenAIRE

    Wang, Linnan; Ye, Jinmian; Zhao, Yiyang; Wu, Wei; Li, Ang; Song, Shuaiwen Leon; Xu, Zenglin; Kraska, Tim

    2018-01-01

    Going deeper and wider in neural architectures improves the accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need change to less desired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far be...

  12. A pilot study investigating changes in neural processing after mindfulness training in elite athletes

    OpenAIRE

    Haase, Lori; May, April C.; Falahpour, Maryam; Isakovic, Sara; Simmons, Alan N.; Hickman, Steven D.; Liu, Thomas T.; Paulus, Martin P.

    2015-01-01

    The ability to pay close attention to the present moment can be a crucial factor for performing well in a competitive situation. Training mindfulness is one approach to potentially improve elite athletes’ ability to focus their attention on the present moment. However, virtually nothing is known about whether these types of interventions alter neural systems that are important for optimal performance. This pilot study examined whether an intervention aimed at improving mindfulness [Mindful Pe...

  13. Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework

    Science.gov (United States)

    Wang, Xiao-Jing

    2016-01-01

    The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, “trained” networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale’s principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity

  14. An Issue of Boundary Value for Velocity and Training Overhead Using Cooperative MIMO Technique in Wireless Sensor Network

    Directory of Open Access Journals (Sweden)

    M. R. Islam

    2011-06-01

    Full Text Available A boundary value of velocity of data gathering node (DGN and a critical value for training overhead beyond which the cooperative communication in wireless sensor network will not be feasible is proposed in this paper. Multiple Input Multiple Outputs (MIMO cooperative communication is taken as an application. The performance in terms of energy efficiency and delay for a combination of two transmitting and two receiving antennas is analyzed. The results show that a set of critical value of velocity and training overhead pair is present for the long haul communication from the sensors to the data gathering node. Later a graphical relation between boundary value of training overhead and velocity is simulated. A mathematical relation between velocity and training overhead is also developed. The effects of several parameters on training overhead and velocity are analyzed.

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

    Directory of Open Access Journals (Sweden)

    Jeremy Purcell

    2015-05-01

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

  16. Deep learning quick reference useful hacks for training and optimizing deep neural networks with TensorFlow and Keras

    CERN Document Server

    Bernico, Michael

    2018-01-01

    This book is a practical guide to applying deep neural networks including MLPs, CNNs, LSTMs, and more in Keras and TensorFlow. Packed with useful hacks to solve real-world challenges along with the supported math and theory around each topic, this book will be a quick reference for training and optimize your deep neural networks.

  17. Attention training improves aberrant neural dynamics during working memory processing in veterans with PTSD.

    Science.gov (United States)

    McDermott, Timothy J; Badura-Brack, Amy S; Becker, Katherine M; Ryan, Tara J; Bar-Haim, Yair; Pine, Daniel S; Khanna, Maya M; Heinrichs-Graham, Elizabeth; Wilson, Tony W

    2016-12-01

    Posttraumatic stress disorder (PTSD) is associated with executive functioning deficits, including disruptions in working memory (WM). Recent studies suggest that attention training reduces PTSD symptomatology, but the underlying neural mechanisms are unknown. We used high-density magnetoencephalography (MEG) to evaluate whether attention training modulates brain regions serving WM processing in PTSD. Fourteen veterans with PTSD completed a WM task during a 306-sensor MEG recording before and after 8 sessions of attention training treatment. A matched comparison sample of 12 combat-exposed veterans without PTSD completed the same WM task during a single MEG session. To identify the spatiotemporal dynamics, each group's data were transformed into the time-frequency domain, and significant oscillatory brain responses were imaged using a beamforming approach. All participants exhibited activity in left hemispheric language areas consistent with a verbal WM task. Additionally, veterans with PTSD and combat-exposed healthy controls each exhibited oscillatory responses in right hemispheric homologue regions (e.g., right Broca's area); however, these responses were in opposite directions. Group differences in oscillatory activity emerged in the theta band (4-8 Hz) during encoding and in the alpha band (9-12 Hz) during maintenance and were significant in right prefrontal and right supramarginal and inferior parietal regions. Importantly, following attention training, these significant group differences were reduced or eliminated. This study provides initial evidence that attention training improves aberrant neural activity in brain networks serving WM processing.

  18. International Cooperation for the Training of Water Managers from Developing Countries

    Science.gov (United States)

    Aswathanarayana, U.

    2007-12-01

    Water is the key to the well being of a community. On one hand, water security is linked to food security, as food cannot be grown without water. On the other hand, water security is linked to environmental security, as water is needed to maintain the health of a community. International cooperation is proposed for the training in Hyderabad, India, with international faculty, of ~ 300 water managers from the developing countries at an estimated cost of ~USD 3300/- per candidate (including ~ USD 1800/- for international travel), through ten interactive and customized training programmes during the period of five years, to enable them to address two crucial issues affecting the poor in the developing countries, namely, access to affordable water and coping with water scarcity. Ways of Good governance and geographical targeting of poverty alleviation programmes are built into each training programme. Each training programme will be for about three weeks (inclusive of field work). Each course will have a component common to all, plus a component customized to the biophysical and socioeconomic situation in a candidate's country. Ten course manuals will be produced. which can later be published commercially as low-cost volumes, for the benefit of the readership in the Developing countries . Each candidate will be provided his own computer, and software, and individual faculty adviser. On the basis of the training received, a candidate should be able to carry with him at the end of the course a draft outline of techno-socio-economic action plan for his country/area in respect of the theme of the course, prepared by himself/herself. A copy of this outline would be provided to the World Bank, and relevant organizations for follow- up activity

  19. Planning Training Loads for the 400 M Hurdles in Three-Month Mesocycles using Artificial Neural Networks.

    Science.gov (United States)

    Przednowek, Krzysztof; Iskra, Janusz; Wiktorowicz, Krzysztof; Krzeszowski, Tomasz; Maszczyk, Adam

    2017-12-01

    This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes' training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period.

  20. Planning Training Loads for The 400 M Hurdles in Three-Month Mesocycles Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Przednowek Krzysztof

    2017-12-01

    Full Text Available This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes’ training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period.

  1. Cooperation in education and training in nuclear- and radiochemistry in Europe

    International Nuclear Information System (INIS)

    John, J.; Čuba, V.; Němec, M.

    2014-01-01

    In this paper, the motivation, history and status of coordination of education and training in nuclear- and radiochemistry in Europe will be reviewed and correlated to similar activities in other nuclear fields such as the nuclear engineering of radiological protection. The achievements of the Euratom FP7 project 'Cooperation In education in Nuclear CHemistry (CINCH)' will be described in detail. This description will cover both the status review and the development activities of this collaboration. In the status review field, the results of a detailed survey of the universities and curricula in nuclear- and radiochemistry in Europe and Russia will be presented. In the development activities field, the main achievements of the CINCH project will be presented. They are particularly the NukWik - an open platform for collaboration and sharing teaching materials in nuclear- and radiochemistry based on a wiki engine

  2. The Technology of Socio-Professional Students Training for International Cooperation

    Directory of Open Access Journals (Sweden)

    Y. V. Troynicova

    2012-01-01

    Full Text Available The contemporary development of the national system of higher education is accompanied by its large scale integration into the international scientific and educational environment. The young people’ effective integration into the global conglomerate of educational systems depends on successful mastering the international cooperation skills. Designing and implementing the integrative portfolio of educational technologies aimed at developing the corresponding competences are regarded as the key factors in solving the above mentioned problem.The paper presents the educational technology preparing students for international cooperation. Its aim and principles, subject-oriented and technology aspects are defined along with the diagnostic control activities. The methodology bases compiles the person-oriented, culture-oriented, communicative-functional approaches, which result in working out the personalized, subjectively functional, culture-creative methods and forms of training in the context of foreign language vocational education. The given technology was approbated at Udmurtskiy State University which resulted in upgrading the students’ foreign language competence and the growing numbers of participants in the international academic exchange programs.

  3. SOFT POWER: TRAINING OF VET TEACHERS AND TRAINERS (RESULTS OF THE RUSSIAN-GERMAN COOPERATION

    Directory of Open Access Journals (Sweden)

    E. Yu. Esenina

    2017-01-01

    Full Text Available Introduction. Nowadays, in Russia the system of interaction between educational institutions and enterprises-employers in training of specialists is being built again after more than a twenty-year period of dissociation. Sharing experiences with other countries on networking and strengthening of education relations with production is very useful for establishing this process. The aim of the publication is to present the results of the Russian-German cooperation in the field of preparation of the qualified pedagogical staff for the system of vocational education as one of the key conditions for ensuring the proper quality of vocational education. Methodology and research methods. The methods involve the methodology of comparative research; methods of collecting empirical information; conceptual and terminological analysis, interpretation, modeling, and problem method. Results. The approaches to preparation of pedagogical staff of the VET system in Germany and Russia are revealed and compared. Specifics of the German model are shown: existence of several skill levels of teachers of vocational education, distribution of zones of their responsibility, variability of providers of additional education, its market nature and minimum participation in its regulation of the state. Features of the modern Russian theory and training experience of instructors of vocational training are described. Despite the existing distinctions of systems of professional education of two countries, the similarity of the Russian and German methods of vocational education is observed. The conclusion is drawn on a community of requirements imposed in Germany and Russia to category of the workers who are carrying out staff training for manufacturing sectors. It is confirmed by the German experts on the basis of the analysis of the standard «Teacher of Vocational Education, Professional Education and Additional Professional Education». Also, the standard was checked and

  4. Decentralized cooperative unmanned aerial vehicles conflict resolution by neural network-based tree search method

    Directory of Open Access Journals (Sweden)

    Jian Yang

    2016-09-01

    Full Text Available In this article, a tree search algorithm is proposed to find the near optimal conflict avoidance solutions for unmanned aerial vehicles. In the dynamic environment, the unmodeled elements, such as wind, would make UAVs deviate from nominal traces. It brings about difficulties for conflict detection and resolution. The back propagation neural networks are utilized to approximate the unmodeled dynamics of the environment. To satisfy the online planning requirement, the search length of the tree search algorithm would be limited. Therefore, the algorithm may not be able to reach the goal states in search process. The midterm reward function for assessing each node is devised, with consideration given to two factors, namely, the safe separation requirement and the mission of each unmanned aerial vehicle. The simulation examples and the comparisons with previous approaches are provided to illustrate the smooth and convincing behaviours of the proposed algorithm.

  5. Neural indicators of interpersonal anger as cause and consequence of combat training stress symptoms.

    Science.gov (United States)

    Gilam, G; Lin, T; Fruchter, E; Hendler, T

    2017-07-01

    Angry outbursts are an important feature of various stress-related disorders, and commonly lead to aggression towards other people. Findings regarding interpersonal anger have linked the ventromedial prefrontal cortex (vmPFC) to anger regulation and the locus coeruleus (LC) to aggression. Both regions were previously associated with traumatic and chronic stress symptoms, yet it is unclear if their functionality represents a consequence of, or possibly also a cause for, stress symptoms. Here we investigated the relationship between the neural trajectory of these indicators of anger and the development and manifestation of stress symptoms. A total of 46 males (29 soldiers, 17 civilians) participated in a prospective functional magnetic resonance imaging experiment in which they played a modified interpersonal anger-provoking Ultimatum Game (UG) at two-points. Soldiers were tested at the beginning and end of combat training, while civilians were tested at the beginning and end of civil service. We assumed that combat training would induce chronic stress and result in increased stress symptoms. Soldiers showed an increase in stress symptoms following combat training while civilians showed no such change following civil service. All participants were angered by the modified UG irrespective of time point. Higher post-combat training stress symptoms were associated with lower pre-combat training vmPFC activation and with higher activation increase in the LC between pre- and post-combat training. Results suggest that during anger-provoking social interactions, flawed vmPFC functionality may serve as a causal risk factor for the development of stress symptoms, and heightened reactivity of the LC possibly reflects a consequence of stress-inducing combat training. These findings provide potential neural targets for therapeutic intervention and inoculation for stress-related psychopathological manifestations of anger.

  6. Wind power forecast using wavelet neural network trained by improved Clonal selection algorithm

    International Nuclear Information System (INIS)

    Chitsaz, Hamed; Amjady, Nima; Zareipour, Hamidreza

    2015-01-01

    Highlights: • Presenting a Morlet wavelet neural network for wind power forecasting. • Proposing improved Clonal selection algorithm for training the model. • Applying Maximum Correntropy Criterion to evaluate the training performance. • Extensive testing of the proposed wind power forecast method on real-world data. - Abstract: With the integration of wind farms into electric power grids, an accurate wind power prediction is becoming increasingly important for the operation of these power plants. In this paper, a new forecasting engine for wind power prediction is proposed. The proposed engine has the structure of Wavelet Neural Network (WNN) with the activation functions of the hidden neurons constructed based on multi-dimensional Morlet wavelets. This forecast engine is trained by a new improved Clonal selection algorithm, which optimizes the free parameters of the WNN for wind power prediction. Furthermore, Maximum Correntropy Criterion (MCC) has been utilized instead of Mean Squared Error as the error measure in training phase of the forecasting model. The proposed wind power forecaster is tested with real-world hourly data of system level wind power generation in Alberta, Canada. In order to demonstrate the efficiency of the proposed method, it is compared with several other wind power forecast techniques. The obtained results confirm the validity of the developed approach

  7. Convolutional neural networks based on augmented training samples for synthetic aperture radar target recognition

    Science.gov (United States)

    Yan, Yue

    2018-03-01

    A synthetic aperture radar (SAR) automatic target recognition (ATR) method based on the convolutional neural networks (CNN) trained by augmented training samples is proposed. To enhance the robustness of CNN to various extended operating conditions (EOCs), the original training images are used to generate the noisy samples at different signal-to-noise ratios (SNRs), multiresolution representations, and partially occluded images. Then, the generated images together with the original ones are used to train a designed CNN for target recognition. The augmented training samples can contrapuntally improve the robustness of the trained CNN to the covered EOCs, i.e., the noise corruption, resolution variance, and partial occlusion. Moreover, the significantly larger training set effectively enhances the representation capability for other conditions, e.g., the standard operating condition (SOC), as well as the stability of the network. Therefore, better performance can be achieved by the proposed method for SAR ATR. For experimental evaluation, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition dataset under SOC and several typical EOCs.

  8. Implementation and evaluation of a training program as part of the Cooperative Biological Engagement Program in Azerbaijan

    Directory of Open Access Journals (Sweden)

    April eJohnson

    2015-10-01

    Full Text Available A training program for animal and human health professionals has been implemented in Azerbaijan through a joint agreement between the United States Defense Threat Reduction Agency and the Government of Azerbaijan. The training program is administered as part of the Cooperative Biological Engagement Program, and targets key employees in Azerbaijan’s disease surveillance system including physicians, veterinarians, epidemiologists, and laboratory personnel. Training is aimed at improving detection, diagnosis, and response to especially dangerous pathogens, although the techniques and methodologies can be applied to other pathogens and diseases of concern. Biosafety and biosecurity training is provided to all trainees within the program. Prior to 2014, a variety of international agencies and organizations provided training, which resulted in gaps related to lack of coordination of training materials and content. In 2014 a new training program was implemented in order to address those gaps. This paper provides an overview of the Cooperative Biological Engagement Program training program in Azerbaijan, a description of how the program fits into existing national training infrastructure, and an evaluation of the new program’s effectiveness to date. Long-term sustainability of the program is also discussed.

  9. Comparative Analysis of Neural Network Training Methods in Real-time Radiotherapy

    Directory of Open Access Journals (Sweden)

    Nouri S.

    2017-03-01

    Full Text Available Background: The motions of body and tumor in some regions such as chest during radiotherapy treatments are one of the major concerns protecting normal tissues against high doses. By using real-time radiotherapy technique, it is possible to increase the accuracy of delivered dose to the tumor region by means of tracing markers on the body of patients. Objective: This study evaluates the accuracy of some artificial intelligence methods including neural network and those of combination with genetic algorithm as well as particle swarm optimization (PSO estimating tumor positions in real-time radiotherapy. Method: One hundred recorded signals of three external markers were used as input data. The signals from 3 markers thorough 10 breathing cycles of a patient treated via a cyber-knife for a lung tumor were used as data input. Then, neural network method and its combination with genetic or PSO algorithms were applied determining the tumor locations using MATLAB© software program. Results: The accuracies were obtained 0.8%, 12% and 14% in neural network, genetic and particle swarm optimization algorithms, respectively. Conclusion: The internal target volume (ITV should be determined based on the applied neural network algorithm on training steps.

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

    Science.gov (United States)

    Panda, Priyadarshini; Srinivasa, Narayan

    2018-01-01

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

  11. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  12. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Directory of Open Access Journals (Sweden)

    Tayfun Gokmen

    2017-10-01

    Full Text Available In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU devices to convolutional neural networks (CNNs. We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  13. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures. PMID:29066942

  14. The neural correlates of belief-bias inhibition: the impact of logic training.

    Science.gov (United States)

    Luo, Junlong; Tang, Xiaochen; Zhang, Entao; Stupple, Edward J N

    2014-12-01

    Functional Magnetic Resonance Imaging (fMRI) was used to investigate the brain activity associated with response change in a belief bias paradigm before and after logic training. Participants completed two sets of belief biased reasoning tasks. In the first set they were instructed to respond based on their empirical beliefs, and in the second - following logic training - they were instructed to respond logically. The comparison between conflict problems in the second scan versus in the first scan revealed differing activation for the left inferior frontal gyrus, left middle frontal gyrus, cerebellum, and precuneus. The scan was time locked to the presentation of the minor premise, and thus demonstrated effects of belief-logic conflict on neural activation earlier in the time course than has previously been shown in fMRI. These data, moreover, indicated that logical training results in changes in brain activity associated with cognitive control processing. Copyright © 2014 Elsevier B.V. All rights reserved.

  15. Training algorithms evaluation for artificial neural network to temporal prediction of photovoltaic generation

    International Nuclear Information System (INIS)

    Arantes Monteiro, Raul Vitor; Caixeta Guimarães, Geraldo; Rocio Castillo, Madeleine; Matheus Moura, Fabrício Augusto; Tamashiro, Márcio Augusto

    2016-01-01

    Current energy policies are encouraging the connection of power generation based on low-polluting technologies, mainly those using renewable sources, to distribution networks. Hence, it becomes increasingly important to understand technical challenges, facing high penetration of PV systems at the grid, especially considering the effects of intermittence of this source on the power quality, reliability and stability of the electric distribution system. This fact can affect the distribution networks on which they are attached causing overvoltage, undervoltage and frequency oscillations. In order to predict these disturbs, artificial neural networks are used. This article aims to analyze 3 training algorithms used in artificial neural networks for temporal prediction of the generated active power thru photovoltaic panels. As a result it was concluded that the algorithm with the best performance among the 3 analyzed was the Levenberg-Marquadrt.

  16. Neural Correlates of Changes in a Visual Search Task due to Cognitive Training in Seniors

    Directory of Open Access Journals (Sweden)

    Nele Wild-Wall

    2012-01-01

    Full Text Available This study aimed to elucidate the underlying neural sources of near transfer after a multidomain cognitive training in older participants in a visual search task. Participants were randomly assigned to a social control, a no-contact control and a training group, receiving a 4-month paper-pencil and PC-based trainer guided cognitive intervention. All participants were tested in a before and after session with a conjunction visual search task. Performance and event-related potentials (ERPs suggest that the cognitive training improved feature processing of the stimuli which was expressed in an increased rate of target detection compared to the control groups. This was paralleled by enhanced amplitudes of the frontal P2 in the ERP and by higher activation in lingual and parahippocampal brain areas which are discussed to support visual feature processing. Enhanced N1 and N2 potentials in the ERP for nontarget stimuli after cognitive training additionally suggest improved attention and subsequent processing of arrays which were not immediately recognized as targets. Possible test repetition effects were confined to processes of stimulus categorisation as suggested by the P3b potential. The results show neurocognitive plasticity in aging after a broad cognitive training and allow pinpointing the functional loci of effects induced by cognitive training.

  17. Electricity price forecast using Combinatorial Neural Network trained by a new stochastic search method

    International Nuclear Information System (INIS)

    Abedinia, O.; Amjady, N.; Shafie-khah, M.; Catalão, J.P.S.

    2015-01-01

    Highlights: • Presenting a Combinatorial Neural Network. • Suggesting a new stochastic search method. • Adapting the suggested method as a training mechanism. • Proposing a new forecast strategy. • Testing the proposed strategy on real-world electricity markets. - Abstract: Electricity price forecast is key information for successful operation of electricity market participants. However, the time series of electricity price has nonlinear, non-stationary and volatile behaviour and so its forecast method should have high learning capability to extract the complex input/output mapping function of electricity price. In this paper, a Combinatorial Neural Network (CNN) based forecasting engine is proposed to predict the future values of price data. The CNN-based forecasting engine is equipped with a new training mechanism for optimizing the weights of the CNN. This training mechanism is based on an efficient stochastic search method, which is a modified version of chemical reaction optimization algorithm, giving high learning ability to the CNN. The proposed price forecast strategy is tested on the real-world electricity markets of Pennsylvania–New Jersey–Maryland (PJM) and mainland Spain and its obtained results are extensively compared with the results obtained from several other forecast methods. These comparisons illustrate effectiveness of the proposed strategy.

  18. Why would musical training benefit the neural encoding of speech? The OPERA hypothesis.

    Directory of Open Access Journals (Sweden)

    Aniruddh D. Patel

    2011-06-01

    Full Text Available Mounting evidence suggests that musical training benefits the neural encoding of speech. This paper offers a hypothesis specifying why such benefits occur. The OPERA hypothesis proposes that such benefits are driven by adaptive plasticity in speech-processing networks, and that this plasticity occurs when five conditions are met. These are: 1 Overlap: there is anatomical overlap in the brain networks that process an acoustic feature used in both music and speech (e.g., waveform periodicity, amplitude envelope, 2 Precision: music places higher demands on these shared networks than does speech, in terms of the precision of processing, 3 Emotion: the musical activities that engage this network elicit strong positive emotion, 4 Repetition: the musical activities that engage this network are frequently repeated, and 5 Attention: the musical activities that engage this network are associated with focused attention. According to the OPERA hypothesis, when these conditions are met neural plasticity drives the networks in question to function with higher precision than needed for ordinary speech communication. Yet since speech shares these networks with music, speech processing benefits. The OPERA hypothesis is used to account for the observed superior subcortical encoding of speech in musically trained individuals, and to suggest mechanisms by which musical training might improve linguistic reading abilities.

  19. Why would Musical Training Benefit the Neural Encoding of Speech? The OPERA Hypothesis.

    Science.gov (United States)

    Patel, Aniruddh D

    2011-01-01

    Mounting evidence suggests that musical training benefits the neural encoding of speech. This paper offers a hypothesis specifying why such benefits occur. The "OPERA" hypothesis proposes that such benefits are driven by adaptive plasticity in speech-processing networks, and that this plasticity occurs when five conditions are met. These are: (1) Overlap: there is anatomical overlap in the brain networks that process an acoustic feature used in both music and speech (e.g., waveform periodicity, amplitude envelope), (2) Precision: music places higher demands on these shared networks than does speech, in terms of the precision of processing, (3) Emotion: the musical activities that engage this network elicit strong positive emotion, (4) Repetition: the musical activities that engage this network are frequently repeated, and (5) Attention: the musical activities that engage this network are associated with focused attention. According to the OPERA hypothesis, when these conditions are met neural plasticity drives the networks in question to function with higher precision than needed for ordinary speech communication. Yet since speech shares these networks with music, speech processing benefits. The OPERA hypothesis is used to account for the observed superior subcortical encoding of speech in musically trained individuals, and to suggest mechanisms by which musical training might improve linguistic reading abilities.

  20. Transfer of training from one working memory task to another: Behavioural and neural evidence

    Directory of Open Access Journals (Sweden)

    Erin L. Beatty

    2015-06-01

    Full Text Available N-back working memory (WM tasks necessitate the maintenance and updating of dynamic rehearsal sets during performance. The delayed matching-to-sample (dMTS task is another WM task, which in turn involves the encoding, maintenance, and retrieval of stimulus representations in sequential order. Because both n-back and dMTS engage WM function, we hypothesized that compared to a control task not taxing WM, training on the n-back task would be associated with better performance on dMTS by virtue of training a shared mental capacity. We tested this hypothesis by randomly assigning subjects (N = 43 to train on either the n-back (including 2-back and 3-back levels or an active control task. Following training, dMTS was administered in the fMRI scanner. The n-back group performed marginally better than the active control group on dMTS. In addition, although the n-back group improved more on the less difficult 2-back level than the more difficult 3-back level across training sessions, it was improvement on the 3-back level that accounted for 21% of the variance in dMTS performance. For the control group, improvement in training across sessions was unrelated to dMTS performance. At the neural level, greater activation in the left inferior frontal gyrus, right posterior parietal cortex and the cerebellum distinguished the n-back group from the control group in the maintenance phase of dMTS. Degree of improvement on the 3-back level across training sessions was correlated with activation in right lateral prefrontal and motor cortices in the maintenance phase of dMTS. Our results suggest that although n-back training is more likely to improve performance in easier blocks, it is improvement in more difficult blocks that is predictive of performance on a target task drawing on WM. In addition, the extent to which training on a task can transfer to another task is likely due to the engagement of shared cognitive capacities and underlying neural substrates

  1. A pilot study investigating changes in neural processing after mindfulness training in elite athletes.

    Science.gov (United States)

    Haase, Lori; May, April C; Falahpour, Maryam; Isakovic, Sara; Simmons, Alan N; Hickman, Steven D; Liu, Thomas T; Paulus, Martin P

    2015-01-01

    The ability to pay close attention to the present moment can be a crucial factor for performing well in a competitive situation. Training mindfulness is one approach to potentially improve elite athletes' ability to focus their attention on the present moment. However, virtually nothing is known about whether these types of interventions alter neural systems that are important for optimal performance. This pilot study examined whether an intervention aimed at improving mindfulness [Mindful Performance Enhancement, Awareness and Knowledge (mPEAK)] changes neural activation patterns during an interoceptive challenge. Participants completed a task involving anticipation and experience of loaded breathing during functional magnetic resonance imaging recording. There were five main results following mPEAK training: (1) elite athletes self-reported higher levels of interoceptive awareness and mindfulness and lower levels of alexithymia; (2) greater insula and anterior cingulate cortex (ACC) activation during anticipation and post-breathing load conditions; (3) increased ACC activation during the anticipation condition was associated with increased scores on the describing subscale of the Five Facet Mindfulness Questionnaire; (4) increased insula activation during the post-load condition was associated with decreases in the Toronto Alexithymia Scale identifying feelings subscale; (5) decreased resting state functional connectivity between the PCC and the right medial frontal cortex and the ACC. Taken together, this pilot study suggests that mPEAK training may lead to increased attention to bodily signals and greater neural processing during the anticipation and recovery from interoceptive perturbations. This association between attention to and processing of interoceptive afferents may result in greater adaptation during stressful situations in elite athletes.

  2. Pre-Trained Neural Networks used for Non-Linear State Estimation

    DEFF Research Database (Denmark)

    Bayramoglu, Enis; Andersen, Nils Axel; Ravn, Ole

    2011-01-01

    of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non-linearities......The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation...

  3. Engine cylinder pressure reconstruction using crank kinematics and recurrently-trained neural networks

    Science.gov (United States)

    Bennett, C.; Dunne, J. F.; Trimby, S.; Richardson, D.

    2017-02-01

    A recurrent non-linear autoregressive with exogenous input (NARX) neural network is proposed, and a suitable fully-recurrent training methodology is adapted and tuned, for reconstructing cylinder pressure in multi-cylinder IC engines using measured crank kinematics. This type of indirect sensing is important for cost effective closed-loop combustion control and for On-Board Diagnostics. The challenge addressed is to accurately predict cylinder pressure traces within the cycle under generalisation conditions: i.e. using data not previously seen by the network during training. This involves direct construction and calibration of a suitable inverse crank dynamic model, which owing to singular behaviour at top-dead-centre (TDC), has proved difficult via physical model construction, calibration, and inversion. The NARX architecture is specialised and adapted to cylinder pressure reconstruction, using a fully-recurrent training methodology which is needed because the alternatives are too slow and unreliable for practical network training on production engines. The fully-recurrent Robust Adaptive Gradient Descent (RAGD) algorithm, is tuned initially using synthesised crank kinematics, and then tested on real engine data to assess the reconstruction capability. Real data is obtained from a 1.125 l, 3-cylinder, in-line, direct injection spark ignition (DISI) engine involving synchronised measurements of crank kinematics and cylinder pressure across a range of steady-state speed and load conditions. The paper shows that a RAGD-trained NARX network using both crank velocity and crank acceleration as input information, provides fast and robust training. By using the optimum epoch identified during RAGD training, acceptably accurate cylinder pressures, and especially accurate location-of-peak-pressure, can be reconstructed robustly under generalisation conditions, making it the most practical NARX configuration and recurrent training methodology for use on production engines.

  4. Pilot test of cooperative learning format for training mental health researchers and black community leaders in partnership skills.

    Science.gov (United States)

    Laborde, Danielle J; Brannock, Kristen; Breland-Noble, Alfiee; Parrish, Theodore

    2007-12-01

    To support reduction of racial disparities in mental health diagnosis and treatment, mental health researchers and black community-based organization (CBO) leaders need training on how to engage in collaborative research partnerships. In this study, we pilot tested a series of partnership skills training modules for researchers and CBO leaders in a collaborative learning format. Two different sets of three modules, designed for separate training of researchers and CBO leaders, covered considering, establishing and managing mental health research partnerships and included instructions for self-directed activities and discussions. Eight CBO leaders participated in 10 sessions, and six researchers participated in eight sessions. The effectiveness of the training content and format was evaluated through standardized observations, focus group discussions, participant evaluation forms and retrospective pre-/posttests to measure perceived gains in knowledge. Participants generally were satisfied with the training experience and gained new partnership knowledge and skills. Although the CBO leaders were more engaged in the cooperative learning process, this training format appealed to both audiences. Pilot testing demonstrated that: 1) our modules can equip researchers and CBO leaders with new partnership knowledge and skills and 2) the cooperative learning format is a well-received and suitable option for mental health research partnership training.

  5. Evaluation of tactical training in team handball by means of artificial neural networks.

    Science.gov (United States)

    Hassan, Amr; Schrapf, Norbert; Ramadan, Wael; Tilp, Markus

    2017-04-01

    While tactical performance in competition has been analysed extensively, the assessment of training processes of tactical behaviour has rather been neglected in the literature. Therefore, the purpose of this study is to provide a methodology to assess the acquisition and implementation of offensive tactical behaviour in team handball. The use of game analysis software combined with an artificial neural network (ANN) software enabled identifying tactical target patterns from high level junior players based on their positions during offensive actions. These patterns were then trained by an amateur junior handball team (n = 14, 17 (0.5) years)). Following 6 weeks of tactical training an exhibition game was performed where the players were advised to use the target patterns as often as possible. Subsequently, the position data of the game was analysed with an ANN. The test revealed that 58% of the played patterns could be related to the trained target patterns. The similarity between executed patterns and target patterns was assessed by calculating the mean distance between key positions of the players in the game and the target pattern which was 0.49 (0.20) m. In summary, the presented method appears to be a valid instrument to assess tactical training.

  6. Can surgical simulation be used to train detection and classification of neural networks?

    Science.gov (United States)

    Zisimopoulos, Odysseas; Flouty, Evangello; Stacey, Mark; Muscroft, Sam; Giataganas, Petros; Nehme, Jean; Chow, Andre; Stoyanov, Danail

    2017-10-01

    Computer-assisted interventions (CAI) aim to increase the effectiveness, precision and repeatability of procedures to improve surgical outcomes. The presence and motion of surgical tools is a key information input for CAI surgical phase recognition algorithms. Vision-based tool detection and recognition approaches are an attractive solution and can be designed to take advantage of the powerful deep learning paradigm that is rapidly advancing image recognition and classification. The challenge for such algorithms is the availability and quality of labelled data used for training. In this Letter, surgical simulation is used to train tool detection and segmentation based on deep convolutional neural networks and generative adversarial networks. The authors experiment with two network architectures for image segmentation in tool classes commonly encountered during cataract surgery. A commercially-available simulator is used to create a simulated cataract dataset for training models prior to performing transfer learning on real surgical data. To the best of authors' knowledge, this is the first attempt to train deep learning models for surgical instrument detection on simulated data while demonstrating promising results to generalise on real data. Results indicate that simulated data does have some potential for training advanced classification methods for CAI systems.

  7. Combined Ozone Retrieval From METOP Sensors Using META-Training Of Deep Neural Networks

    Science.gov (United States)

    Felder, Martin; Sehnke, Frank; Kaifel, Anton

    2013-12-01

    The newest installment of our well-proven Neural Net- work Ozone Retrieval System (NNORSY) combines the METOP sensors GOME-2 and IASI with cloud information from AVHRR. Through the use of advanced meta- learning techniques like automatic feature selection and automatic architecture search applied to a set of deep neural networks, having at least two or three hidden layers, we have been able to avoid many technical issues normally encountered during the construction of such a joint retrieval system. This has been made possible by harnessing the processing power of modern consumer graphics cards with high performance graphic processors (GPU), which decreases training times by about two orders of magnitude. The system was trained on data from 2009 and 2010, including target ozone profiles from ozone sondes, ACE- FTS and MLS-AURA. To make maximum use of tropospheric information in the spectra, the data were partitioned into several sets of different cloud fraction ranges with the GOME-2 FOV, on which specialized retrieval networks are being trained. For the final ozone retrieval processing the different specialized networks are combined. The resulting retrieval system is very stable and does not show any systematic dependence on solar zenith angle, scan angle or sensor degradation. We present several sensitivity studies with regard to cloud fraction and target sensor type, as well as the performance in several latitude bands and with respect to independent validation stations. A visual cross-comparison against high-resolution ozone profiles from the KNMI EUMETSAT Ozone SAF product has also been performed and shows some distinctive features which we will briefly discuss. Overall, we demonstrate that a complex retrieval system can now be constructed with a minimum of ma- chine learning knowledge, using automated algorithms for many design decisions previously requiring expert knowledge. Provided sufficient training data and computation power of GPUs is available, the

  8. Musical training during early childhood enhances the neural encoding of speech in noise.

    Science.gov (United States)

    Strait, Dana L; Parbery-Clark, Alexandra; Hittner, Emily; Kraus, Nina

    2012-12-01

    For children, learning often occurs in the presence of background noise. As such, there is growing desire to improve a child's access to a target signal in noise. Given adult musicians' perceptual and neural speech-in-noise enhancements, we asked whether similar effects are present in musically-trained children. We assessed the perception and subcortical processing of speech in noise and related cognitive abilities in musician and nonmusician children that were matched for a variety of overarching factors. Outcomes reveal that musicians' advantages for processing speech in noise are present during pivotal developmental years. Supported by correlations between auditory working memory and attention and auditory brainstem response properties, we propose that musicians' perceptual and neural enhancements are driven in a top-down manner by strengthened cognitive abilities with training. Our results may be considered by professionals involved in the remediation of language-based learning deficits, which are often characterized by poor speech perception in noise. Copyright © 2012 Elsevier Inc. All rights reserved.

  9. The Analysis of User Behaviour of a Network Management Training Tool using a Neural Network

    Directory of Open Access Journals (Sweden)

    Helen Donelan

    2005-10-01

    Full Text Available A novel method for the analysis and interpretation of data that describes the interaction between trainee network managers and a network management training tool is presented. A simulation based approach is currently being used to train network managers, through the use of a simulated network. The motivation is to provide a tool for exposing trainees to a life like situation without disrupting a live network. The data logged by this system describes the detailed interaction between trainee network manager and simulated network. The work presented here provides an analysis of this interaction data that enables an assessment of the capabilities of the trainee network manager as well as an understanding of how the network management tasks are being approached. A neural network architecture is implemented in order to perform an exploratory data analysis of the interaction data. The neural network employs a novel form of continuous self-organisation to discover key features in the data and thus provide new insights into the learning and teaching strategies employed.

  10. EEG signal classification using PSO trained RBF neural network for epilepsy identification

    Directory of Open Access Journals (Sweden)

    Sandeep Kumar Satapathy

    Full Text Available The electroencephalogram (EEG is a low amplitude signal generated in the brain, as a result of information flow during the communication of several neurons. Hence, careful analysis of these signals could be useful in understanding many human brain disorder diseases. One such disease topic is epileptic seizure identification, which can be identified via a classification process of the EEG signal after preprocessing with the discrete wavelet transform (DWT. To classify the EEG signal, we used a radial basis function neural network (RBFNN. As shown herein, the network can be trained to optimize the mean square error (MSE by using a modified particle swarm optimization (PSO algorithm. The key idea behind the modification of PSO is to introduce a method to overcome the problem of slow searching in and around the global optimum solution. The effectiveness of this procedure was verified by an experimental analysis on a benchmark dataset which is publicly available. The result of our experimental analysis revealed that the improvement in the algorithm is significant with respect to RBF trained by gradient descent and canonical PSO. Here, two classes of EEG signals were considered: the first being an epileptic and the other being non-epileptic. The proposed method produced a maximum accuracy of 99% as compared to the other techniques. Keywords: Electroencephalography, Radial basis function neural network, Particle swarm optimization, Discrete wavelet transform, Machine learning

  11. A pilot study investigating changes in neural processing after mindfulness training in elite athletes

    Directory of Open Access Journals (Sweden)

    Lori eHaase

    2015-08-01

    Full Text Available The ability to pay close attention to the present moment can be a crucial factor for performing well in a competitive situation. Training mindfulness is one approach to potentially improve elite athletes’ ability to focus their attention on the present moment. However, virtually nothing is known about whether these types of interventions alter neural systems that are important for optimal performance. This pilot study examined whether an intervention aimed at improving mindfulness [Mindful Performance Enhancement, Awareness and Knowledge (mPEAK] changes neural activation patterns during an interoceptive challenge. Participants completed a task involving anticipation and experience of loaded breathing during functional magnetic resonance imaging (fMRI recording. There were five main results following mPEAK training: (1 elite athletes self-reported higher levels of interoceptive awareness and mindfulness and lower levels of alexithymia; (2 greater insula and anterior cingulate cortex (ACC activation during anticipation and post-breathing load conditions; (3 increased ACC activation during the anticipation condition was associated with increased scores on the describing subscale of the Five Facet Mindfulness Questionnaire (FFMQ; (4 increased insula activation during the post-load condition was associated with decreases in the Toronto Alexithymia Scale (TAS identifying feelings subscale; (5 decreased resting state functional connectivity between the PCC and the

  12. Neural Spike-Train Analyses of the Speech-Based Envelope Power Spectrum Model

    Science.gov (United States)

    Rallapalli, Varsha H.

    2016-01-01

    Diagnosing and treating hearing impairment is challenging because people with similar degrees of sensorineural hearing loss (SNHL) often have different speech-recognition abilities. The speech-based envelope power spectrum model (sEPSM) has demonstrated that the signal-to-noise ratio (SNRENV) from a modulation filter bank provides a robust speech-intelligibility measure across a wider range of degraded conditions than many long-standing models. In the sEPSM, noise (N) is assumed to: (a) reduce S + N envelope power by filling in dips within clean speech (S) and (b) introduce an envelope noise floor from intrinsic fluctuations in the noise itself. While the promise of SNRENV has been demonstrated for normal-hearing listeners, it has not been thoroughly extended to hearing-impaired listeners because of limited physiological knowledge of how SNHL affects speech-in-noise envelope coding relative to noise alone. Here, envelope coding to speech-in-noise stimuli was quantified from auditory-nerve model spike trains using shuffled correlograms, which were analyzed in the modulation-frequency domain to compute modulation-band estimates of neural SNRENV. Preliminary spike-train analyses show strong similarities to the sEPSM, demonstrating feasibility of neural SNRENV computations. Results suggest that individual differences can occur based on differential degrees of outer- and inner-hair-cell dysfunction in listeners currently diagnosed into the single audiological SNHL category. The predicted acoustic-SNR dependence in individual differences suggests that the SNR-dependent rate of susceptibility could be an important metric in diagnosing individual differences. Future measurements of the neural SNRENV in animal studies with various forms of SNHL will provide valuable insight for understanding individual differences in speech-in-noise intelligibility.

  13. Assessment of neural networks training strategies for histomorphometric analysis of synchrotron radiation medical images

    Energy Technology Data Exchange (ETDEWEB)

    Alvarenga de Moura Meneses, Anderson, E-mail: ameneses@lmp.ufrj.b [Federal University of Rio de Janeiro, COPPE, Nuclear Engineering Program, CP 68509, CEP 21.941-972, Rio de Janeiro, RJ (Brazil); IDSIA (Dalle Molle Institute for Artificial Intelligence), University of Lugano (Switzerland); Gomes Pinheiro, Christiano Jorge [State University of Rio de Janeiro, RJ (Brazil); Rancoita, Paola [IDSIA (Dalle Molle Institute for Artificial Intelligence), University of Lugano (Switzerland); Mathematics Department, Universita degli Studi di Milano (Italy); Schaul, Tom; Gambardella, Luca Maria [IDSIA (Dalle Molle Institute for Artificial Intelligence), University of Lugano (Switzerland); Schirru, Roberto [Federal University of Rio de Janeiro, COPPE, Nuclear Engineering Program, CP 68509, CEP 21.941-972, Rio de Janeiro, RJ (Brazil); Barroso, Regina Cely; Oliveira, Luis Fernando de [State University of Rio de Janeiro, RJ (Brazil)

    2010-09-21

    Micro-computed tomography ({mu}CT) obtained by synchrotron radiation (SR) enables magnified images with a high space resolution that might be used as a non-invasive and non-destructive technique for the quantitative analysis of medical images, in particular the histomorphometry (HMM) of bony mass. In the preprocessing of such images, conventional operations such as binarization and morphological filtering are used before calculating the stereological parameters related, for example, to the trabecular bone microarchitecture. However, there is no standardization of methods for HMM based on {mu}CT images, especially the ones obtained with SR X-ray. Notwithstanding the several uses of artificial neural networks (ANNs) in medical imaging, their application to the HMM of SR-{mu}CT medical images is still incipient, despite the potential of both techniques. The contribution of this paper is the assessment and comparison of well-known training algorithms as well as the proposal of training strategies (combinations of training algorithms, sub-image kernel and symmetry information) for feed-forward ANNs in the task of bone pixels recognition in SR-{mu}CT medical images. For a quantitative comparison, the results of a cross validation and a statistical analysis of the results for 36 training strategies are presented. The ANNs demonstrated both very low mean square errors in the validation, and good quality segmentation of the image of interest for application to HMM in SR-{mu}CT medical images.

  14. A pre-trained convolutional neural network based method for thyroid nodule diagnosis.

    Science.gov (United States)

    Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing

    2017-01-01

    In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.

  15. Assessment of neural networks training strategies for histomorphometric analysis of synchrotron radiation medical images

    International Nuclear Information System (INIS)

    Alvarenga de Moura Meneses, Anderson; Gomes Pinheiro, Christiano Jorge; Rancoita, Paola; Schaul, Tom; Gambardella, Luca Maria; Schirru, Roberto; Barroso, Regina Cely; Oliveira, Luis Fernando de

    2010-01-01

    Micro-computed tomography (μCT) obtained by synchrotron radiation (SR) enables magnified images with a high space resolution that might be used as a non-invasive and non-destructive technique for the quantitative analysis of medical images, in particular the histomorphometry (HMM) of bony mass. In the preprocessing of such images, conventional operations such as binarization and morphological filtering are used before calculating the stereological parameters related, for example, to the trabecular bone microarchitecture. However, there is no standardization of methods for HMM based on μCT images, especially the ones obtained with SR X-ray. Notwithstanding the several uses of artificial neural networks (ANNs) in medical imaging, their application to the HMM of SR-μCT medical images is still incipient, despite the potential of both techniques. The contribution of this paper is the assessment and comparison of well-known training algorithms as well as the proposal of training strategies (combinations of training algorithms, sub-image kernel and symmetry information) for feed-forward ANNs in the task of bone pixels recognition in SR-μCT medical images. For a quantitative comparison, the results of a cross validation and a statistical analysis of the results for 36 training strategies are presented. The ANNs demonstrated both very low mean square errors in the validation, and good quality segmentation of the image of interest for application to HMM in SR-μCT medical images.

  16. A comparative study of breast cancer diagnosis based on neural network ensemble via improved training algorithms.

    Science.gov (United States)

    Azami, Hamed; Escudero, Javier

    2015-08-01

    Breast cancer is one of the most common types of cancer in women all over the world. Early diagnosis of this kind of cancer can significantly increase the chances of long-term survival. Since diagnosis of breast cancer is a complex problem, neural network (NN) approaches have been used as a promising solution. Considering the low speed of the back-propagation (BP) algorithm to train a feed-forward NN, we consider a number of improved NN trainings for the Wisconsin breast cancer dataset: BP with momentum, BP with adaptive learning rate, BP with adaptive learning rate and momentum, Polak-Ribikre conjugate gradient algorithm (CGA), Fletcher-Reeves CGA, Powell-Beale CGA, scaled CGA, resilient BP (RBP), one-step secant and quasi-Newton methods. An NN ensemble, which is a learning paradigm to combine a number of NN outputs, is used to improve the accuracy of the classification task. Results demonstrate that NN ensemble-based classification methods have better performance than NN-based algorithms. The highest overall average accuracy is 97.68% obtained by NN ensemble trained by RBP for 50%-50% training-test evaluation method.

  17. Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations

    Directory of Open Access Journals (Sweden)

    Tayfun Gokmen

    2016-07-01

    Full Text Available In recent years, deep neural networks (DNN have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs, however, is universally considered as time consuming and computationally intensive task that demands datacenter-scale computational resources recruited for many days. Here we propose a concept of resistive processing unit (RPU devices that can potentially accelerate DNN training by orders of magnitude while using much less power. The proposed RPU device can store and update the weight values locally thus minimizing data movement during training and allowing to fully exploit the locality and the parallelism of the training algorithm. We evaluate the effect of various RPU device features/non-idealities and system parameters on performance in order to derive the device and system level specifications for implementation of an accelerator chip for DNN training in a realistic CMOS-compatible technology. For large DNNs with about 1 billion weights this massively parallel RPU architecture can achieve acceleration factors of 30,000X compared to state-of-the-art microprocessors while providing power efficiency of 84,000 GigaOps/s/W. Problems that currently require days of training on a datacenter-size cluster with thousands of machines can be addressed within hours on a single RPU accelerator. A system consisting of a cluster of RPU accelerators will be able to tackle Big Data problems with trillions of parameters that is impossible to address today like, for example, natural speech recognition and translation between all world languages, real-time analytics on large streams of business and scientific data, integration and analysis of multimodal sensory data flows from a massive number of IoT (Internet of Things sensors.

  18. Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations.

    Science.gov (United States)

    Gokmen, Tayfun; Vlasov, Yurii

    2016-01-01

    In recent years, deep neural networks (DNN) have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs, however, is universally considered as time consuming and computationally intensive task that demands datacenter-scale computational resources recruited for many days. Here we propose a concept of resistive processing unit (RPU) devices that can potentially accelerate DNN training by orders of magnitude while using much less power. The proposed RPU device can store and update the weight values locally thus minimizing data movement during training and allowing to fully exploit the locality and the parallelism of the training algorithm. We evaluate the effect of various RPU device features/non-idealities and system parameters on performance in order to derive the device and system level specifications for implementation of an accelerator chip for DNN training in a realistic CMOS-compatible technology. For large DNNs with about 1 billion weights this massively parallel RPU architecture can achieve acceleration factors of 30, 000 × compared to state-of-the-art microprocessors while providing power efficiency of 84, 000 GigaOps∕s∕W. Problems that currently require days of training on a datacenter-size cluster with thousands of machines can be addressed within hours on a single RPU accelerator. A system consisting of a cluster of RPU accelerators will be able to tackle Big Data problems with trillions of parameters that is impossible to address today like, for example, natural speech recognition and translation between all world languages, real-time analytics on large streams of business and scientific data, integration, and analysis of multimodal sensory data flows from a massive number of IoT (Internet of Things) sensors.

  19. Training-Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural Network

    Science.gov (United States)

    Laloy, Eric; Hérault, Romain; Jacques, Diederik; Linde, Niklas

    2018-01-01

    Probabilistic inversion within a multiple-point statistics framework is often computationally prohibitive for high-dimensional problems. To partly address this, we introduce and evaluate a new training-image based inversion approach for complex geologic media. Our approach relies on a deep neural network of the generative adversarial network (GAN) type. After training using a training image (TI), our proposed spatial GAN (SGAN) can quickly generate 2-D and 3-D unconditional realizations. A key characteristic of our SGAN is that it defines a (very) low-dimensional parameterization, thereby allowing for efficient probabilistic inversion using state-of-the-art Markov chain Monte Carlo (MCMC) methods. In addition, available direct conditioning data can be incorporated within the inversion. Several 2-D and 3-D categorical TIs are first used to analyze the performance of our SGAN for unconditional geostatistical simulation. Training our deep network can take several hours. After training, realizations containing a few millions of pixels/voxels can be produced in a matter of seconds. This makes it especially useful for simulating many thousands of realizations (e.g., for MCMC inversion) as the relative cost of the training per realization diminishes with the considered number of realizations. Synthetic inversion case studies involving 2-D steady state flow and 3-D transient hydraulic tomography with and without direct conditioning data are used to illustrate the effectiveness of our proposed SGAN-based inversion. For the 2-D case, the inversion rapidly explores the posterior model distribution. For the 3-D case, the inversion recovers model realizations that fit the data close to the target level and visually resemble the true model well.

  20. The regional co-operative agreement for research, development and training related to nuclear science and technology

    International Nuclear Information System (INIS)

    Fowler, E.

    1978-01-01

    The history of the Agreement, known as the RCA, is given and the operation of the Agreement, its achievements and current projects are described. The Agreement entered into force in 1972 for a period of five years and has been extended for an additional five years. Any IAEA Member State in the area of South Asia, South East Asia, the Pacific and the Far East may become a party to the Agreement. The purpose of the Agreement is to promote and co-ordinate research, development and training projects in nuclear science and technology through co-operation between the appropriate national institutions and with the assistance of the IAEA. The current RCA co-operative projects cover a broad spectrum of technologies and interests, among which are: food and agriculture, medicine, environmental research, industrial applications, training, research reactor use including radioisotope production, and physical research such as nuclear data programs

  1. Binding and segmentation via a neural mass model trained with Hebbian and anti-Hebbian mechanisms.

    Science.gov (United States)

    Cona, Filippo; Zavaglia, Melissa; Ursino, Mauro

    2012-04-01

    Synchronization of neural activity in the gamma band, modulated by a slower theta rhythm, is assumed to play a significant role in binding and segmentation of multiple objects. In the present work, a recent neural mass model of a single cortical column is used to analyze the synaptic mechanisms which can warrant synchronization and desynchronization of cortical columns, during an autoassociation memory task. The model considers two distinct layers communicating via feedforward connections. The first layer receives the external input and works as an autoassociative network in the theta band, to recover a previously memorized object from incomplete information. The second realizes segmentation of different objects in the gamma band. To this end, units within both layers are connected with synapses trained on the basis of previous experience to store objects. The main model assumptions are: (i) recovery of incomplete objects is realized by excitatory synapses from pyramidal to pyramidal neurons in the same object; (ii) binding in the gamma range is realized by excitatory synapses from pyramidal neurons to fast inhibitory interneurons in the same object. These synapses (both at points i and ii) have a few ms dynamics and are trained with a Hebbian mechanism. (iii) Segmentation is realized with faster AMPA synapses, with rise times smaller than 1 ms, trained with an anti-Hebbian mechanism. Results show that the model, with the previous assumptions, can correctly reconstruct and segment three simultaneous objects, starting from incomplete knowledge. Segmentation of more objects is possible but requires an increased ratio between the theta and gamma periods.

  2. [Simulator-based modular human factor training in anesthesiology. Concept and results of the module "Communication and Team Cooperation"].

    Science.gov (United States)

    St Pierre, M; Hofinger, G; Buerschaper, C; Grapengeter, M; Harms, H; Breuer, G; Schüttler, J

    2004-02-01

    Human factors (HF) play a major role in crisis development and management and simulator training can help to train HF aspects. We developed a modular training concept with psychological intensive briefing. The aim of the study was to see whether learning and transfer in the treatment group (TG) with the module "communication and team-cooperation" differed from that in the control group (CG) without psychological briefing ("anaesthesia crisis resource management type course"). A total of 34 residents (TG: n=20, CG: n=14) managed 1 out of 3 scenarios and communication patterns and management were evaluated using video recordings. A questionnaire was answered at the end of the course and 2 months later participants were asked for lessons learnt and behavioral changes. Good communication and medical management showed a significant correlation (r=0.57, p=0.001). The TG showed greater initiative ( p=0.001) and came more often in conflict with the surgeon ( p=0.06). The TG also reported more behavioral changes than the CG 2 months later. The reported benefit of the simulation was training for rare events in the CG, whereas in the TG it was issues of communication and cooperation ( p=0.001). A training concept with psychological intensive briefing may enhance the transfer of HF aspects more than classical ACRM.

  3. Data Normalization to Accelerate Training for Linear Neural Net to Predict Tropical Cyclone Tracks

    Directory of Open Access Journals (Sweden)

    Jian Jin

    2015-01-01

    Full Text Available When pure linear neural network (PLNN is used to predict tropical cyclone tracks (TCTs in South China Sea, whether the data is normalized or not greatly affects the training process. In this paper, min.-max. method and normal distribution method, instead of standard normal distribution, are applied to TCT data before modeling. We propose the experimental schemes in which, with min.-max. method, the min.-max. value pair of each variable is mapped to (−1, 1 and (0, 1; with normal distribution method, each variable’s mean and standard deviation pair is set to (0, 1 and (100, 1. We present the following results: (1 data scaled to the similar intervals have similar effects, no matter the use of min.-max. or normal distribution method; (2 mapping data to around 0 gains much faster training speed than mapping them to the intervals far away from 0 or using unnormalized raw data, although all of them can approach the same lower level after certain steps from their training error curves. This could be useful to decide data normalization method when PLNN is used individually.

  4. Music training relates to the development of neural mechanisms of selective auditory attention.

    Science.gov (United States)

    Strait, Dana L; Slater, Jessica; O'Connell, Samantha; Kraus, Nina

    2015-04-01

    Selective attention decreases trial-to-trial variability in cortical auditory-evoked activity. This effect increases over the course of maturation, potentially reflecting the gradual development of selective attention and inhibitory control. Work in adults indicates that music training may alter the development of this neural response characteristic, especially over brain regions associated with executive control: in adult musicians, attention decreases variability in auditory-evoked responses recorded over prefrontal cortex to a greater extent than in nonmusicians. We aimed to determine whether this musician-associated effect emerges during childhood, when selective attention and inhibitory control are under development. We compared cortical auditory-evoked variability to attended and ignored speech streams in musicians and nonmusicians across three age groups: preschoolers, school-aged children and young adults. Results reveal that childhood music training is associated with reduced auditory-evoked response variability recorded over prefrontal cortex during selective auditory attention in school-aged child and adult musicians. Preschoolers, on the other hand, demonstrate no impact of selective attention on cortical response variability and no musician distinctions. This finding is consistent with the gradual emergence of attention during this period and may suggest no pre-existing differences in this attention-related cortical metric between children who undergo music training and those who do not. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

  5. Pre-trained convolutional neural networks as feature extractors for tuberculosis detection.

    Science.gov (United States)

    Lopes, U K; Valiati, J F

    2017-10-01

    It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists. Significant research can be found on automating diagnosis by applying computational techniques to medical images, thereby eliminating the need for individual image analysis and greatly diminishing overall costs. In addition, recent improvements on deep learning accomplished excellent results classifying images on diverse domains, but its application for tuberculosis diagnosis remains limited. Thus, the focus of this work is to produce an investigation that will advance the research in the area, presenting three proposals to the application of pre-trained convolutional neural networks as feature extractors to detect the disease. The proposals presented in this work are implemented and compared to the current literature. The obtained results are competitive with published works demonstrating the potential of pre-trained convolutional networks as medical image feature extractors. Copyright © 2017 Elsevier Ltd. All rights reserved.

  6. Mindfulness training applied to addiction therapy: insights into the neural mechanisms of positive behavioral change

    Directory of Open Access Journals (Sweden)

    Garl

    2016-07-01

    Full Text Available Eric L Garland,1,2 Matthew O Howard,3 Sarah E Priddy,1 Patrick A McConnell,4 Michael R Riquino,1 Brett Froeliger4 1College of Social Work, 2Hunstsman Cancer Institute, University of Utah, Salt Lake City, UT, USA; 3School of Social Work, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA; 4Department of Neuroscience, Medical University of South Carolina, Charleston, SC, USA Abstract: Dual-process models from neuroscience suggest that addiction is driven by dysregulated interactions between bottom-up neural processes underpinning reward learning and top-down neural functions subserving executive function. Over time, drug use causes atrophy in prefrontally mediated cognitive control networks and hijacks striatal circuits devoted to processing natural rewards in service of compulsive seeking of drug-related reward. In essence, mindfulness-based interventions (MBIs can be conceptualized as mental training programs for exercising, strengthening, and remediating these functional brain networks. This review describes how MBIs may remediate addiction by regulating frontostriatal circuits, thereby restoring an adaptive balance between these top-down and bottom-up processes. Empirical evidence is presented suggesting that MBIs facilitate cognitive control over drug-related automaticity, attentional bias, and drug cue reactivity, while enhancing responsiveness to natural rewards. Findings from the literature are incorporated into an integrative account of the neural mechanisms of mindfulness-based therapies for effecting positive behavior change in the context of addiction recovery. Implications of our theoretical framework are presented with respect to how these insights can inform the addiction therapy process. Keywords: mindfulness, frontostriatal, savoring, cue reactivity, hedonic dysregulation, reward, addiction

  7. A parallel neural network training algorithm for control of discrete dynamical systems.

    Energy Technology Data Exchange (ETDEWEB)

    Gordillo, J. L.; Hanebutte, U. R.; Vitela, J. E.

    1998-01-20

    In this work we present a parallel neural network controller training code, that uses MPI, a portable message passing environment. A comprehensive performance analysis is reported which compares results of a performance model with actual measurements. The analysis is made for three different load assignment schemes: block distribution, strip mining and a sliding average bin packing (best-fit) algorithm. Such analysis is crucial since optimal load balance can not be achieved because the work load information is not available a priori. The speedup results obtained with the above schemes are compared with those corresponding to the bin packing load balance scheme with perfect load prediction based on a priori knowledge of the computing effort. Two multiprocessor platforms: a SGI/Cray Origin 2000 and a IBM SP have been utilized for this study. It is shown that for the best load balance scheme a parallel efficiency of over 50% for the entire computation is achieved by 17 processors of either parallel computers.

  8. Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction

    Science.gov (United States)

    Li, Zhencai; Wang, Yang; Liu, Zhen

    2016-01-01

    The purpose of this work is to investigate the accurate trajectory tracking control of a wheeled mobile robot (WMR) based on the slip model prediction. Generally, a nonholonomic WMR may increase the slippage risk, when traveling on outdoor unstructured terrain (such as longitudinal and lateral slippage of wheels). In order to control a WMR stably and accurately under the effect of slippage, an unscented Kalman filter and neural networks (NNs) are applied to estimate the slip model in real time. This method exploits the model approximating capabilities of nonlinear state–space NN, and the unscented Kalman filter is used to train NN’s weights online. The slip parameters can be estimated and used to predict the time series of deviation velocity, which can be used to compensate control inputs of a WMR. The results of numerical simulation show that the desired trajectory tracking control can be performed by predicting the nonlinear slip model. PMID:27467703

  9. Reconstruction of sparse connectivity in neural networks from spike train covariances

    International Nuclear Information System (INIS)

    Pernice, Volker; Rotter, Stefan

    2013-01-01

    The inference of causation from correlation is in general highly problematic. Correspondingly, it is difficult to infer the existence of physical synaptic connections between neurons from correlations in their activity. Covariances in neural spike trains and their relation to network structure have been the subject of intense research, both experimentally and theoretically. The influence of recurrent connections on covariances can be characterized directly in linear models, where connectivity in the network is described by a matrix of linear coupling kernels. However, as indirect connections also give rise to covariances, the inverse problem of inferring network structure from covariances can generally not be solved unambiguously. Here we study to what degree this ambiguity can be resolved if the sparseness of neural networks is taken into account. To reconstruct a sparse network, we determine the minimal set of linear couplings consistent with the measured covariances by minimizing the L 1 norm of the coupling matrix under appropriate constraints. Contrary to intuition, after stochastic optimization of the coupling matrix, the resulting estimate of the underlying network is directed, despite the fact that a symmetric matrix of count covariances is used for inference. The performance of the new method is best if connections are neither exceedingly sparse, nor too dense, and it is easily applicable for networks of a few hundred nodes. Full coupling kernels can be obtained from the matrix of full covariance functions. We apply our method to networks of leaky integrate-and-fire neurons in an asynchronous–irregular state, where spike train covariances are well described by a linear model. (paper)

  10. The text of an African regional co-operative agreement for research, development and training related to nuclear science and technology

    International Nuclear Information System (INIS)

    1990-04-01

    The document reproduces the text of an African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology among African Member States that was endorsed by the Board of Governors on 21 February 1990

  11. Cooperative effect of random and time-periodic coupling strength on synchronization transitions in one-way coupled neural system: mean field approach.

    Science.gov (United States)

    Jiancheng, Shi; Min, Luo; Chusheng, Huang

    2017-08-01

    The cooperative effect of random coupling strength and time-periodic coupling strengh on synchronization transitions in one-way coupled neural system has been investigated by mean field approach. Results show that cooperative coupling strength (CCS) plays an active role for the enhancement of synchronization transitions. There exist an optimal frequency of CCS which makes the system display the best CCS-induced synchronization transitions, a critical frequency of CCS which can not further affect the CCS-induced synchronization transitions, and a critical amplitude of CCS which can not occur the CCS-induced synchronization transitions. Meanwhile, noise intensity plays a negative role for the CCS-induced synchronization transitions. Furthermore, it is found that the novel CCS amplitude-induced synchronization transitions and CCS frequency-induced synchronization transitions are found.

  12. Use of training workshops as an object of study for the transformation of the cooperative community environment

    Directory of Open Access Journals (Sweden)

    Rafael Ojeda Suárez

    2017-07-01

    Full Text Available Using the potential of didactics for capacity building is a must to ensure organizational sustainability. We used a set of tools, such as, object of study, didactics, action-participatory research, generating exploratory, descriptive, correlational and explanatory studies within the cooperative organization. The workshops allowed the design of innovative teaching-learning processes to meet the demands of organizational knowledge systems, identify the main administrative management problems and actions to contribute to the organizational sustainability of the cooperative with the active, creative, participatory and compromising contribution of the social actors involved in the programs or projects. The measurement of the impacts of the projects of connection with the society, can be more easily determinable from identifying the base line that is part and the shortcomings of the organization for which the workshops of proactive socialization of information are an essential tool. On the other hand, it is required that the continuous training of teachers that lead to modify their educational conceptions and, as a consequence, their methodologies and practices at the time of tackling work with the community. The proposed actions were accepted in their entirety by the cooperative's directive, transforming itself into a Cooperative Participatory Development Program.

  13. Family medicine training in sub-Saharan Africa: South-South cooperation in the Primafamed project as strategy for development.

    Science.gov (United States)

    Flinkenflögel, Maaike; Essuman, Akye; Chege, Patrick; Ayankogbe, Olayinka; De Maeseneer, Jan

    2014-08-01

    Health-care systems based on primary health care (PHC) are more equitable and cost effective. Family medicine trains medical doctors in comprehensive PHC with knowledge and skills that are needed to increase quality of care. Family medicine is a relatively new specialty in sub-Saharan Africa. To explore the extent to which the Primafamed South-South cooperative project contributed to the development of family medicine in sub-Saharan Africa. The Primafamed (Primary Health Care and Family Medicine Education) project worked together with 10 partner universities in sub-Saharan Africa to develop family medicine training programmes over a period of 2.5 years. A SWOT (strengths, weaknesses, opportunities and threats) analysis was done and the training development from 2008 to 2010 in the different partner universities was analysed. During the 2.5 years of the Primafamed project, all partner universities made progress in the development of their family medicine training programmes. The SWOT analysis showed that at both national and international levels, the time is ripe to train medical doctors in family medicine and to integrate the specialty into health-care systems, although many barriers, including little awareness, lack of funding, low support from other specialists and reserved support from policymakers, are still present. Family medicine can play an important role in health-care systems in sub-Saharan Africa; however, developing a new discipline is challenging. Advocacy, local ownership, action research and support from governments are necessary to develop family medicine and increase its impact. The Primafamed project showed that development of sustainable family medicine training programmes is a feasible but slow process. The South-South cooperation between the ten partners and the South African departments of family medicine strengthened confidence at both national and international levels. © The Author 2014. Published by Oxford University Press.

  14. Family medicine training in sub-Saharan Africa: South–South cooperation in the Primafamed project as strategy for development

    Science.gov (United States)

    Flinkenflögel, Maaike; Essuman, Akye; Chege, Patrick; Ayankogbe, Olayinka; De Maeseneer, Jan

    2014-01-01

    Background. Health-care systems based on primary health care (PHC) are more equitable and cost effective. Family medicine trains medical doctors in comprehensive PHC with knowledge and skills that are needed to increase quality of care. Family medicine is a relatively new specialty in sub-Saharan Africa. Objective. To explore the extent to which the Primafamed South–South cooperative project contributed to the development of family medicine in sub-Saharan Africa. Methods. The Primafamed (Primary Health Care and Family Medicine Education) project worked together with 10 partner universities in sub-Saharan Africa to develop family medicine training programmes over a period of 2.5 years. A SWOT (strengths, weaknesses, opportunities and threats) analysis was done and the training development from 2008 to 2010 in the different partner universities was analysed. Results. During the 2.5 years of the Primafamed project, all partner universities made progress in the development of their family medicine training programmes. The SWOT analysis showed that at both national and international levels, the time is ripe to train medical doctors in family medicine and to integrate the specialty into health-care systems, although many barriers, including little awareness, lack of funding, low support from other specialists and reserved support from policymakers, are still present. Conclusions. Family medicine can play an important role in health-care systems in sub-Saharan Africa; however, developing a new discipline is challenging. Advocacy, local ownership, action research and support from governments are necessary to develop family medicine and increase its impact. The Primafamed project showed that development of sustainable family medicine training programmes is a feasible but slow process. The South–South cooperation between the ten partners and the South African departments of family medicine strengthened confidence at both national and international levels. PMID:24857843

  15. Manifold absolute pressure estimation using neural network with hybrid training algorithm.

    Directory of Open Access Journals (Sweden)

    Mohd Taufiq Muslim

    Full Text Available In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM algorithm, Bayesian Regularization (BR algorithm and Particle Swarm Optimization (PSO algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS. The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.

  16. Training Knowledge Bots for Physics-Based Simulations Using Artificial Neural Networks

    Science.gov (United States)

    Samareh, Jamshid A.; Wong, Jay Ming

    2014-01-01

    Millions of complex physics-based simulations are required for design of an aerospace vehicle. These simulations are usually performed by highly trained and skilled analysts, who execute, monitor, and steer each simulation. Analysts rely heavily on their broad experience that may have taken 20-30 years to accumulate. In addition, the simulation software is complex in nature, requiring significant computational resources. Simulations of system of systems become even more complex and are beyond human capacity to effectively learn their behavior. IBM has developed machines that can learn and compete successfully with a chess grandmaster and most successful jeopardy contestants. These machines are capable of learning some complex problems much faster than humans can learn. In this paper, we propose using artificial neural network to train knowledge bots to identify the idiosyncrasies of simulation software and recognize patterns that can lead to successful simulations. We examine the use of knowledge bots for applications of computational fluid dynamics (CFD), trajectory analysis, commercial finite-element analysis software, and slosh propellant dynamics. We will show that machine learning algorithms can be used to learn the idiosyncrasies of computational simulations and identify regions of instability without including any additional information about their mathematical form or applied discretization approaches.

  17. Manifold absolute pressure estimation using neural network with hybrid training algorithm.

    Science.gov (United States)

    Muslim, Mohd Taufiq; Selamat, Hazlina; Alimin, Ahmad Jais; Haniff, Mohamad Fadzli

    2017-01-01

    In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.

  18. The International Research Training Group on "Brain-Behavior Relationship of Normal and Disturbed Emotions in Schizophrenia and Autism" as an Example of German-American Cooperation in Doctoral Training

    Science.gov (United States)

    Schneider, Frank; Gur, Ruben C.

    2008-01-01

    The International Research Training Group "Brain-Behavior Relationship of Normal and Disturbed Emotions in Schizophrenia and Autism" (IRTG 1328), funded by the German Research Council (DFG), is a German-American cooperation. Its major aims are interdisciplinary and international scientific cooperation and the support of young scientists…

  19. Neural Mechanisms of Qigong Sensory Training Massage for Children With Autism Spectrum Disorder: A Feasibility Study.

    Science.gov (United States)

    Jerger, Kristin K; Lundegard, Laura; Piepmeier, Aaron; Faurot, Keturah; Ruffino, Amanda; Jerger, Margaret A; Belger, Aysenil

    2018-01-01

    Despite the enormous prevalence of autism spectrum disorder (ASD), its global impact has yet to be realized. Millions of families worldwide need effective treatments to help them get through everyday challenges like eating, sleeping, digestion, and social interaction. Qigong Sensory Training (QST) is a nonverbal, parent-delivered intervention recently shown to be effective at reducing these everyday challenges in children with ASD. This study tested the feasibility of a protocol for investigating QST's neural mechanism. During a single visit, 20 children, 4- to 7-year-old, with ASD viewed images of emotional faces before and after receiving QST or watching a video (controls). Heart rate variability was recorded throughout the visit, and power in the high frequency band (0.15-0.4 Hz) was calculated to estimate parasympathetic tone in 5-s nonoverlapping windows. Cerebral oximetry of prefrontal cortex was recorded during rest and while viewing emotional faces. 95% completion rate and 7.6% missing data met a priori standards confirming protocol feasibility for future studies. Preliminary data suggest: (1) during the intervention, parasympathetic tone increased more in children receiving massage (M = 2.9, SD = 0.3) versus controls (M = 2.5, SD = 0.5); (2) while viewing emotional faces post-intervention, parasympathetic tone was more affected (reduced) in the massage group ( p  = 0.036); and (3) prefrontal cortex response to emotional faces was greater after massage compared to controls. These results did not reach statistical significance in this small study powered to test feasibility. This study demonstrates solid protocol feasibility. If replicated in a larger sample, these findings would provide important clues to the neural mechanism of action underlying QST's efficacy for improving sensory, social, and communication difficulties in children with autism.

  20. Text of an African regional co-operative agreement for research, development and training related to nuclear science and technology

    International Nuclear Information System (INIS)

    1994-01-01

    As of 1 September 1994, notifications of acceptance of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (see INFCIRC/377), in accordance with Article XIII thereof, had been received by the Director General from the Governments of: Tunisia, Egypt, Algeria, Nigeria, Madagascar, Libya, Morocco, Kenya, Sudan, Ghana, Tanzania, Mauritius, Cameroon, South Africa, Zaire, Ethiopia, Zambia, Niger. The Agreement entered into force on 4 April 1990, the date of receipt of the third notification of acceptance

  1. Influence of the Training Set Value on the Quality of the Neural Network to Identify Selected Moulding Sand Properties

    Directory of Open Access Journals (Sweden)

    Jakubski J.

    2013-06-01

    Full Text Available Artificial neural networks are one of the modern methods of the production optimisation. An attempt to apply neural networks for controlling the quality of bentonite moulding sands is presented in this paper. This is the assessment method of sands suitability by means of detecting correlations between their individual parameters. This paper presents the next part of the study on usefulness of artificial neural networks to support rebonding of green moulding sand, using chosen properties of moulding sands, which can be determined fast. The effect of changes in the training set quantity on the quality of the network is presented in this article. It has been shown that a small change in the data set would change the quality of the network, and may also make it necessary to change the type of network in order to obtain good results.

  2. Neural substrates of cognitive control under the belief of getting neurofeedback training

    Directory of Open Access Journals (Sweden)

    Manuel eNinaus

    2013-12-01

    Full Text Available Learning to modulate one’s own brain activity is the fundament of neurofeedback (NF applications. Besides the neural networks directly involved in the generation and modulation of the neurophysiological parameter being specifically trained, more general determinants of NF efficacy such as self-referential processes and cognitive control have been frequently disregarded. Nonetheless, deeper insight into these cognitive mechanisms and their neuronal underpinnings sheds light on various open NF related questions concerning individual differences, brain-computer interface (BCI illiteracy as well as a more general model of NF learning. In this context, we investigated the neuronal substrate of these more general regulatory mechanisms that are engaged when participants believe that they are receiving NF. Twenty healthy participants (40-63 years, 10 female performed a sham NF paradigm during fMRI scanning. All participants were novices to NF-experiments and were instructed to voluntarily modulate their own brain activity based on a visual display of moving color bars. However, the bar depicted a recording and not the actual brain activity of participants. Reports collected at the end of the experiment indicate that participants were unaware of the sham feedback. In comparison to a passive watching condition, bilateral insula, anterior cingulate cortex and supplementary motor and dorsomedial and lateral prefrontal area were activated when participants actively tried to control the bar. In contrast, when merely watching moving bars, increased activation in the left angular gyrus was observed. These results show that the intention to control a moving bar is sufficient to engage a broad frontoparietal and cingulo-opercular network involved in cognitive control. The results of the present study indicate that tasks such as those generally employed in NF training recruit the neuronal correlates of cognitive control even when only sham NF is presented.

  3. Cognitive and Neural Plasticity in Older Adults’ Prospective Memory Following Training with the Virtual Week Computer Game

    Directory of Open Access Journals (Sweden)

    Nathan S Rose

    2015-10-01

    Full Text Available Prospective memory (PM – the ability to remember and successfully execute our intentions and planned activities – is critical for functional independence and declines with age, yet few studies have attempted to train PM in older adults. We developed a PM training program using the Virtual Week computer game. Trained participants played the game in twelve, 1-hour sessions over one month. Measures of neuropsychological functions, lab-based PM, event-related potentials (ERPs during performance on a lab-based PM task, instrumental activities of daily living, and real-world PM were assessed before and after training. Performance was compared to both no-contact and active (music training control groups. PM on the Virtual Week game dramatically improved following training relative to controls, suggesting PM plasticity is preserved in older adults. Relative to control participants, training did not produce reliable transfer to laboratory-based tasks, but was associated with a reduction of an ERP component (sustained negativity over occipito-parietal cortex associated with processing PM cues, indicative of more automatic PM retrieval. Most importantly, training produced far transfer to real-world outcomes including improvements in performance on real-world PM and activities of daily living. Real-world gains were not observed in either control group. Our findings demonstrate that short-term training with the Virtual Week game produces cognitive and neural plasticity that may result in real-world benefits to supporting functional independence in older adulthood.

  4. Cognitive and neural plasticity in older adults' prospective memory following training with the Virtual Week computer game.

    Science.gov (United States)

    Rose, Nathan S; Rendell, Peter G; Hering, Alexandra; Kliegel, Matthias; Bidelman, Gavin M; Craik, Fergus I M

    2015-01-01

    Prospective memory (PM) - the ability to remember and successfully execute our intentions and planned activities - is critical for functional independence and declines with age, yet few studies have attempted to train PM in older adults. We developed a PM training program using the Virtual Week computer game. Trained participants played the game in 12, 1-h sessions over 1 month. Measures of neuropsychological functions, lab-based PM, event-related potentials (ERPs) during performance on a lab-based PM task, instrumental activities of daily living, and real-world PM were assessed before and after training. Performance was compared to both no-contact and active (music training) control groups. PM on the Virtual Week game dramatically improved following training relative to controls, suggesting PM plasticity is preserved in older adults. Relative to control participants, training did not produce reliable transfer to laboratory-based tasks, but was associated with a reduction of an ERP component (sustained negativity over occipito-parietal cortex) associated with processing PM cues, indicative of more automatic PM retrieval. Most importantly, training produced far transfer to real-world outcomes including improvements in performance on real-world PM and activities of daily living. Real-world gains were not observed in either control group. Our findings demonstrate that short-term training with the Virtual Week game produces cognitive and neural plasticity that may result in real-world benefits to supporting functional independence in older adulthood.

  5. The Need for a Cooperative Paradigm to Meet Business' Key Microcomputer Training Requirements.

    Science.gov (United States)

    Hubbard, Gary R.

    1985-01-01

    The growing awareness and availability of business application software at small business prices and the creation of a unique national computer training consortium has motivated one community college district to promote more non-credit, short-term training opportunities in accounting software. Rationale for and development of these opportunities…

  6. Improving quantitative structure-activity relationship models using Artificial Neural Networks trained with dropout.

    Science.gov (United States)

    Mendenhall, Jeffrey; Meiler, Jens

    2016-02-01

    Dropout is an Artificial Neural Network (ANN) training technique that has been shown to improve ANN performance across canonical machine learning (ML) datasets. Quantitative Structure Activity Relationship (QSAR) datasets used to relate chemical structure to biological activity in Ligand-Based Computer-Aided Drug Discovery pose unique challenges for ML techniques, such as heavily biased dataset composition, and relatively large number of descriptors relative to the number of actives. To test the hypothesis that dropout also improves QSAR ANNs, we conduct a benchmark on nine large QSAR datasets. Use of dropout improved both enrichment false positive rate and log-scaled area under the receiver-operating characteristic curve (logAUC) by 22-46 % over conventional ANN implementations. Optimal dropout rates are found to be a function of the signal-to-noise ratio of the descriptor set, and relatively independent of the dataset. Dropout ANNs with 2D and 3D autocorrelation descriptors outperform conventional ANNs as well as optimized fingerprint similarity search methods.

  7. International technical cooperation to develop the Russian methodological and training center

    International Nuclear Information System (INIS)

    Pshakin, G.; Ryazanov, B.; Dickman, D.; Cross, R.; Guardini, S.; Cuypers, M.

    1999-01-01

    The RMTC, located at the Institute of Physics and Power Engineering (IPPE) in Obninsk, Russia has been designated by the Russian Ministry of Atomic Energy (Minatom) to provide nuclear materials protection, control and accounting (MPC and A) training to Minatom and the Federal Nuclear and Radiation Safety Authority (Gosatomndzor) personnel. Following the political changes within the RF that resulted in fragmentation of centralized control and management of nuclear materials, the RF embarked on an effort to upgrade its state system of accountancy and control (SSAC) of nuclear materials. This situation created the need to provide widespread training to Russian specialists in new MPC and A methods and modern technologies. The RMTC was established to provide centralized training and implementation support in these areas, as well as provide a forum for discussions between plant operators and inspectors. During the period of the RMTC's development, both the European Commission and the U.S. have contributed to the rapid progress made in Russian training program development and equipment upgrades. Enhanced training facilities are in operation, laboratory and other training equipment has been installed, and over 30 courses have been developed. The majority of these have been jointly developed and taught. The RMTC infrastructure has been strengthened and a strategic plan for the long-term sustainability of the RMTC has been completed. Future directions of this project include ensuring continued development of indigenous Russian training capabilities and viability of the RMTC. This paper describes collaboration to date, discusses accomplishments and outlines future developmental activities for the RMTC. (author)

  8. Cooperative approach to training for radiological emergency preparedness and response in Southeast Asia

    International Nuclear Information System (INIS)

    Bus, John; Popp, Andrew; Holland, Brian; Murray, Allan

    2011-01-01

    The paper describes the collaborative and systematic approach to training for nuclear and radiological emergency preparedness and response and the outcomes of this work with ANSTO's Southeast Asian counterparts, particularly in the Philippines. The standards and criteria being applied are discussed, along with the methods, design and conduct of workshops, table-top and field exercises. The following elements of this training will be presented: (a) identifying the priority areas for training through needs analysis;(b) strengthening individual profesional expertise through a structured approach to training; and (c) enhancing individual Agency and National nuclear and radiological emergency preparedness and response arrangements and capabilities. Whilst the work is motivated by nuclear security concerns, the implications for effective and sustainable emergency response to any nuclear or radiological incidents are noted. (author)

  9. Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the 'Extreme Learning Machine' Algorithm.

    Directory of Open Access Journals (Sweden)

    Mark D McDonnell

    Full Text Available Recent advances in training deep (multi-layer architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM approach, which also enables a very rapid training time (∼ 10 minutes. Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random 'receptive field' sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.

  10. Relationship of mindful awareness to neural processing of angry faces and impact of mindfulness training: A pilot investigation.

    Science.gov (United States)

    Lee, Athene K W; Gansler, David A; Zhang, Nanyin; Jerram, Matthew W; King, Jean A; Fulwiler, Carl

    2017-06-30

    Mindfulness is paying attention, non-judgmentally, to experience in the moment. Mindfulness training reduces depression and anxiety and influences neural processes in midline self-referential and lateralized somatosensory and executive networks. Although mindfulness benefits emotion regulation, less is known about its relationship to anger and the corresponding neural correlates. This study examined the relationship of mindful awareness and brain hemodynamics of angry face processing, and the impact of mindfulness training. Eighteen healthy volunteers completed an angry face processing fMRI paradigm and measurement of mindfulness and anger traits. Ten of these participants were recruited from a Mindfulness-Based Stress Reduction (MBSR) class and also completed imaging and other assessments post-training. Self-reported mindful awareness increased after MBSR, but trait anger did not change. Baseline mindful awareness was negatively related to left inferior parietal lobule activation to angry faces; trait anger was positively related to right middle frontal gyrus and bilateral angular gyrus. No significant pre-post changes in angry face processing were found, but changes in trait mindful awareness and anger were associated with sub-threshold differences in paralimbic activation. These preliminary and hypothesis-generating findings, suggest the analysis of possible impact of mindfulness training on anger may begin with individual differences in angry face processing. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

  11. 75 FR 11561 - Solicitation for a Cooperative Agreement-Training for Executive Excellence: Leadership Style and...

    Science.gov (United States)

    2010-03-11

    ...--Training for Executive Excellence: Leadership Style and Instrumentation Curriculum Development AGENCY... leadership styles through the Myers-Briggs Type Indicator; An emotional intelligence and leadership profile...' ``Correctional Leadership Competencies for the 21st Century'' for the executive level. It is expected that the...

  12. The role of inter-institutional cooperation in surgical training and ...

    African Journals Online (AJOL)

    Methods: Contact was first initiated between the heads of department at the two institutions and communications was almost entirely through e-mail. A Memorandum of Understanding ... taking part in the exchange programs. Keywords: Surgical training, North-South divide, academic exchange programs, Tanzania, Germany ...

  13. Cooperativas habitacionais e capacitação profissional. /Housing cooperatives and professional training.

    Directory of Open Access Journals (Sweden)

    Gobbi Santos, Alessandra

    2005-06-01

    Full Text Available Este artigo descreve a importância do compromisso social na formação dos profissionais de arquitetura e urbanismo no momento em que é abordada a temática da habitação de interesse social. Essa abordagem é feita através da apresentação de diretrizes organizacionais de implementação de cooperativas habitacionais autogestionárias a fim de auxiliar na preparação de alunos e no assessoramento com a capacitação dos profissionais. Nesse contexto é feita apresentação de um quadro de diretrizes organizacionais, e a partir desse quadro, apresentam-se também duas figuras: a primeira ilustra as principais causas de dissolução de cooperativas habitacionais autogeridas e a segunda figura demonstra o papel da assessoria técnica e mais precisamente as funções essenciais do arquiteto urbanista numa cooperativa habitacional autogerida. Ao finalizar, são expostos conceitos e características da autogestão na produção de moradia./This subject describes the importance of the social commitment in the formation of the architecture and urbanization professionals at the moment what is approach the housing thematic of social interesting. This approach is doing through of the presentation of directives ordering of implementation of self-managed housing cooperatives in order to aid in the preparation of students and in the assistment with the enable of the professionals. On the context is doing presentation of a chart of directives ordering and from this chart presents also two pictures: the first to illustrate the principal reasons of the dissolving of the self-managed housing cooperatives, and the second demonstrate the role of the tecnic assistance and more specifyty the essential function of the urban architect on a self-managed housing cooperatives. To the ending, are exposed concepts and characteristics of the self administration on the production of residence dwelling.

  14. International cooperation

    International Nuclear Information System (INIS)

    1996-01-01

    In 1995, Nuclear Regulatory Authority of the Slovak Republic (NRA SR) ensured foreign cooperation particularly in the frame of the Slovak Republic is membership in the IAEA, as well as cooperation with the Nuclear Energy Agency of the Organization for Economic Cooperation and Development (OECD NEA), cooperation with European Union in the frame of PHARE programmes, and intergovernmental cooperation and cooperation among nuclear regulatory authorities. With respect to an international importance, prestige and a wide-scope possibilities of a technical assistance , either a direct one (expert assessments, technology supplies, work placement, scientific trips, training courses) or indirect one (participation at various conferences, seminars, technical committees, etc), the most important cooperation with the IAEA in Vienna. In 1994, the Slovak Republic, was elected to the Board Governors, the represent the group of Eastern European countries. The Slovak Government entrusted the NRA SR's Chairman with representing the Slovak Republic in the Board of Governors. Owing to a good name of Slovakia was elected to the one of two Vice-Chairmen of the Board of Governors at the 882-nd session on the Board. IAEA approved and developed 8 national projects for Slovakia in 1995. Generally, IAEA is contracting scientific contracts with research institutes, nuclear power plants and other organizations. Slovak organizations used these contracts as complementary funding of their tasks. In 1995, there were 12 scientific contracts in progress, or approved respectively. Other international activities of the NRA SR, international co-operations as well as foreign affairs are reported

  15. Joint Combined Exchange Training Evaluation Framework: A Crucial Tool in Security Cooperation Assessment

    Science.gov (United States)

    2015-12-01

    contested when both parties originally signed it in 1947.48 Manuel Quezon, Philippine Senate President at the time, stated that if the United States had...2014. 63 Ibid. 64 Manuel Mogato, “United States Seeks Access to Philippine Bases as Part of Asia Pivot,” Reuters, http://www.reuters.com/article...document is classified FOUO. Mark Cruz (U) Balance Piston XX-X After Training Report (Department of National Defense: Republic of the Philippines

  16. Exploring the effects of transducer models when training convolutional neural networks to eliminate reflection artifacts in experimental photoacoustic images

    Science.gov (United States)

    Allman, Derek; Reiter, Austin; Bell, Muyinatu

    2018-02-01

    We previously proposed a method of removing reflection artifacts in photoacoustic images that uses deep learning. Our approach generally relies on using simulated photoacoustic channel data to train a convolutional neural network (CNN) that is capable of distinguishing sources from artifacts based on unique differences in their spatial impulse responses (manifested as depth-based differences in wavefront shapes). In this paper, we directly compare a CNN trained with our previous continuous transducer model to a CNN trained with an updated discrete acoustic receiver model that more closely matches an experimental ultrasound transducer. These two CNNs were trained with simulated data and tested on experimental data. The CNN trained using the continuous receiver model correctly classified 100% of sources and 70.3% of artifacts in the experimental data. In contrast, the CNN trained using the discrete receiver model correctly classified 100% of sources and 89.7% of artifacts in the experimental images. The 19.4% increase in artifact classification accuracy indicates that an acoustic receiver model that closely mimics the experimental transducer plays an important role in improving the classification of artifacts in experimental photoacoustic data. Results are promising for developing a method to display CNN-based images that remove artifacts in addition to only displaying network-identified sources as previously proposed.

  17. Effects of Time-Compressed Speech Training on Multiple Functional and Structural Neural Mechanisms Involving the Left Superior Temporal Gyrus.

    Science.gov (United States)

    Maruyama, Tsukasa; Takeuchi, Hikaru; Taki, Yasuyuki; Motoki, Kosuke; Jeong, Hyeonjeong; Kotozaki, Yuka; Nakagawa, Seishu; Nouchi, Rui; Iizuka, Kunio; Yokoyama, Ryoichi; Yamamoto, Yuki; Hanawa, Sugiko; Araki, Tsuyoshi; Sakaki, Kohei; Sasaki, Yukako; Magistro, Daniele; Kawashima, Ryuta

    2018-01-01

    Time-compressed speech is an artificial form of rapidly presented speech. Training with time-compressed speech (TCSSL) in a second language leads to adaptation toward TCSSL. Here, we newly investigated the effects of 4 weeks of training with TCSSL on diverse cognitive functions and neural systems using the fractional amplitude of spontaneous low-frequency fluctuations (fALFF), resting-state functional connectivity (RSFC) with the left superior temporal gyrus (STG), fractional anisotropy (FA), and regional gray matter volume (rGMV) of young adults by magnetic resonance imaging. There were no significant differences in change of performance of measures of cognitive functions or second language skills after training with TCSSL compared with that of the active control group. However, compared with the active control group, training with TCSSL was associated with increased fALFF, RSFC, and FA and decreased rGMV involving areas in the left STG. These results lacked evidence of a far transfer effect of time-compressed speech training on a wide range of cognitive functions and second language skills in young adults. However, these results demonstrated effects of time-compressed speech training on gray and white matter structures as well as on resting-state intrinsic activity and connectivity involving the left STG, which plays a key role in listening comprehension.

  18. An integrated neural-symbolic cognitive agent architecture for training and assessment in simulators

    NARCIS (Netherlands)

    Penning, H.L.H. de; d'Avila Garcez, A.S.; Lamb, L.C.; Meyer, J.J.C.

    2010-01-01

    Training and assessment of complex tasks has always been a complex task in itself. Training simulators can be used for training and assessment of low-order skills. High-order skills (e.g. safe driving, leadership, tactical manoeuvring, etc.) are generally trained and assessed by human experts, due

  19. Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

    Directory of Open Access Journals (Sweden)

    Jeng-Fung Chen

    2014-10-01

    Full Text Available Predicting student academic performance with a high accuracy facilitates admission decisions and enhances educational services at educational institutions. This raises the need to propose a model that predicts student performance, based on the results of standardized exams, including university entrance exams, high school graduation exams, and other influential factors. In this study, an approach to the problem based on the artificial neural network (ANN with the two meta-heuristic algorithms inspired by cuckoo birds and their lifestyle, namely, Cuckoo Search (CS and Cuckoo Optimization Algorithm (COA is proposed. In particular, we used previous exam results and other factors, such as the location of the student’s high school and the student’s gender as input variables, and predicted the student academic performance. The standard CS and standard COA were separately utilized to train the feed-forward network for prediction. The algorithms optimized the weights between layers and biases of the neuron network. The simulation results were then discussed and analyzed to investigate the prediction ability of the neural network trained by these two algorithms. The findings demonstrated that both CS and COA have potential in training ANN and ANN-COA obtained slightly better results for predicting student academic performance in this case. It is expected that this work may be used to support student admission procedures and strengthen the service system in educational institutions.

  20. Prediction of composite fatigue life under variable amplitude loading using artificial neural network trained by genetic algorithm

    Science.gov (United States)

    Rohman, Muhamad Nur; Hidayat, Mas Irfan P.; Purniawan, Agung

    2018-04-01

    Neural networks (NN) have been widely used in application of fatigue life prediction. In the use of fatigue life prediction for polymeric-base composite, development of NN model is necessary with respect to the limited fatigue data and applicable to be used to predict the fatigue life under varying stress amplitudes in the different stress ratios. In the present paper, Multilayer-Perceptrons (MLP) model of neural network is developed, and Genetic Algorithm was employed to optimize the respective weights of NN for prediction of polymeric-base composite materials under variable amplitude loading. From the simulation result obtained with two different composite systems, named E-glass fabrics/epoxy (layups [(±45)/(0)2]S), and E-glass/polyester (layups [90/0/±45/0]S), NN model were trained with fatigue data from two different stress ratios, which represent limited fatigue data, can be used to predict another four and seven stress ratios respectively, with high accuracy of fatigue life prediction. The accuracy of NN prediction were quantified with the small value of mean square error (MSE). When using 33% from the total fatigue data for training, the NN model able to produce high accuracy for all stress ratios. When using less fatigue data during training (22% from the total fatigue data), the NN model still able to produce high coefficient of determination between the prediction result compared with obtained by experiment.

  1. Upper Limb Rehabilitation Robot Powered by PAMs Cooperates with FES Arrays to Realize Reach-to-Grasp Trainings

    Science.gov (United States)

    Su, Chen; Jiang, Xiaobo

    2017-01-01

    The reach-to-grasp activities play an important role in our daily lives. The developed RUPERT for stroke patients with high stiffness in arm flexor muscles is a low-cost lightweight portable exoskeleton rehabilitation robot whose joints are unidirectionally actuated by pneumatic artificial muscles (PAMs). In order to expand the useful range of RUPERT especially for patients with flaccid paralysis, functional electrical stimulation (FES) is taken to activate paralyzed arm muscles. As both the exoskeleton robot driven by PAMs and the neuromuscular skeletal system under FES possess the highly nonlinear and time-varying characteristics, iterative learning control (ILC) is studied and is taken to control this newly designed hybrid rehabilitation system for reaching trainings. Hand function rehabilitation refers to grasping. Because of tiny finger muscles, grasping and releasing are realized by FES array electrodes and matrix scan method. By using the surface electromyography (EMG) technique, the subject's active intent is identified. The upper limb rehabilitation robot powered by PAMs cooperates with FES arrays to realize active reach-to-grasp trainings, which was verified through experiments. PMID:29065566

  2. Training of Radiation Protection and Medical Physics in Latin American Through the SEPR (Griapra): Six years of Cooperation

    International Nuclear Information System (INIS)

    Pena, J. J.; Rossell, M. A.; Calvo, J. L.; Vega, J. M.

    2003-01-01

    The Ibero-American Group of Scientific Societies of Radiological Protection (GRIAPRA) was constituted on 30-September-1996 as the end of a process that the SEPR began in its V National Congress (Santiago de Compostela, 1994). In this work are presented some of the results of the experience accumulated by the SEPR (GRIAPRA) in training and professional update of latin-american radiologists,medical physicists and technician during these last six years:Cuba (La Habana 1998), Peru (Lima 1999), Mexico (Guadalajara 2000), Brazil (Recife, 2001), Peru (Lima 2002) and Cuba (La Habana 2003). They are shown the professional profiles of the american colleagues that in number superior to 300 persons have been accepted in these training courses imparted by members very qualified of the SEPR and SEFM, the theoric-practical structure of these courses, the design of their programming, documentation, the sources of financing, the general analysis of the wisdoms and mistakes and the proposal to continue with this cooperation in the future. (Author)

  3. Upper Limb Rehabilitation Robot Powered by PAMs Cooperates with FES Arrays to Realize Reach-to-Grasp Trainings

    Directory of Open Access Journals (Sweden)

    Xikai Tu

    2017-01-01

    Full Text Available The reach-to-grasp activities play an important role in our daily lives. The developed RUPERT for stroke patients with high stiffness in arm flexor muscles is a low-cost lightweight portable exoskeleton rehabilitation robot whose joints are unidirectionally actuated by pneumatic artificial muscles (PAMs. In order to expand the useful range of RUPERT especially for patients with flaccid paralysis, functional electrical stimulation (FES is taken to activate paralyzed arm muscles. As both the exoskeleton robot driven by PAMs and the neuromuscular skeletal system under FES possess the highly nonlinear and time-varying characteristics, iterative learning control (ILC is studied and is taken to control this newly designed hybrid rehabilitation system for reaching trainings. Hand function rehabilitation refers to grasping. Because of tiny finger muscles, grasping and releasing are realized by FES array electrodes and matrix scan method. By using the surface electromyography (EMG technique, the subject’s active intent is identified. The upper limb rehabilitation robot powered by PAMs cooperates with FES arrays to realize active reach-to-grasp trainings, which was verified through experiments.

  4. The text of the third agreement to extend the regional co-operative agreement for research, development and training related to nuclear science and technology of 1972

    International Nuclear Information System (INIS)

    1987-09-01

    The full text of the third agreement to extend the regional co-operative agreement for research, development and training related to nuclear science and technology of 1972 (INFCIRC/167) (extended first in 1977 and then in 1982) for a further period of five years with effect from 12 June 1987, is reproduced

  5. The Text of a Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology. Acceptance of the Agreement by Bangladesh

    International Nuclear Information System (INIS)

    1974-01-01

    On 23 October 1974 the Government of Bangladesh notified the Agency of its acceptance of the Regional Cooperative Agreement for Research, Development and Training Related to Nuclear Science and Technology between the Agency and Member States, in accordance with Section 9 thereof. Pursuant to Section 10, the Agreement consequently entered into force with respect to the Government of Bangladesh on that date

  6. The Text of the Third Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology of 1972

    International Nuclear Information System (INIS)

    1987-09-01

    The text of the Third Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology of 1972 the RCA Agreement, extended first in 1977 and then in 1982, for a further period of five years with effect from 12 June 1987, is reproduced herein for the information of all Members [fr

  7. The Text of a Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology. Latest Status. Declarations/Reservations

    International Nuclear Information System (INIS)

    1972-01-01

    The text of a Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology between the Agency and Member States is reproduced herein for the information of all Members. Section 9 thereof specifies the Members that may become party to it [es

  8. Competitive versus Cooperative Exergame Play for African American Adolescents' Executive Function Skills: Short-Term Effects in a Long-Term Training Intervention

    Science.gov (United States)

    Staiano, Amanda E.; Abraham, Anisha A.; Calvert, Sandra L.

    2012-01-01

    Exergames are videogames that require gross motor activity, thereby combining gaming with physical activity. This study examined the role of competitive versus cooperative exergame play on short-term changes in executive function skills, following a 10-week exergame training intervention. Fifty-four low-income overweight and obese African American…

  9. The Text of a Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology. Latest Status. Declarations/Reservations

    International Nuclear Information System (INIS)

    1972-01-01

    The text of a Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology between the Agency and Member States is reproduced herein for the information of all Members. Section 9 thereof specifies the Members that may become party to it

  10. The text of the second agreement to extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology

    International Nuclear Information System (INIS)

    1998-03-01

    The document reproduces the text of the Second Agreement to Extend the 1987 Regional Co-operative Agreement for Research, development and Training Related to Nuclear Science and Technology for a further period of five years with effect from 12 june 1997, i.e., through 11 June 2002

  11. The Text of a Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology. Latest Status. Declarations/Reservations

    International Nuclear Information System (INIS)

    1972-01-01

    The text of a Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology between the Agency and Member States is reproduced herein for the information of all Members. Section 9 thereof specifies the Members that may become party to it [fr

  12. The Text of the Second Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology of 1972

    International Nuclear Information System (INIS)

    1982-12-01

    The text of the Second Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology of 1972 the RCA Agreement, fist extended in 1977, for a further period of five years with effect from 12 June 1982, is reproduced herein for the information of all Members

  13. Neural responses in the primary auditory cortex of freely behaving cats while discriminating fast and slow click-trains.

    Science.gov (United States)

    Dong, Chao; Qin, Ling; Liu, Yongchun; Zhang, Xinan; Sato, Yu

    2011-01-01

    Repeated acoustic events are ubiquitous temporal features of natural sounds. To reveal the neural representation of the sound repetition rate, a number of electrophysiological studies have been conducted on various mammals and it has been proposed that both the spike-time and firing rate of primary auditory cortex (A1) neurons encode the repetition rate. However, previous studies rarely examined how the experimental animals perceive the difference in the sound repetition rate, and a caveat to these experiments is that they compared physiological data obtained from animals with psychophysical data obtained from humans. In this study, for the first time, we directly investigated acoustic perception and the underlying neural mechanisms in the same experimental animal by examining spike activities in the A1 of free-moving cats while performing a Go/No-go task to discriminate the click-trains at different repetition rates (12.5-200 Hz). As reported by previous studies on passively listening animals, A1 neurons showed both synchronized and non-synchronized responses to the click-trains. We further found that the neural performance estimated from the precise temporal information of synchronized units was good enough to distinguish all 16.7-200 Hz from the 12.5 Hz repetition rate; however, the cats showed declining behavioral performance with the decrease of the target repetition rate, indicating an increase of difficulty in discriminating two slower click-trains. Such behavioral performance was well explained by the firing rate of some synchronized and non-synchronized units. Trial-by-trial analysis indicated that A1 activity was not affected by the cat's judgment of behavioral response. Our results suggest that the main function of A1 is to effectively represent temporal signals using both spike timing and firing rate, while the cats may read out the rate-coding information to perform the task in this experiment.

  14. Neural responses in the primary auditory cortex of freely behaving cats while discriminating fast and slow click-trains.

    Directory of Open Access Journals (Sweden)

    Chao Dong

    Full Text Available Repeated acoustic events are ubiquitous temporal features of natural sounds. To reveal the neural representation of the sound repetition rate, a number of electrophysiological studies have been conducted on various mammals and it has been proposed that both the spike-time and firing rate of primary auditory cortex (A1 neurons encode the repetition rate. However, previous studies rarely examined how the experimental animals perceive the difference in the sound repetition rate, and a caveat to these experiments is that they compared physiological data obtained from animals with psychophysical data obtained from humans. In this study, for the first time, we directly investigated acoustic perception and the underlying neural mechanisms in the same experimental animal by examining spike activities in the A1 of free-moving cats while performing a Go/No-go task to discriminate the click-trains at different repetition rates (12.5-200 Hz. As reported by previous studies on passively listening animals, A1 neurons showed both synchronized and non-synchronized responses to the click-trains. We further found that the neural performance estimated from the precise temporal information of synchronized units was good enough to distinguish all 16.7-200 Hz from the 12.5 Hz repetition rate; however, the cats showed declining behavioral performance with the decrease of the target repetition rate, indicating an increase of difficulty in discriminating two slower click-trains. Such behavioral performance was well explained by the firing rate of some synchronized and non-synchronized units. Trial-by-trial analysis indicated that A1 activity was not affected by the cat's judgment of behavioral response. Our results suggest that the main function of A1 is to effectively represent temporal signals using both spike timing and firing rate, while the cats may read out the rate-coding information to perform the task in this experiment.

  15. Identification of Abnormal System Noise Temperature Patterns in Deep Space Network Antennas Using Neural Network Trained Fuzzy Logic

    Science.gov (United States)

    Lu, Thomas; Pham, Timothy; Liao, Jason

    2011-01-01

    This paper presents the development of a fuzzy logic function trained by an artificial neural network to classify the system noise temperature (SNT) of antennas in the NASA Deep Space Network (DSN). The SNT data were classified into normal, marginal, and abnormal classes. The irregular SNT pattern was further correlated with link margin and weather data. A reasonably good correlation is detected among high SNT, low link margin and the effect of bad weather; however we also saw some unexpected non-correlations which merit further study in the future.

  16. Cooperation of deterministic dynamics and random noise in production of complex syntactical avian song sequences: a neural network model

    Directory of Open Access Journals (Sweden)

    Yuichi eYamashita

    2011-04-01

    Full Text Available How the brain learns and generates temporal sequences is a fundamental issue in neuroscience. The production of birdsongs, a process which involves complex learned sequences, provides researchers with an excellent biological model for this topic. The Bengalese finch in particular learns a highly complex song with syntactical structure. The nucleus HVC (HVC, a premotor nucleus within the avian song system, plays a key role in generating the temporal structures of their songs. From lesion studies, the nucleus interfacialis (NIf projecting to the HVC is considered one of the essential regions that contribute to the complexity of their songs. However, the types of interaction between the HVC and the NIf that can produce complex syntactical songs remain unclear. In order to investigate the function of interactions between the HVC and NIf, we have proposed a neural network model based on previous biological evidence. The HVC is modeled by a recurrent neural network (RNN that learns to generate temporal patterns of songs. The NIf is modeled as a mechanism that provides auditory feedback to the HVC and generates random noise that feeds into the HVC. The model showed that complex syntactical songs can be replicated by simple interactions between deterministic dynamics of the RNN and random noise. In the current study, the plausibility of the model is tested by the comparison between the changes in the songs of actual birds induced by pharmacological inhibition of the NIf and the changes in the songs produced by the model resulting from modification of parameters representing NIf functions. The efficacy of the model demonstrates that the changes of songs induced by pharmacological inhibition of the NIf can be interpreted as a trade-off between the effects of noise and the effects of feedback on the dynamics of the RNN of the HVC. These facts suggest that the current model provides a convincing hypothesis for the functional role of NIf-HVC interaction.

  17. Distributed Virtual Reality: System Concepts for Cooperative Training and Commanding in Virtual Worlds

    Directory of Open Access Journals (Sweden)

    Eckhard Freund

    2003-02-01

    Full Text Available The general aim of the development of virtual reality technology for automation applications at the IRF is to provide the framework for Projective Virtual Reality which allows users to "project" their actions in the virtual world into the real world primarily by means of robots but also by other means of automation. The framework is based on a new task-oriented approach which builds on the "task deduction" capabilities of a newly developed virtual reality system and a task planning component. The advantage of this new approach is that robots which work at great distances from the control station can be controlled as easily and intuitively as robots that work right next to the control station. Robot control technology now provides the user in the virtual world with a "prolonged arm" into the physical environment, thus paving the way for a new quality of userfriendly man machine interfaces for automation applications. Lately, this work has been enhanced by a new structure that allows to distribute the virtual reality application over multiple computers. With this new step, it is now possible for multiple users to work together in the same virtual room, although they may physically be thousands of miles apart. They only need an Internet or ISDN connection to share this new experience. Last but not least, the distribution technology has been further developed to not just allow users to cooperate but to be able to run the virtual world on many synchronized PCs so that a panorama projection or even a cave can be run with 10 synchronized PCs instead of high-end workstations, thus cutting down the costs for such a visualization environment drastically and allowing for a new range of applications.

  18. Training the brain: practical applications of neural plasticity from the intersection of cognitive neuroscience, developmental psychology, and prevention science.

    Science.gov (United States)

    Bryck, Richard L; Fisher, Philip A

    2012-01-01

    Prior researchers have shown that the brain has a remarkable ability for adapting to environmental changes. The positive effects of such neural plasticity include enhanced functioning in specific cognitive domains and shifts in cortical representation following naturally occurring cases of sensory deprivation; however, maladaptive changes in brain function and development owing to early developmental adversity and stress have also been well documented. Researchers examining enriched rearing environments in animals have revealed the potential for inducing positive brain plasticity effects and have helped to popularize methods for training the brain to reverse early brain deficits or to boost normal cognitive functioning. In this article, two classes of empirically based methods of brain training in children are reviewed and critiqued: laboratory-based, mental process training paradigms and ecological interventions based upon neurocognitive conceptual models. Given the susceptibility of executive function disruption, special attention is paid to training programs that emphasize executive function enhancement. In addition, a third approach to brain training, aimed at tapping into compensatory processes, is postulated. Study results showing the effectiveness of this strategy in the field of neurorehabilitation and in terms of naturally occurring compensatory processing in human aging lend credence to the potential of this approach. (PsycINFO Database Record (c) 2012 APA, all rights reserved).

  19. Cooperation with Emerging Countries in Advanced Mining Training Programmes Involving an Industrial Partner

    Energy Technology Data Exchange (ETDEWEB)

    Ahmadzadeh, H., E-mail: Hossein.Ahmadzadeh@ema.fr [CESMAT, CESSEM, Alès (France); Petitclerc, J-L. [AREVA NC, Paris (France)

    2014-05-15

    After about 20 years at a low level of activity the global uranium mining industry has been enjoying a significant expansion since about 2003. However, it is apparent that the “quiet” period has led to a shortage of new staff coming into the industry, many middle ranking and skilled professionals have moved to other industries and many of the remaining staff is fast approaching retirement. Many organizations are looking at ways to address this situation as quickly and effectively as possible, including governments, industry and the IAEA. This paper describes one training programme that has been developed, and is currently being implemented, as a joint venture between the uranium mining company AREVA NC and the Centre for Advanced Studies of Mineral Resources, which is located at the School of Mines in Ales, France. (author)

  20. Dynamics and spike trains statistics in conductance-based integrate-and-fire neural networks with chemical and electric synapses

    International Nuclear Information System (INIS)

    Cofré, Rodrigo; Cessac, Bruno

    2013-01-01

    We investigate the effect of electric synapses (gap junctions) on collective neuronal dynamics and spike statistics in a conductance-based integrate-and-fire neural network, driven by Brownian noise, where conductances depend upon spike history. We compute explicitly the time evolution operator and show that, given the spike-history of the network and the membrane potentials at a given time, the further dynamical evolution can be written in a closed form. We show that spike train statistics is described by a Gibbs distribution whose potential can be approximated with an explicit formula, when the noise is weak. This potential form encompasses existing models for spike trains statistics analysis such as maximum entropy models or generalized linear models (GLM). We also discuss the different types of correlations: those induced by a shared stimulus and those induced by neurons interactions

  1. Training spiking neural networks to associate spatio-temporal input-output spike patterns

    OpenAIRE

    Mohemmed, A; Schliebs, S; Matsuda, S; Kasabov, N

    2013-01-01

    In a previous work (Mohemmed et al., Method for training a spiking neuron to associate input–output spike trains) [1] we have proposed a supervised learning algorithm based on temporal coding to train a spiking neuron to associate input spatiotemporal spike patterns to desired output spike patterns. The algorithm is based on the conversion of spike trains into analogue signals and the application of the Widrow–Hoff learning rule. In this paper we present a mathematical formulation of the prop...

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

    Directory of Open Access Journals (Sweden)

    Ángel Gutiérrez

    2015-04-01

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

  3. Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models.

    Science.gov (United States)

    Karimi, Davood; Samei, Golnoosh; Kesch, Claudia; Nir, Guy; Salcudean, Septimiu E

    2018-05-15

    Most of the existing convolutional neural network (CNN)-based medical image segmentation methods are based on methods that have originally been developed for segmentation of natural images. Therefore, they largely ignore the differences between the two domains, such as the smaller degree of variability in the shape and appearance of the target volume and the smaller amounts of training data in medical applications. We propose a CNN-based method for prostate segmentation in MRI that employs statistical shape models to address these issues. Our CNN predicts the location of the prostate center and the parameters of the shape model, which determine the position of prostate surface keypoints. To train such a large model for segmentation of 3D images using small data (1) we adopt a stage-wise training strategy by first training the network to predict the prostate center and subsequently adding modules for predicting the parameters of the shape model and prostate rotation, (2) we propose a data augmentation method whereby the training images and their prostate surface keypoints are deformed according to the displacements computed based on the shape model, and (3) we employ various regularization techniques. Our proposed method achieves a Dice score of 0.88, which is obtained by using both elastic-net and spectral dropout for regularization. Compared with a standard CNN-based method, our method shows significantly better segmentation performance on the prostate base and apex. Our experiments also show that data augmentation using the shape model significantly improves the segmentation results. Prior knowledge about the shape of the target organ can improve the performance of CNN-based segmentation methods, especially where image features are not sufficient for a precise segmentation. Statistical shape models can also be employed to synthesize additional training data that can ease the training of large CNNs.

  4. A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems.

    Science.gov (United States)

    Kuntanapreeda, S; Fullmer, R R

    1996-01-01

    A training method for a class of neural network controllers is presented which guarantees closed-loop system stability. The controllers are assumed to be nonlinear, feedforward, sampled-data, full-state regulators implemented as single hidden-layer neural networks. The controlled systems must be locally hermitian and observable. Stability of the closed-loop system is demonstrated by determining a Lyapunov function, which can be used to identify a finite stability region about the regulator point.

  5. SU-F-E-09: Respiratory Signal Prediction Based On Multi-Layer Perceptron Neural Network Using Adjustable Training Samples

    Energy Technology Data Exchange (ETDEWEB)

    Sun, W; Jiang, M; Yin, F [Duke University Medical Center, Durham, NC (United States)

    2016-06-15

    Purpose: Dynamic tracking of moving organs, such as lung and liver tumors, under radiation therapy requires prediction of organ motions prior to delivery. The shift of moving organ may change a lot due to huge transform of respiration at different periods. This study aims to reduce the influence of that changes using adjustable training signals and multi-layer perceptron neural network (ASMLP). Methods: Respiratory signals obtained using a Real-time Position Management(RPM) device were used for this study. The ASMLP uses two multi-layer perceptron neural networks(MLPs) to infer respiration position alternately and the training sample will be updated with time. Firstly, a Savitzky-Golay finite impulse response smoothing filter was established to smooth the respiratory signal. Secondly, two same MLPs were developed to estimate respiratory position from its previous positions separately. Weights and thresholds were updated to minimize network errors according to Leverberg-Marquart optimization algorithm through backward propagation method. Finally, MLP 1 was used to predict 120∼150s respiration position using 0∼120s training signals. At the same time, MLP 2 was trained using 30∼150s training signals. Then MLP is used to predict 150∼180s training signals according to 30∼150s training signals. The respiration position is predicted as this way until it was finished. Results: In this experiment, the two methods were used to predict 2.5 minute respiratory signals. For predicting 1s ahead of response time, correlation coefficient was improved from 0.8250(MLP method) to 0.8856(ASMLP method). Besides, a 30% improvement of mean absolute error between MLP(0.1798 on average) and ASMLP(0.1267 on average) was achieved. For predicting 2s ahead of response time, correlation coefficient was improved from 0.61415 to 0.7098.Mean absolute error of MLP method(0.3111 on average) was reduced by 35% using ASMLP method(0.2020 on average). Conclusion: The preliminary results

  6. International Cooperation in Nuclear E&T: On the Way to Nuclear Training Harmonization

    International Nuclear Information System (INIS)

    Filipev, I.; Karmanov, F.; Artisyuk, V.; Karezin, V.; Sushkov, P.

    2016-01-01

    Full text: Global use of nuclear power is likely to continue to grow in the coming decades. Some countries have chosen to invite multiple vendors for NPP technology supply. The worldwide expansion of nuclear power use and the multi-vendor paradigm inevitably lead to the need of harmonized approaches towards safety and the initial step here is harmonization of education and training (E&T) efforts between recipient and vendor countries and between vendors as well. Establishing international and regional E&T networks is the vital mechanism of the harmonization. The present paper gives an example of collaboration between Russia and the EU through achievements of ENEN-RU projects aimed at harmonization of E&T efforts in nuclear field. One of the goals of this activity is to introduce double-degree programmes in nuclear engineering in Russian and EU universities. To support this initiative ROSATOM-CICE&T is currently developing multimedia-based fundamental educational courses in Russian and English languages. The courses will be also used as the backbone for new nuclear engineering programmes in the universities of newcomer states. To provide a harmonized development of operating personnel career trajectories in these countries an applied bachelor programme for operating personnel has been developed. (author

  7. EUROSUNMED. Euro-Mediterranean cooperation on research and training in sun based renewable energies

    International Nuclear Information System (INIS)

    Slaoui, Abdelilah

    2013-01-01

    Here we present the different aspects of the EUROSUNMED project. The scientific targets of EUROSUNMED are the development of new technologies in three energy field areas, namely photovoltaics (PV), concentrated solar power (CSP) and grid integration (GI), in strong collaboration with research institutes, universities and SMSs from Europe in the north side of the Mediterranean sea and from Morocco and Egypt from the south of the sea. the focus in PV will be on thin film (Si, CZTS) based solar cells and modules while the goal in CSP field is to design and test new heliostats as well as novel solutions for energy storage compatible with these technologies. The project aims at producing components that will be tested under specific conditions of MPC (hot climate, absence of water, etc.). Such investigations are complemented with studies on grid integration of energy sources from PV and CSP in Morocco and Egypt context. Additionally, the consortium envisages training PhD students and post-docs in these interdisciplinary fields (chemistry, physics, materials science) in a close and fruitful collaboration between academic institutions and industry from EU and MPCs. The consortium is well placed around leading academic groups in materials science and engineering devices and equipments for the development of PV and CSP, and also in the promotion of the renewable energies in general. Moreover, technology transfer and research infrastructure development in the targeted areas will be provided. Disseminating the results of the projects will be done through the organization of summer schools and stakeholders involved in the 3 selected energy area and beyond. Another outreach of the project will be the proposal for a roadmap on the technological aspects (research, industry, implementation) of the PV, CSP and grid area as well as on the best practice for the continuation of strong collaboration between the EU and MPCS partners and beyond for mutual interest. (author)

  8. Demonstration of Self-Training Autonomous Neural Networks in Space Vehicle Docking Simulations

    Science.gov (United States)

    Patrick, M. Clinton; Thaler, Stephen L.; Stevenson-Chavis, Katherine

    2006-01-01

    Neural Networks have been under examination for decades in many areas of research, with varying degrees of success and acceptance. Key goals of computer learning, rapid problem solution, and automatic adaptation have been elusive at best. This paper summarizes efforts at NASA's Marshall Space Flight Center harnessing such technology to autonomous space vehicle docking for the purpose of evaluating applicability to future missions.

  9. Self-consistent determination of the spike-train power spectrum in a neural network with sparse connectivity

    Directory of Open Access Journals (Sweden)

    Benjamin eDummer

    2014-09-01

    Full Text Available A major source of random variability in cortical networks is the quasi-random arrival of presynaptic action potentials from many other cells. In network studies as well as in the study of the response properties of single cells embedded in a network, synaptic background input is often approximated by Poissonian spike trains. However, the output statistics of the cells is in most cases far from being Poisson. This is inconsistent with the assumption of similar spike-train statistics for pre- and postsynaptic cells in a recurrent network. Here we tackle this problem for the popular class of integrate-and-fire neurons and study a self-consistent statistics of input and output spectra of neural spike trains. Instead of actually using a large network, we use an iterative scheme, in which we simulate a single neuron over several generations. In each of these generations, the neuron is stimulated with surrogate stochastic input that has a similar statistics as the output of the previous generation. For the surrogate input, we employ two distinct approximations: (i a superposition of renewal spike trains with the same interspike interval density as observed in the previous generation and (ii a Gaussian current with a power spectrum proportional to that observed in the previous generation. For input parameters that correspond to balanced input in the network, both the renewal and the Gaussian iteration procedure converge quickly and yield comparable results for the self-consistent spike-train power spectrum. We compare our results to large-scale simulations of a random sparsely connected network of leaky integrate-and-fire neurons (Brunel, J. Comp. Neurosci. 2000 and show that in the asynchronous regime close to a state of balanced synaptic input from the network, our iterative schemes provide excellent approximations to the autocorrelation of spike trains in the recurrent network.

  10. Human-robot cooperative movement training: Learning a novel sensory motor transformation during walking with robotic assistance-as-needed

    Directory of Open Access Journals (Sweden)

    Benitez Raul

    2007-03-01

    Full Text Available Abstract Background A prevailing paradigm of physical rehabilitation following neurologic injury is to "assist-as-needed" in completing desired movements. Several research groups are attempting to automate this principle with robotic movement training devices and patient cooperative algorithms that encourage voluntary participation. These attempts are currently not based on computational models of motor learning. Methods Here we assume that motor recovery from a neurologic injury can be modelled as a process of learning a novel sensory motor transformation, which allows us to study a simplified experimental protocol amenable to mathematical description. Specifically, we use a robotic force field paradigm to impose a virtual impairment on the left leg of unimpaired subjects walking on a treadmill. We then derive an "assist-as-needed" robotic training algorithm to help subjects overcome the virtual impairment and walk normally. The problem is posed as an optimization of performance error and robotic assistance. The optimal robotic movement trainer becomes an error-based controller with a forgetting factor that bounds kinematic errors while systematically reducing its assistance when those errors are small. As humans have a natural range of movement variability, we introduce an error weighting function that causes the robotic trainer to disregard this variability. Results We experimentally validated the controller with ten unimpaired subjects by demonstrating how it helped the subjects learn the novel sensory motor transformation necessary to counteract the virtual impairment, while also preventing them from experiencing large kinematic errors. The addition of the error weighting function allowed the robot assistance to fade to zero even though the subjects' movements were variable. We also show that in order to assist-as-needed, the robot must relax its assistance at a rate faster than that of the learning human. Conclusion The assist

  11. Human-robot cooperative movement training: learning a novel sensory motor transformation during walking with robotic assistance-as-needed.

    Science.gov (United States)

    Emken, Jeremy L; Benitez, Raul; Reinkensmeyer, David J

    2007-03-28

    A prevailing paradigm of physical rehabilitation following neurologic injury is to "assist-as-needed" in completing desired movements. Several research groups are attempting to automate this principle with robotic movement training devices and patient cooperative algorithms that encourage voluntary participation. These attempts are currently not based on computational models of motor learning. Here we assume that motor recovery from a neurologic injury can be modelled as a process of learning a novel sensory motor transformation, which allows us to study a simplified experimental protocol amenable to mathematical description. Specifically, we use a robotic force field paradigm to impose a virtual impairment on the left leg of unimpaired subjects walking on a treadmill. We then derive an "assist-as-needed" robotic training algorithm to help subjects overcome the virtual impairment and walk normally. The problem is posed as an optimization of performance error and robotic assistance. The optimal robotic movement trainer becomes an error-based controller with a forgetting factor that bounds kinematic errors while systematically reducing its assistance when those errors are small. As humans have a natural range of movement variability, we introduce an error weighting function that causes the robotic trainer to disregard this variability. We experimentally validated the controller with ten unimpaired subjects by demonstrating how it helped the subjects learn the novel sensory motor transformation necessary to counteract the virtual impairment, while also preventing them from experiencing large kinematic errors. The addition of the error weighting function allowed the robot assistance to fade to zero even though the subjects' movements were variable. We also show that in order to assist-as-needed, the robot must relax its assistance at a rate faster than that of the learning human. The assist-as-needed algorithm proposed here can limit error during the learning of a

  12. Endurance training in mild hypertension - effects on ambulatory blood pressure and neural circulatory control.

    Science.gov (United States)

    Narkiewicz; Somers

    1997-10-01

    This review examines the effects of a single bout of exercise and of endurance training on blood pressure in patients with hypertension. Possible autonomic mechanisms that mediate these changes in blood pressure are reviewed briefly. Blood pressure rises during exercise. During the second half hour after exercise blood pressure is lower. This p;ost-exercise reduction in blood pressure is associated with a decrease in muscle sympathetic nerve activity, an increase in baroreflex gain and a reduction in the level of blood pressure (set point) at which baroreflex activation occurs. The post-exercise fall in blood pressure appears to be limited to several hours and is not likely to explain any chronic reduction in blood pressure from endurance training. Endurance training elicits modest (approximately 4-5 mmHg) reductions in blood pressure. Because of the intrinsic variability of blood pressure, the decreases in blood pressure after endurance training is evident, especially when multiple measurements of blood pressure are obtained. Studies using 24 h blood pressure measurements suggest that, although endurance training lowers daytime blood pressure, blood pressure during sleep remains unchanged. The mechanism underlying the reduction in blood pressure in endurance training is not known. Although physical fitness is known to attenuate the sympathetic response to acute exercise, whether resting sympathetic drive is decreased with endurance training remains controversial. The slowing of heart rate that accompanies endurance training is also associated with an increase in variability of heart rate. The slower heart rate, increased variability of heart rate and lower blood pressure after endurance training are accompanied by an increase in baroreflex sensitivity. Even though the antihypertensive effect of endurance training is modest, the favourable effects of physical fitness on other risk factors for cardiovascular disease make exercise training an important approach in

  13. Neural correlates of accelerated auditory processing in children engaged in music training.

    Science.gov (United States)

    Habibi, Assal; Cahn, B Rael; Damasio, Antonio; Damasio, Hanna

    2016-10-01

    Several studies comparing adult musicians and non-musicians have shown that music training is associated with brain differences. It is unknown, however, whether these differences result from lengthy musical training, from pre-existing biological traits, or from social factors favoring musicality. As part of an ongoing 5-year longitudinal study, we investigated the effects of a music training program on the auditory development of children, over the course of two years, beginning at age 6-7. The training was group-based and inspired by El-Sistema. We compared the children in the music group with two comparison groups of children of the same socio-economic background, one involved in sports training, another not involved in any systematic training. Prior to participating, children who began training in music did not differ from those in the comparison groups in any of the assessed measures. After two years, we now observe that children in the music group, but not in the two comparison groups, show an enhanced ability to detect changes in tonal environment and an accelerated maturity of auditory processing as measured by cortical auditory evoked potentials to musical notes. Our results suggest that music training may result in stimulus specific brain changes in school aged children. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

  14. A neural-symbolic system for automated assessment in training simulators - A position paper

    NARCIS (Netherlands)

    Penning, H.L.H. de; Kappé, B.; Bosch, K. van den

    2009-01-01

    Performance assessment in training simulators is a complex task. It requires monitoring and interpreting the student’s behaviour in the simulator using knowledge of the training task, the environment and a lot of experience. Assessment in simulators is therefore generally done by human observers. To

  15. Strength training reduces arterial blood pressure but not sympathetic neural activity in young normotensive subjects

    Science.gov (United States)

    Carter, Jason R.; Ray, Chester A.; Downs, Emily M.; Cooke, William H.

    2003-01-01

    The effects of resistance training on arterial blood pressure and muscle sympathetic nerve activity (MSNA) at rest have not been established. Although endurance training is commonly recommended to lower arterial blood pressure, it is not known whether similar adaptations occur with resistance training. Therefore, we tested the hypothesis that whole body resistance training reduces arterial blood pressure at rest, with concomitant reductions in MSNA. Twelve young [21 +/- 0.3 (SE) yr] subjects underwent a program of whole body resistance training 3 days/wk for 8 wk. Resting arterial blood pressure (n = 12; automated sphygmomanometer) and MSNA (n = 8; peroneal nerve microneurography) were measured during a 5-min period of supine rest before and after exercise training. Thirteen additional young (21 +/- 0.8 yr) subjects served as controls. Resistance training significantly increased one-repetition maximum values in all trained muscle groups (P < 0.001), and it significantly decreased systolic (130 +/- 3 to 121 +/- 2 mmHg; P = 0.01), diastolic (69 +/- 3 to 61 +/- 2 mmHg; P = 0.04), and mean (89 +/- 2 to 81 +/- 2 mmHg; P = 0.01) arterial blood pressures at rest. Resistance training did not affect MSNA or heart rate. Arterial blood pressures and MSNA were unchanged, but heart rate increased after 8 wk of relative inactivity for subjects in the control group (61 +/- 2 to 67 +/- 3 beats/min; P = 0.01). These results indicate that whole body resistance exercise training might decrease the risk for development of cardiovascular disease by lowering arterial blood pressure but that reductions of pressure are not coupled to resistance exercise-induced decreases of sympathetic tone.

  16. The text of an African regional co-operative agreement for research, development and training related to nuclear science and technology

    International Nuclear Information System (INIS)

    1993-02-01

    The document informs that as of 31 January 1993, the following states sent to the Director General notifications of acceptance of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology: Tunisia, Egypt, Algeria, Nigeria, Madagascar, Libyan Arab Jamahiriya, Morocco, Kenya, Sudan, Ghana, Tanzania, Mauritius, Cameroon, South Africa and Zaire. The Agreement entered into force on 4 April 1990

  17. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    International Nuclear Information System (INIS)

    1998-01-01

    The document presents the status of acceptances as of 21 September 1998 of the extension of the African Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) which entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  18. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    International Nuclear Information System (INIS)

    1999-01-01

    The document presents the status of acceptances as of 16 March 1999 of the extension of the African Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) which entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000. There are 25 States which notified the acceptance of the Agreement extension

  19. The text of the agreement to extend the regional co-operative agreement for research, development and training related to nuclear science and technology, 1987

    International Nuclear Information System (INIS)

    1992-09-01

    The document reproduces the text of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 1987, for a further period of five years with effect from 12 June 1992. Australia, Bangladesh, the People's Republic of China, India, Indonesia, Japan, the Republic of Korea, Malaysia, Pakistan, the Philippines, Singapore, Sri Lanka, Thailand and Viet Nam are parties of this Agreement

  20. Extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1999-11-23

    The document presents the status of acceptances as of 6 October 1999 of the extension of the African Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) which entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000. There are 26 States which notified the acceptance of the Agreement extension.

  1. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1999-04-19

    The document presents the status of acceptances as of 16 March 1999 of the extension of the African Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) which entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000. There are 25 States which notified the acceptance of the Agreement extension

  2. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1998-11-13

    The document presents the status of acceptances as of 21 September 1998 of the extension of the African Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) which entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  3. QEEG-based neural correlates of decision making in a well-trained eight year-old chess player.

    Science.gov (United States)

    Alipour, Abolfazl; Seifzadeh, Sahar; Aligholi, Hadi; Nami, Mohammad

    2017-10-25

    The neurocognitive substrates of decision making (DM) in the context of chess has appealed to researchers' interest for decades. Expert and beginner chess players are hypothesized to employ different brain functional networks when involved in episodes of critical DM upon chess. Cognitive capacities including, but not restricted to pattern recognition, visuospatial search, reasoning, planning and DM are perhaps the key determinants of rewarding and judgmental decisions in chess. Meanwhile, the precise neural correlates of DM in this context has largely remained elusive. The quantitative electroencephalography (QEEG) is an investigation tool possessing a proper temporal resolution in the study of neural correlates of cognitive tasks at cortical level. Here, we used a 22-channel EEG setup and digital polygraphy in a well-trained 8 year-old boy while engaged in playing chess against the computer. Quantitative analyses were done to map and source-localize the EEG signals. Our analyses indicated a lower power spectral density (PSD) for higher frequency bands in the right hemisphere upon DM-related epochs. Moreover, the information flow upon DM blocks in this particular case was more of posterior towards anterior brain regions.

  4. Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods

    Directory of Open Access Journals (Sweden)

    Mahesh Jangid

    2018-02-01

    Full Text Available Handwritten character recognition is currently getting the attention of researchers because of possible applications in assisting technology for blind and visually impaired users, human–robot interaction, automatic data entry for business documents, etc. In this work, we propose a technique to recognize handwritten Devanagari characters using deep convolutional neural networks (DCNN which are one of the recent techniques adopted from the deep learning community. We experimented the ISIDCHAR database provided by (Information Sharing Index ISI, Kolkata and V2DMDCHAR database with six different architectures of DCNN to evaluate the performance and also investigate the use of six recently developed adaptive gradient methods. A layer-wise technique of DCNN has been employed that helped to achieve the highest recognition accuracy and also get a faster convergence rate. The results of layer-wise-trained DCNN are favorable in comparison with those achieved by a shallow technique of handcrafted features and standard DCNN.

  5. Nonlinear System Identification Using Neural Networks Trained with Natural Gradient Descent

    Directory of Open Access Journals (Sweden)

    Ibnkahla Mohamed

    2003-01-01

    Full Text Available We use natural gradient (NG learning neural networks (NNs for modeling and identifying nonlinear systems with memory. The nonlinear system is comprised of a discrete-time linear filter followed by a zero-memory nonlinearity . The NN model is composed of a linear adaptive filter followed by a two-layer memoryless nonlinear NN. A Kalman filter-based technique and a search-and-converge method have been employed for the NG algorithm. It is shown that the NG descent learning significantly outperforms the ordinary gradient descent and the Levenberg-Marquardt (LM procedure in terms of convergence speed and mean squared error (MSE performance.

  6. The effects of inhibitory control training for preschoolers on reasoning ability and neural activity

    DEFF Research Database (Denmark)

    Liu, Qian; Zhu, Xinyi; Ziegler, Albert

    2015-01-01

    Inhibitory control (including response inhibition and interference control) develops rapidly during the preschool period and is important for early cognitive development. This study aimed to determine the training and transfer effects on response inhibition in young children. Children....../week, for 3 weeks. Several cognitive tasks (involving inhibitory control, working memory, and fluid intelligence) were used to evaluate the transfer effects, and electroencephalography (EEG) was performed during a go/no-go task. Progress on the trained game was significant, while performance on a reasoning...

  7. The Text of the Third Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology (RCA). Latest Status. Extension of Agreement

    International Nuclear Information System (INIS)

    2002-01-01

    The text of the Third Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, t he 1987 RCA , is reproduced herein for the information of all Members [es

  8. The Text of the Fifth Agreement to Extend the 1987 Regional Cooperative Agreement for Research, Development and Training Related to Nuclear Science and Technology (RCA). Extension of Agreement. Latest Status

    International Nuclear Information System (INIS)

    2012-01-01

    The Text of the Fifth Agreement to Extend the 1987 Regional Cooperative Agreement for Research, Development and Training Related to Nuclear Science and Technology (RCA). Extension of Agreement. Latest Status [es

  9. The Text of the Fourth Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology (RCA). Extension of Agreement. Latest Status

    International Nuclear Information System (INIS)

    2007-01-01

    The text of the Fourth Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 'the 1987 RCA', is reproduced herein for the information of all Members [es

  10. The Text of the Fourth Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology (RCA). Extension of Agreement. Latest Status

    International Nuclear Information System (INIS)

    2007-01-01

    The text of the Fourth Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 'the 1987 RCA', is reproduced herein for the information of all Members

  11. The text of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 1987. Status of acceptances as of 28 February 1993

    International Nuclear Information System (INIS)

    1993-04-01

    The document gives the status of acceptances as of 28 February 1993 of the agreement to extend regional co-operative agreement for research, development and training related to nuclear science and technology from 1987

  12. Cognitive and Neural Effects of Vision-Based Speed-of-Processing Training in Older Adults with Amnestic Mild Cognitive Impairment: A Pilot Study.

    Science.gov (United States)

    Lin, Feng; Heffner, Kathi L; Ren, Ping; Tivarus, Madalina E; Brasch, Judith; Chen, Ding-Geng; Mapstone, Mark; Porsteinsson, Anton P; Tadin, Duje

    2016-06-01

    To examine the cognitive and neural effects of vision-based speed-of-processing (VSOP) training in older adults with amnestic mild cognitive impairment (aMCI) and contrast those effects with an active control (mental leisure activities (MLA)). Randomized single-blind controlled pilot trial. Academic medical center. Individuals with aMCI (N = 21). Six-week computerized VSOP training. Multiple cognitive processing measures, instrumental activities of daily living (IADLs), and two resting state neural networks regulating cognitive processing: central executive network (CEN) and default mode network (DMN). VSOP training led to significantly greater improvements in trained (processing speed and attention: F1,19  = 6.61, partial η(2)  = 0.26, P = .02) and untrained (working memory: F1,19  = 7.33, partial η(2)  = 0.28, P = .01; IADLs: F1,19  = 5.16, partial η(2)  = 0.21, P = .03) cognitive domains than MLA and protective maintenance in DMN (F1, 9  = 14.63, partial η(2)  = 0.62, P = .004). VSOP training, but not MLA, resulted in a significant improvement in CEN connectivity (Z = -2.37, P = .02). Target and transfer effects of VSOP training were identified, and links between VSOP training and two neural networks associated with aMCI were found. These findings highlight the potential of VSOP training to slow cognitive decline in individuals with aMCI. Further delineation of mechanisms underlying VSOP-induced plasticity is necessary to understand in which populations and under what conditions such training may be most effective. © 2016, Copyright the Authors Journal compilation © 2016, The American Geriatrics Society.

  13. An Equal Start: Absence of Group Differences in Cognitive, Social and Neural Measures Prior to Music or Sports Training in Children.

    Directory of Open Access Journals (Sweden)

    Assal eHabibi

    2014-09-01

    Full Text Available Several studies comparing adult musicians and non-musicians have provided compelling evidence for functional and anatomical differences in the brain systems engaged by musical training. It is not known, however, whether those differences result from long term musical training or from pre-existing traits favoring musicality. In an attempt to begin addressing this question, we have launched a longitudinal investigation of the effects of childhood music training on cognitive, social and neural development. We compared a group of 6-7 year old children at the start of intense after-school musical training, with two groups of children: one involved in high intensity sports training but not musical training, another not involved in any systematic training. All children were tested with a comprehensive battery of cognitive, motor, musical, emotional and social assessments and underwent magnetic resonance imaging and electroencephalography. Our first objective was to determine whether children who participate in musical training were different, prior to training, from children in the control groups in terms of cognitive, motor, musical, emotional and social behavior measures as well as in structural and functional brain measures. Our second objective was to determine whether musical skills, as measured by a music perception assessment prior to training, correlates with emotional and social outcome measures that have been shown to be associated with musical training. We found no neural, cognitive, motor, emotional or social differences among the three groups. In addition, there was no correlation between music perception skills and any of the social or emotional measures. These results provide a baseline for an ongoing longitudinal investigation of the effects of music training.

  14. An equal start: absence of group differences in cognitive, social, and neural measures prior to music or sports training in children.

    Science.gov (United States)

    Habibi, Assal; Ilari, Beatriz; Crimi, Kevin; Metke, Michael; Kaplan, Jonas T; Joshi, Anand A; Leahy, Richard M; Shattuck, David W; Choi, So Y; Haldar, Justin P; Ficek, Bronte; Damasio, Antonio; Damasio, Hanna

    2014-01-01

    Several studies comparing adult musicians and non-musicians have provided compelling evidence for functional and anatomical differences in the brain systems engaged by musical training. It is not known, however, whether those differences result from long-term musical training or from pre-existing traits favoring musicality. In an attempt to begin addressing this question, we have launched a longitudinal investigation of the effects of childhood music training on cognitive, social and neural development. We compared a group of 6- to 7-year old children at the start of intense after-school musical training, with two groups of children: one involved in high intensity sports training but not musical training, another not involved in any systematic training. All children were tested with a comprehensive battery of cognitive, motor, musical, emotional, and social assessments and underwent magnetic resonance imaging and electroencephalography. Our first objective was to determine whether children who participate in musical training were different, prior to training, from children in the control groups in terms of cognitive, motor, musical, emotional, and social behavior measures as well as in structural and functional brain measures. Our second objective was to determine whether musical skills, as measured by a music perception assessment prior to training, correlates with emotional and social outcome measures that have been shown to be associated with musical training. We found no neural, cognitive, motor, emotional, or social differences among the three groups. In addition, there was no correlation between music perception skills and any of the social or emotional measures. These results provide a baseline for an ongoing longitudinal investigation of the effects of music training.

  15. Retrieving forest stand parameters from SAR backscatter data using a neural network trained by a canopy backscatter model

    International Nuclear Information System (INIS)

    Wang, Y.; Dong, D.

    1997-01-01

    It was possible to retrieve the stand mean dbh (tree trunk diameter at breast height) and stand density from the Jet Propulsion Laboratory (JPL) Airborne Synthetic Aperture Radar (AIRSAR) backscatter data by using threelayered perceptron neural networks (NNs). Two sets of NNs were trained by the Santa Barbara microwave canopy backscatter model. One set of the trained NNs was used to retrieve the stand mean dbh, and the other to retrieve the stand density. Each set of the NNs consisted of seven individual NNs for all possible combinations of one, two, and three radar wavelengths. Ground and multiple wavelength AIRSAR backscatter data from two ponderosa pine forest stands near Mt. Shasta, California (U.S.A.) were used to evaluate the accuracy of the retrievals. The r.m.s. and relative errors of the retrieval for stand mean dbh were 6.1 cm and 15.6 per cent for one stand (St2), and 3.1 cm and 6.7 per cent for the other stand (St11). The r.m.s. and relative errors of the retrieval for stand density were 71.2 treesha-1 and 23.0 per cent for St2, and 49.7 treesha-1 and 21.3 per cent for St11. (author)

  16. Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images

    Directory of Open Access Journals (Sweden)

    Sivaramakrishnan Rajaraman

    2018-04-01

    Full Text Available Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx methods using machine learning (ML techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI. In contrast, Convolutional Neural Networks (CNN, a class of deep learning (DL models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

  17. User intent prediction with a scaled conjugate gradient trained artificial neural network for lower limb amputees using a powered prosthesis.

    Science.gov (United States)

    Woodward, Richard B; Spanias, John A; Hargrove, Levi J

    2016-08-01

    Powered lower limb prostheses have the ability to provide greater mobility for amputee patients. Such prostheses often have pre-programmed modes which can allow activities such as climbing stairs and descending ramps, something which many amputees struggle with when using non-powered limbs. Previous literature has shown how pattern classification can allow seamless transitions between modes with a high accuracy and without any user interaction. Although accurate, training and testing each subject with their own dependent data is time consuming. By using subject independent datasets, whereby a unique subject is tested against a pooled dataset of other subjects, we believe subject training time can be reduced while still achieving an accurate classification. We present here an intent recognition system using an artificial neural network (ANN) with a scaled conjugate gradient learning algorithm to classify gait intention with user-dependent and independent datasets for six unilateral lower limb amputees. We compare these results against a linear discriminant analysis (LDA) classifier. The ANN was found to have significantly lower classification error (P<;0.05) than LDA with all user-dependent step-types, as well as transitional steps for user-independent datasets. Both types of classifiers are capable of making fast decisions; 1.29 and 2.83 ms for the LDA and ANN respectively. These results suggest that ANNs can provide suitable and accurate offline classification in prosthesis gait prediction.

  18. Modeling of an ionic polymer metal composite actuator based on an extended Kalman filter trained neural network

    International Nuclear Information System (INIS)

    Truong, Dinh Quang; Ahn, Kyoung Kwan

    2014-01-01

    An ion polymer metal composite (IPMC) is an electroactive polymer that bends in response to a small applied electric field as a result of mobility of cations in the polymer network and vice versa. This paper presents an innovative and accurate nonlinear black-box model (NBBM) for estimating the bending behavior of IPMC actuators. The model is constructed via a general multilayer perceptron neural network (GMLPNN) integrated with a smart learning mechanism (SLM) that is based on an extended Kalman filter with self-decoupling ability (SDEKF). Here the GMLPNN is built with an ability to autoadjust its structure based on its characteristic vector. Furthermore, by using the SLM based on the SDEKF, the GMLPNN parameters are optimized with small computational effort, and the modeling accuracy is improved. An apparatus employing an IPMC actuator is first set up to investigate the IPMC characteristics and to generate the data for training and validating the model. The advanced NBBM model for the IPMC system is then created with the proper inputs to estimate IPMC tip displacement. Next, the model is optimized using the SLM mechanism with the training data. Finally, the optimized NBBM model is verified with the validating data. A comparison between this model and the previously developed model is also carried out to prove the effectiveness of the proposed modeling technique. (paper)

  19. Functional Recovery Secondary to Neural Stem/Progenitor Cells Transplantation Combined with Treadmill Training in Mice with Chronic Spinal Cord Injury

    DEFF Research Database (Denmark)

    Tashiro, Syoichi; Nishimura, Soraya; Iwai, Hiroki

    are chiefly developed to improve the effect of regenerative therapy for this refractory state, physical training also have attracted the attention as a desirable candidate to combine with cell transplantation. Recently, we have reported that the addition of treadmill training enhances the effect of NS...... in the combined therapy group. Further investigation revealed that NS/PC transplantation improved spinal conductivity and central pattern generator activity, and that training promoted the appropriate inhibitory motor control including spasticity. The combined therapy enhanced these independent effects of each......Rapid progress in stem cell medicine is being realized in neural regeneration also in spinal cord injury (SCI). Researchers have reported remarkable functional recovery with various cell sources including induced Pluripotent Stem cell derived neural stem/progenitor cells (NS/PCs), especially...

  20. The strategic framework for European cooperation in education and training (ET 2020: Which place for archaeological heritage in the lifelong learning context?

    Directory of Open Access Journals (Sweden)

    Martínez Rodríguez, R.

    2012-01-01

    Full Text Available The Lisbon Strategy objective of turning Europe into a world-leading knowledge-based society, has left the way to the Europe 2020 strategyobjectives of smart, sustainable and inclusive growth. The strategic framework for European cooperation in education and training (ET 2020 establishes that educational and training systems should provide the means for all citizens to realise their potentials, as well as to acquire and develop skills and competencies needed for their employability and foster further learning, active citizenship and inter-cultural dialogue; from a lifelong learning perspective, covering all levels and contexts (including non-formal and informal learning. The aim of this paper is to present the strategic objectives of EU education and training policies and discuss, accordingly, a place for archaeological heritage in school, higher and adult education.

  1. Distance training for teachers: an inter-institutional cooperation strategy for the public acceptance of nuclear energy

    International Nuclear Information System (INIS)

    Perez Matzen, Claudio

    2003-01-01

    Two experiences of teacher distance training using new information and communication technologies are described. These experiences were developed in 2000-2002 to promote the public acceptance of nuclear energy, including efforts from the Chilean Nuclear Energy Commission (CCHEN, http://www.cchen.cl) , the Metropolitan University of Sciences of Education (UMCE, http://www.umce.cl) , the Center for Improvement, Experimentation and Pedagogical Research (CPEIP, http://cpeip.mineduc.cl) and the National University Network (REUNA, http://www.reuna.cl). The experiences described consist of improving courses for teachers working at the basic and intermediate levels in the Chilean educational system. Both courses focused on methods and resources that support constructive teaching and meaningful learning of both basic concepts and peaceful applications of nuclear energy, in line with contemporary theories and practice in the teaching of sciences, technology and society. In the first of these experiences, developed in 2000 and entitled T eacher's Workshop: Nuclear Energy in Education. A Didactic Approach , the course received support from the International Atomic Energy Agency (IAEA). Five interactive video conference sessions were implemented to cover a wide area of the country, thanks to the Virtual University Network at REUNA (http://www.uvirtual.cl). Another component of the instructional system was a web site to help with matters like the delivery of learning materials and communications among the participants. In the second experience, developed in 2001-2002 and entitled E ducational Debate: Man, Society and Nuclear Energy , the authors received support and funding from the InterAmerican Virtual Center of Cooperation for Teacher Formation (CIDI-OEA). The participants in the distance course were from several countries, including Chile, Argentina, Colombia, Brazil and the Dominican Republic. Instructional resources included a virtual learning environment via Internet and

  2. Neural network hydrological modelling: on questions of over-fitting, over-training and over-parameterisation

    Science.gov (United States)

    Abrahart, R. J.; Dawson, C. W.; Heppenstall, A. J.; See, L. M.

    2009-04-01

    The most critical issue in developing a neural network model is generalisation: how well will the preferred solution perform when it is applied to unseen datasets? The reported experiments used far-reaching sequences of model architectures and training periods to investigate the potential damage that could result from the impact of several interrelated items: (i) over-fitting - a machine learning concept related to exceeding some optimal architectural size; (ii) over-training - a machine learning concept related to the amount of adjustment that is applied to a specific model - based on the understanding that too much fine-tuning might result in a model that had accommodated random aspects of its training dataset - items that had no causal relationship to the target function; and (iii) over-parameterisation - a statistical modelling concept that is used to restrict the number of parameters in a model so as to match the information content of its calibration dataset. The last item in this triplet stems from an understanding that excessive computational complexities might permit an absurd and false solution to be fitted to the available material. Numerous feedforward multilayered perceptrons were trialled and tested. Two different methods of model construction were also compared and contrasted: (i) traditional Backpropagation of Error; and (ii) state-of-the-art Symbiotic Adaptive Neuro-Evolution. Modelling solutions were developed using the reported experimental set ups of Gaume & Gosset (2003). The models were applied to a near-linear hydrological modelling scenario in which past upstream and past downstream discharge records were used to forecast current discharge at the downstream gauging station [CS1: River Marne]; and a non-linear hydrological modelling scenario in which past river discharge measurements and past local meteorological records (precipitation and evaporation) were used to forecast current discharge at the river gauging station [CS2: Le Sauzay].

  3. Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network

    OpenAIRE

    Su, Yu-Chuan; Chiu, Tzu-Hsuan; Yeh, Chun-Yen; Huang, Hsin-Fu; Hsu, Winston H.

    2014-01-01

    Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that video corpora with complete ground truth are usually not large and diverse enough to learn a robust model. The networks trained directly on the video data set suffer from significant overfitting and have poor recognition rate on the test set. The same lack-...

  4. Examining neural correlates of skill acquisition in a complex videogame training program

    OpenAIRE

    Prakash, Ruchika S.; De Leon, Angeline A.; Mourany, Lyla; Lee, Hyunkyu; Voss, Michelle W.; Boot, Walter R.; Basak, Chandramallika; Fabiani, Monica; Gratton, Gabriele; Kramer, Arthur F.

    2012-01-01

    Acquisition of complex skills is a universal feature of human behavior that has been conceptualized as a process that starts with intense resource dependency, requires effortful cognitive control, and ends in relative automaticity on the multi-faceted task. The present study examined the effects of different theoretically based training strategies on cortical recruitment during acquisition of complex video game skills. Seventy-five participants were recruited and assigned to one of three trai...

  5. Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

    Science.gov (United States)

    Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

    1999-01-01

    A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

  6. Cooperative VET in Training Networks: Analysing the Free-Rider Problem in a Sociology-of-Conventions Perspective

    Science.gov (United States)

    Leemann, Regula Julia; Imdorf, Christian

    2015-01-01

    In training networks, particularly small and medium-sized enterprises pool their resources to train apprentices within the framework of the dual VET system, while an intermediary organisation is tasked with managing operations. Over the course of their apprenticeship, the apprentices switch from one training company to another on a (half-) yearly…

  7. Training and evaluation of neural networks for multi-variate time series processing

    DEFF Research Database (Denmark)

    Fog, Torben L.; Larsen, Jan; Hansen, Lars Kai

    1995-01-01

    We study the training and generalization for multi-variate time series processing. It is suggested to used a quasi-maximum likelihood approach rather than the standard sum of squared errors, thus taking dependencies among the errors of the individual time series into account. This may lead...... to improved generalization performance. Further, we extend the optimal brain damage pruning technique to the multi-variate case. A key ingredient is an algebraic expression for the generalization ability of a multi-variate model. The variability of the suggested techniques are successfully demonstrated...

  8. A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

    Science.gov (United States)

    van den Bergh, J.; Schutz, J.; Chirayath, V.; Li, A.

    2017-12-01

    NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Net's convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign.Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users' input against pre-classified coral imagery to gauge their accuracy and utilizes in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

  9. A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

    Science.gov (United States)

    van den Bergh, Jarrett; Schutz, Joey; Li, Alan; Chirayath, Ved

    2017-01-01

    NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Nets convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign. Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users input against pre-classified coral imagery to gauge their accuracy and utilize in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

  10. Neural control of locomotion and training-induced plasticity after spinal and cerebral lesions.

    Science.gov (United States)

    Knikou, Maria

    2010-10-01

    Standing and walking require a plethora of sensorimotor interactions that occur throughout the nervous system. Sensory afferent feedback plays a crucial role in the rhythmical muscle activation pattern, as it affects through spinal reflex circuits the spinal neuronal networks responsible for inducing and maintaining rhythmicity, drives short-term and long-term re-organization of the brain and spinal cord circuits, and contributes to recovery of walking after locomotor training. Therefore, spinal circuits integrating sensory signals are adjustable networks with learning capabilities. In this review, I will synthesize the mechanisms underlying phase-dependent modulation of spinal reflexes in healthy humans as well as those with spinal or cerebral lesions along with findings on afferent regulation of spinal reflexes and central pattern generator in reduced animal preparations. Recovery of walking after locomotor training has been documented in numerous studies but the re-organization of spinal interneuronal and cortical circuits need to be further explored at cellular and physiological levels. For maximizing sensorimotor recovery in people with spinal or cerebral lesions, a multidisciplinary approach (rehabilitation, pharmacology, and electrical stimulation) delivered during various sensorimotor constraints is needed. Copyright 2010 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

  11. Extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA)

    International Nuclear Information System (INIS)

    1998-01-01

    As of 4 May 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, development and Training Related to Nuclear Science and Technology (INFCIRC/377), had been received by the Director General of the IAEA from the Governments of 22 African States. Zimbabwe is added to the list of 21 States reported in the previous edition (add. 9) to this document. Extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  12. Extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1998-05-15

    As of 4 May 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, development and Training Related to Nuclear Science and Technology (INFCIRC/377), had been received by the Director General of the IAEA from the Governments of 22 African States. Zimbabwe is added to the list of 21 States reported in the previous edition (add. 9) to this document. Extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  13. Transfer Effects to a Multimodal Dual-Task after Working Memory Training and Associated Neural Correlates in Older Adults - A Pilot Study.

    Science.gov (United States)

    Heinzel, Stephan; Rimpel, Jérôme; Stelzel, Christine; Rapp, Michael A

    2017-01-01

    Working memory (WM) performance declines with age. However, several studies have shown that WM training may lead to performance increases not only in the trained task, but also in untrained cognitive transfer tasks. It has been suggested that transfer effects occur if training task and transfer task share specific processing components that are supposedly processed in the same brain areas. In the current study, we investigated whether single-task WM training and training-related alterations in neural activity might support performance in a dual-task setting, thus assessing transfer effects to higher-order control processes in the context of dual-task coordination. A sample of older adults (age 60-72) was assigned to either a training or control group. The training group participated in 12 sessions of an adaptive n-back training. At pre and post-measurement, a multimodal dual-task was performed in all participants to assess transfer effects. This task consisted of two simultaneous delayed match to sample WM tasks using two different stimulus modalities (visual and auditory) that were performed either in isolation (single-task) or in conjunction (dual-task). A subgroup also participated in functional magnetic resonance imaging (fMRI) during the performance of the n-back task before and after training. While no transfer to single-task performance was found, dual-task costs in both the visual modality ( p task costs, while neural activity changes in right DLPFC during three-back predicted visual dual-task costs. Results might indicate an improvement in central executive processing that could facilitate both WM and dual-task coordination.

  14. Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters

    Directory of Open Access Journals (Sweden)

    Jingbo Chen

    2018-02-01

    Full Text Available Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs, have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable.

  15. Blood Glucose Prediction Using Artificial Neural Networks Trained with the AIDA Diabetes Simulator: A Proof-of-Concept Pilot Study

    Directory of Open Access Journals (Sweden)

    Gavin Robertson

    2011-01-01

    Full Text Available Diabetes mellitus is a major, and increasing, global problem. However, it has been shown that, through good management of blood glucose levels (BGLs, the associated and costly complications can be reduced significantly. In this pilot study, Elman recurrent artificial neural networks (ANNs were used to make BGL predictions based on a history of BGLs, meal intake, and insulin injections. Twenty-eight datasets (from a single case scenario were compiled from the freeware mathematical diabetes simulator, AIDA. It was found that the most accurate predictions were made during the nocturnal period of the 24 hour daily cycle. The accuracy of the nocturnal predictions was measured as the root mean square error over five test days (RMSE5 day not used during ANN training. For BGL predictions of up to 1 hour a RMSE5 day of (±SD 0.15±0.04 mmol/L was observed. For BGL predictions up to 10 hours, a RMSE5  day of (±SD 0.14±0.16 mmol/L was observed. Future research will investigate a wider range of AIDA case scenarios, real-patient data, and data relating to other factors influencing BGLs. ANN paradigms based on real-time recurrent learning will also be explored to accommodate dynamic physiology in diabetes.

  16. High-Intensity Progressive Resistance Training Increases Strength With No Change in Cardiovascular Function and Autonomic Neural Regulation in Older Adults.

    Science.gov (United States)

    Kanegusuku, Hélcio; Queiroz, Andréia C; Silva, Valdo J; de Mello, Marco T; Ugrinowitsch, Carlos; Forjaz, Cláudia L

    2015-07-01

    The effects of high-intensity progressive resistance training (HIPRT) on cardiovascular function and autonomic neural regulation in older adults are unclear. To investigate this issue, 25 older adults were randomly divided into two groups: control (CON, N = 13, 63 ± 4 years; no training) and HIPRT (N = 12, 64 ± 4 years; 2 sessions/week, 7 exercises, 2–4 sets, 10–4 RM). Before and after four months, maximal strength, quadriceps cross-sectional area (QCSA), clinic and ambulatory blood pressures (BP), systemic hemodynamics, and cardiovascular autonomic modulation were measured. Maximal strength and QCSA increased in the HIPRT group and did not change in the CON group. Clinic and ambulatory BP, cardiac output, systemic vascular resistance, stroke volume, heart rate, and cardiac sympathovagal balance did not change in the HIPRT group or the CON group. In conclusion, HIPRT was effective at increasing muscle mass and strength without promoting changes in cardiovascular function or autonomic neural regulation.

  17. 75 FR 10319 - Cooper Tools-Sumter, Cooper Tools Divisions, a Subsidiary of Cooper Industries, Inc., Including...

    Science.gov (United States)

    2010-03-05

    ... DEPARTMENT OF LABOR Employment and Training Administration [TA-W-71,602] Cooper Tools--Sumter, Cooper Tools Divisions, a Subsidiary of Cooper Industries, Inc., Including On-Site Leased Workers From... January 26, 2010, applicable to workers of Cooper Tools--Sumter, Cooper Tools Division, a subsidiary of...

  18. Neural control of magnetic suspension systems

    Science.gov (United States)

    Gray, W. Steven

    1993-01-01

    The purpose of this research program is to design, build and test (in cooperation with NASA personnel from the NASA Langley Research Center) neural controllers for two different small air-gap magnetic suspension systems. The general objective of the program is to study neural network architectures for the purpose of control in an experimental setting and to demonstrate the feasibility of the concept. The specific objectives of the research program are: (1) to demonstrate through simulation and experimentation the feasibility of using neural controllers to stabilize a nonlinear magnetic suspension system; (2) to investigate through simulation and experimentation the performance of neural controllers designs under various types of parametric and nonparametric uncertainty; (3) to investigate through simulation and experimentation various types of neural architectures for real-time control with respect to performance and complexity; and (4) to benchmark in an experimental setting the performance of neural controllers against other types of existing linear and nonlinear compensator designs. To date, the first one-dimensional, small air-gap magnetic suspension system has been built, tested and delivered to the NASA Langley Research Center. The device is currently being stabilized with a digital linear phase-lead controller. The neural controller hardware is under construction. Two different neural network paradigms are under consideration, one based on hidden layer feedforward networks trained via back propagation and one based on using Gaussian radial basis functions trained by analytical methods related to stability conditions. Some advanced nonlinear control algorithms using feedback linearization and sliding mode control are in simulation studies.

  19. Cooperative Learning in Graduate Education: A Study of Its Effectiveness in Administrator Training in Two California Universities.

    Science.gov (United States)

    Hughes, H. Woodrow; Townley, Arthur J.

    This paper presents findings from a study that explored students' perceptions of cooperative learning strategies used in educational administration classes. Specifically, the study sought to determine whether students perceived the strategies to be more effective than traditional methods in increasing their knowledge and retention and in improving…

  20. Choosing the cooperative option

    Energy Technology Data Exchange (ETDEWEB)

    English, G. (National Rural Electric Cooperative Association (United States))

    1999-06-01

    Cooperatives do not ask to be exempted from the law. They do ask that laws and regulations be designed to allow them to meet the needs of their consumer-owners in accordance with cooperative principles, at a time that the marginal consumers being abandoned by for-profit utilities may be ready to gravitate toward cooperatives. The cooperative principles are worth reviewing because they explain the focus on the consumer and the cooperative concept of service: cooperatives are voluntary organizations, open to all persons able to use their services and willing to accept the responsibilities of membership; cooperatives are democratic organizations controlled by their members, who actively participate in setting policies and making decisions, the elected representatives are accountable to the membership; members contribute equitably to, and democratically control, the capital of their cooperative; cooperatives are autonomous, self-help organizations controlled by their members, if they enter into agreements with other organizations, including governments, they do so on terms that ensure democratic control by their members and maintain their cooperative autonomy; cooperatives provide education and training for their members, elected representatives, managers, and employees so they can contribute effectively to the development of their cooperatives, they inform the general public, particularly young people and opinion leaders, about the nature and benefits of cooperation; cooperatives serve their members most effectively and strength the cooperative movement by working together through local, national, regional, and international structures; and while focusing on member needs, cooperatives work for the sustainable development of their communities through policies accepted by their members.

  1. Lenses on ‘Japaneseness’ in the Development Cooperation Charter of 2015: Soft power, human resources development, education and training

    OpenAIRE

    King, Kenneth

    2016-01-01

    The Working Paper provides a critical analysis of the 2015 Development Assistance Charter, paying particular attention to its case for Japan’s comparative advantage and uniqueness in its development cooperation policies and practice. The term ‘Japaneseness’ is used as a shorthand for this ‘Japan brand ODA’. The paper’s focus is especially on the softer side of Japanese aid, notably its long history of concern with human resources development, knowledge creation, and self-help. These prioritie...

  2. Development and Comparative Study of Effects of Training Algorithms on Performance of Artificial Neural Network Based Analog and Digital Automatic Modulation Recognition

    Directory of Open Access Journals (Sweden)

    Jide Julius Popoola

    2015-11-01

    Full Text Available This paper proposes two new classifiers that automatically recognise twelve combined analog and digital modulated signals without any a priori knowledge of the modulation schemes and the modulation parameters. The classifiers are developed using pattern recognition approach. Feature keys extracted from the instantaneous amplitude, instantaneous phase and the spectrum symmetry of the simulated signals are used as inputs to the artificial neural network employed in developing the classifiers. The two developed classifiers are trained using scaled conjugate gradient (SCG and conjugate gradient (CONJGRAD training algorithms. Sample results of the two classifiers show good success recognition performance with an average overall recognition rate above 99.50% at signal-to-noise ratio (SNR value from 0 dB and above with the two training algorithms employed and an average overall recognition rate slightly above 99.00% and 96.40% respectively at - 5 dB SNR value for SCG and CONJGRAD training algorithms. The comparative performance evaluation of the two developed classifiers using the two training algorithms shows that the two training algorithms have different effects on both the response rate and efficiency of the two developed artificial neural networks classifiers. In addition, the result of the performance evaluation carried out on the overall success recognition rates between the two developed classifiers in this study using pattern recognition approach with the two training algorithms and one reported classifier in surveyed literature using decision-theoretic approach shows that the classifiers developed in this study perform favourably with regard to accuracy and performance probability as compared to classifier presented in previous study.

  3. Deep convolutional neural network training enrichment using multi-view object-based analysis of Unmanned Aerial systems imagery for wetlands classification

    Science.gov (United States)

    Liu, Tao; Abd-Elrahman, Amr

    2018-05-01

    Deep convolutional neural network (DCNN) requires massive training datasets to trigger its image classification power, while collecting training samples for remote sensing application is usually an expensive process. When DCNN is simply implemented with traditional object-based image analysis (OBIA) for classification of Unmanned Aerial systems (UAS) orthoimage, its power may be undermined if the number training samples is relatively small. This research aims to develop a novel OBIA classification approach that can take advantage of DCNN by enriching the training dataset automatically using multi-view data. Specifically, this study introduces a Multi-View Object-based classification using Deep convolutional neural network (MODe) method to process UAS images for land cover classification. MODe conducts the classification on multi-view UAS images instead of directly on the orthoimage, and gets the final results via a voting procedure. 10-fold cross validation results show the mean overall classification accuracy increasing substantially from 65.32%, when DCNN was applied on the orthoimage to 82.08% achieved when MODe was implemented. This study also compared the performances of the support vector machine (SVM) and random forest (RF) classifiers with DCNN under traditional OBIA and the proposed multi-view OBIA frameworks. The results indicate that the advantage of DCNN over traditional classifiers in terms of accuracy is more obvious when these classifiers were applied with the proposed multi-view OBIA framework than when these classifiers were applied within the traditional OBIA framework.

  4. NeMO-Net - The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

    Science.gov (United States)

    Li, A. S. X.; Chirayath, V.; Segal-Rosenhaimer, M.; Das, K.

    2017-12-01

    In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8% error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets.We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Python's extensive libraries for machine learning, as well as extending integration to GPU

  5. Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.

    Science.gov (United States)

    Yang, Xin; Liu, Chaoyue; Wang, Zhiwei; Yang, Jun; Min, Hung Le; Wang, Liang; Cheng, Kwang-Ting Tim

    2017-12-01

    Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive

  6. THINKING ALOUD, TALKING, AND LEAThinking aloud, talking, and learning to read: esl reading comprehension training in small cooperative groups Thinking aloud, talking, and learning to read: esl reading comprehension training in small cooperative groups

    Directory of Open Access Journals (Sweden)

    Yael Bejanaro

    2008-04-01

    Full Text Available Training students to become independent skillful readers is a major concern of the EFL reading teacher. How can we best train students in selecting and applying reading strategies so that they become more efficient readers? Can we ensure that an increase in students’ awareness of the need to use strategies will help them become more skillful readers? These questions served as a trigger for this study. The aim of this study was to investigate whether verbal articulation of reading behavior in a small group will improve foreign language comprehension. It is our contention that using verbalization in small groups will raise metacognitive awareness which will in turn enhance effective use of skills and strategies and result in improvement in reading comprehension. We assume that the special features that characterize small group interactions can provide an appropriate setting for raising metacognitive awareness. Training students to become independent skillful readers is a major concern of the EFL reading teacher. How can we best train students in selecting and applying reading strategies so that they become more efficient readers? Can we ensure that an increase in students’ awareness of the need to use strategies will help them become more skillful readers? These questions served as a trigger for this study. The aim of this study was to investigate whether verbal articulation of reading behavior in a small group will improve foreign language comprehension. It is our contention that using verbalization in small groups will raise metacognitive awareness which will in turn enhance effective use of skills and strategies and result in improvement in reading comprehension. We assume that the special features that characterize small group interactions can provide an appropriate setting for raising metacognitive awareness.

  7. Co-operative agreement for Arab States in Asia for Research, Development and Training Related to Nuclear Science and Technology (ARASIA). Entry into force

    International Nuclear Information System (INIS)

    2002-01-01

    The Co-operative Agreement for Arab States in Asia for Research, Development and Training related to Nuclear Science and Technology (ARASIA), pursuant to Article XII, entered into force upon receipt by the Director General of the Agency of notification of acceptance by three Arab Member States of the Agency in Asia, in accordance with Article XI, i.e. on 29 July 2002. The Agreement shall continue to be in force for a period of six years from the date of its entry into force and may be extended for further period(s) if the States Parties so agree. The text of the Agreement is reproduced in the Annex hereto for the information of all Member States. By 20 November 2002, there were 5 Parties to the above Agreement

  8. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    International Nuclear Information System (INIS)

    1998-01-01

    As of 31 January 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology(INFCIRC/377), has been received by the Director General of the IAEA from the Governments of 21 African States. Uganda is added at the at the list of 20 African States reported in the previous addition to the document (INFCIRC/377/Add.8). Pursuant to Article XIV.2 of the original Agreement the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  9. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    International Nuclear Information System (INIS)

    1997-01-01

    As of 31 December 1996, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) (see INFCIRC/377), had been received by the Director General from the Governments of 20 African countries. Niger, Libya and Mali are added at the list of 17 countries reported in the previous addition of the document (INFCIRC/377/Add.7). Pursuant to Article XIV.2 of the original Agreement, the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  10. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1998-02-24

    As of 31 January 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology(INFCIRC/377), has been received by the Director General of the IAEA from the Governments of 21 African States. Uganda is added at the at the list of 20 African States reported in the previous addition to the document (INFCIRC/377/Add.8). Pursuant to Article XIV.2 of the original Agreement the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000.

  11. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA)

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1997-02-28

    As of 31 December 1996, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) (see INFCIRC/377), had been received by the Director General from the Governments of 20 African countries. Niger, Libya and Mali are added at the list of 17 countries reported in the previous addition of the document (INFCIRC/377/Add.7). Pursuant to Article XIV.2 of the original Agreement, the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000.

  12. Cooperative Extension Training Impact on Military Youth and 4-H Youth: The Case of Speak Out for Military Kids

    Science.gov (United States)

    Edwin, James; McKinley, Steve; Talbert, B. Allen

    2010-01-01

    Extension needs new venues to promote their programming skills to unfamiliar audiences. One new audience Extension is currently reaching is military children. By partnering with Operation: Military Kids to offer a Speak Out for Military Kids training, Extension supports military children and document changes in the behavior of this audience.…

  13. Cooperative VET in Training Networks: Analysing the Free-Rider Problem in a Sociology-of-Conventions Perspective

    Directory of Open Access Journals (Sweden)

    Regula Julia Leemann

    2015-12-01

    Full Text Available In training networks, particularly small and medium-sized enterprises pool their resources to train apprentices within the framework of the dual VET system, while an intermediary organisation is tasked with managing operations. Over the course of their apprenticeship, the apprentices switch from one training company to another on a (half- yearly basis. Drawing on a case study of four training networks in Switzerland and the theoretical framework of the sociology of conventions, this paper aims to understand the reasons for the slow dissemination and reluctant adoption of this promising form of organising VET in Switzerland. The results of the study show that the system of moving from one company to another creages a variety of free-rider constellations in the distribution of the collectively generated corporative benefits. This explains why companies are reluctant to participate in this model. For the network to be sustainable, the intermediary organisation has to address discontent arising from free-rider problems while taking into account that the solutions found are always tentative and will often result in new free-rider problems.

  14. Educational Effects and Problems on Cooperative Education for Training Practical Engineer at Anan National College of Technology

    Science.gov (United States)

    Harano, Tomoki; Yoshimura, Hiroshi; Yasuno, Emiko; Uehara, Nobutomo

    The first author has devised the new cooperative education program to adopt the curricula at Colleges of Technology in Japan. The program consists of the practical work programs at manufacturing industries for three weeks and two weeks in every summer and spring vacation at third to fourth grade year, to enhance the communication skill, and to acquire the practical manufacturing technology and so on. In addition, the program has the practical design project of the manufacturing industry to cultivate the problem-solving skill for the fifth grade students at last. The program has many participants that are forty industry companies and seventy students in successfully. It is found that the program is to enhance the communication skill, writing skill and self-confident as a practical engineer by the iterative work.

  15. International cooperation

    International Nuclear Information System (INIS)

    2008-01-01

    In this chapter international cooperation of the Division for Radiation Safety, NPP Decommissioning and Radwaste Management of the VUJE, a. s. is presented. Very important is cooperation with the International Atomic Energy Agency. This cooperation has various forms - national and regional projects of technical cooperation, coordinated research activities, participation of our experts in preparation of the IAEA documentation etc.

  16. Relative cortico-subcortical shift in brain activity but preserved training-induced neural modulation in older adults during bimanual motor learning.

    Science.gov (United States)

    Santos Monteiro, Thiago; Beets, Iseult A M; Boisgontier, Matthieu P; Gooijers, Jolien; Pauwels, Lisa; Chalavi, Sima; King, Brad; Albouy, Geneviève; Swinnen, Stephan P

    2017-10-01

    To study age-related differences in neural activation during motor learning, functional magnetic resonance imaging scans were acquired from 25 young (mean 21.5-year old) and 18 older adults (mean 68.6-year old) while performing a bimanual coordination task before (pretest) and after (posttest) a 2-week training intervention on the task. We studied whether task-related brain activity and training-induced brain activation changes differed between age groups, particularly with respect to the hyperactivation typically observed in older adults. Findings revealed that older adults showed lower performance levels than younger adults but similar learning capability. At the cerebral level, the task-related hyperactivation in parietofrontal areas and underactivation in subcortical areas observed in older adults were not differentially modulated by the training intervention. However, brain activity related to task planning and execution decreased from pretest to posttest in temporo-parieto-frontal areas and subcortical areas in both age groups, suggesting similar processes of enhanced activation efficiency with advanced skill level. Furthermore, older adults who displayed higher activity in prefrontal regions at pretest demonstrated larger training-induced performance gains. In conclusion, in spite of prominent age-related brain activation differences during movement planning and execution, the mechanisms of learning-related reduction of brain activation appear to be similar in both groups. Importantly, cerebral activity during early learning can differentially predict the amplitude of the training-induced performance benefit between young and older adults. Copyright © 2017 Elsevier Inc. All rights reserved.

  17. Proposal for an IAEA - sponsored project of interregional co-operation for training of nuclear scientists in developing countries, using the expertise available in the nuclear data field

    International Nuclear Information System (INIS)

    Kocherov, N.; Schmidt, J.J.

    1980-07-01

    During the Winter College on Nuclear Physics and Reactors jointly organized by the IAEA and the International Centre for Theoretical Physics (ICTP) in January - March 1980 and held at the ICTP in Trieste, a Working Group was convened from participants in the Interregional Advanced Training Course on Applications of Nuclear Theory to Nuclear Data Calculations for Reactor Design. The Working Group examined the current fast neutron nuclear data requirements for nuclear technologies and discussed possible means to meet these requirements, with a major emphasis on the possible contributions by and benefit for the developing countries. The Working Group concluded that the organisation of an IAEA-sponsored Project of Interregional Co-operation for Training of Nuclear Scientists in Developing Countries, Using the Expertise Available in the Nuclear Data Field, would be the best solution to cope with the problems in question and drafted an outline of the technical programme and organization of such a project the revised version of which is presented in this report

  18. 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

  19. The Text of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology, 1987. Status of Acceptances as of 28 February 1993

    International Nuclear Information System (INIS)

    1993-04-01

    As of 28 February 1993, notifications of acceptance of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 1987 (See INFCIRC/ 167/Add.15), in accordance with Article 2 thereof, had been received by the Director General from the Governments [ru

  20. The Text of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training related to Nuclear Science and Technology, 1987. Status of Acceptances as of 28 February 1993

    International Nuclear Information System (INIS)

    1993-04-01

    As of 28 February 1993, notifications of acceptance of the Agreement to Extend the Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 1987 (See INFCIRC/ 167/Add.15), in accordance with Article 2 thereof, had been received by the Director General from the Governments [es

  1. Evaluation of teacher-training programs in cooperative learning methods, based on an analysis of structural equations

    Directory of Open Access Journals (Sweden)

    José Manuel Serrano

    2008-11-01

    Full Text Available The present study is focused on the design of the assessment of programs for teacher training. The authors emphasize the relevance of the assessment of this kind of programs and its development by models of structural equations. There are specifically postulated four exogenous variables, which coincide with four segments of a program, and an endogenous variable, which refers to the results, expressed these in terms of adequacy, productivity, efficacy, efficiency, and effectiveness. Both the structural and the measurement aspects are totally developed in the corresponding causal model.

  2. Functional Strength Training and Movement Performance Therapy for Upper Limb Recovery Early Poststroke—Efficacy, Neural Correlates, Predictive Markers, and Cost-Effectiveness: FAST-INdiCATE Trial

    Directory of Open Access Journals (Sweden)

    Susan M. Hunter

    2018-01-01

    Full Text Available BackgroundVariation in physiological deficits underlying upper limb paresis after stroke could influence how people recover and to which physical therapy they best respond.ObjectivesTo determine whether functional strength training (FST improves upper limb recovery more than movement performance therapy (MPT. To identify: (a neural correlates of response and (b whether pre-intervention neural characteristics predict response.DesignExplanatory investigations within a randomised, controlled, observer-blind, and multicentre trial. Randomisation was computer-generated and concealed by an independent facility until baseline measures were completed. Primary time point was outcome, after the 6-week intervention phase. Follow-up was at 6 months after stroke.ParticipantsWith some voluntary muscle contraction in the paretic upper limb, not full dexterity, when recruited up to 60 days after an anterior cerebral circulation territory stroke.InterventionsConventional physical therapy (CPT plus either MPT or FST for up to 90 min-a-day, 5 days-a-week for 6 weeks. FST was “hands-off” progressive resistive exercise cemented into functional task training. MPT was “hands-on” sensory/facilitation techniques for smooth and accurate movement.OutcomesThe primary efficacy measure was the Action Research Arm Test (ARAT. Neural measures: fractional anisotropy (FA corpus callosum midline; asymmetry of corticospinal tracts FA; and resting motor threshold (RMT of motor-evoked potentials.AnalysisCovariance models tested ARAT change from baseline. At outcome: correlation coefficients assessed relationship between change in ARAT and neural measures; an interaction term assessed whether baseline neural characteristics predicted response.Results288 Participants had: mean age of 72.2 (SD 12.5 years and mean ARAT 25.5 (18.2. For 240 participants with ARAT at baseline and outcome the mean change was 9.70 (11.72 for FST + CPT and 7.90 (9.18 for MPT

  3. Activities of the nuclear emergency assistance and training center. Strengthening co-operation with parties in normal circumstances

    International Nuclear Information System (INIS)

    Watanabe, Fumitaka; Matsui, Tomoaki; Nomura, Tamotsu

    2005-01-01

    The Japan Nuclear Cycle Development Institute (JNC) and the Japan Atomic Energy Research Institute (JAERI) established the Nuclear Emergency Assistance and Training Center (NEAT) in March 2002. The center aims to provide various support nuclear safety regulatory bodies, local governments and nuclear facility licenses as specialists about nuclear and radiological issues according to the role shown in the Basic Disaster Management Plan. Upon a nuclear and/or radiological disaster occurring in Japan, NEAT will send specialists to the disaster scene, and offer the use of special equipments. NEAT maintains frequent contact with related organizations in normal circumstance. NEAT also participates in nuclear emergency exercises instructed by the parties concerned, which has contributed to the brewing of mutual trust with related organizations. In October 2005, JNC and JAERI merged into a new organization named the Japan Atomic Energy Agency (JAEA). NEAT, as a section of the organization, continuously deals with nuclear emergencies. (author)

  4. Importance of the awareness, training exchange of information and co-operation between regulatory authorities and customs, police and other law enforcement agencies

    International Nuclear Information System (INIS)

    Shakshooki, S.K.; Al-Ahaimer, R.O.

    1998-01-01

    Fast developments in science and technology are a great accomplishment in this century. These facilities have been utilized by criminals and deviants by identified way. Industrial developed countries have their own means to improve and to modify technology and scientific facilities to cope up with any new existing problems, such as the problem of illegal trading of nuclear materials. Facilities for exchange of information among industrial countries also play an important role to prevent any dangerous phenomena may exist. In contrast most developing countries lack the means of up-to-date follow up quick and continuous scientific and technological developments. However they have qualified personnel to follow up quickly and to prevent drug and narcotics smuggling. Recently we have heard about a dangerous phenomena, the illegal trading of nuclear materials, which derive attention internationally. The developed countries can cope easily with it. However, in developing countries, their lack of up to date facilities can cause a grate damage to their nations. Libyan Arab Jamahiriya is always willing to co-operate internationally to prevent any new dangerous phenomena. We think it is a time for conformation on international official agreement regarding this phenomena. Exchange of information between different countries through an international agency is important for prohibiting the illegal nuclear materials trading. Also to help in creation of a temporally scientific committee to provide different countries of the world the available information in this area and to co-operate specially with police, custom and law enforcement agencies of each nation providing an international legislation for dealing with such phenomena is a priority. Assistance for the arrangement of training through IAEA is of great importance. (author)

  5. Effects of oxytocin and vasopressin on the neural response to unreciprocated cooperation within brain regions involved in stress and anxiety in men and women.

    Science.gov (United States)

    Chen, Xu; Hackett, Patrick D; DeMarco, Ashley C; Feng, Chunliang; Stair, Sabrina; Haroon, Ebrahim; Ditzen, Beate; Pagnoni, Giuseppe; Rilling, James K

    2016-06-01

    Anxiety disorders are characterized by hyperactivity in both the amygdala and the anterior insula. Interventions that normalize activity in these areas may therefore be effective in treating anxiety disorders. Recently, there has been significant interest in the potential use of oxytocin (OT), as well as vasopressin (AVP) antagonists, as treatments for anxiety disorders. In this double-blind, placebo-controlled, pharmaco- fMRI study, 153 men and 151 women were randomized to treatment with either 24 IU intranasal OT, 20 IU intranasal AVP, or placebo and imaged with fMRI as they played the iterated Prisoner's Dilemma game with same-sex human and computer partners. In men, OT attenuated the fMRI response to unreciprocated cooperation (CD), a negative social interaction, within the amygdala and anterior insula. This effect was specific to interactions with human partners. In contrast, among women, OT unexpectedly attenuated the amygdala and anterior insula response to unreciprocated cooperation from computer but not human partners. Among women, AVP did not significantly modulate the response to unreciprocated cooperation in either the amygdala or the anterior insula. However, among men, AVP attenuated the BOLD response to CD outcomes with human partners across a relatively large cluster including the amygdala and the anterior insula, which was contrary to expectations. Our results suggest that OT may decrease the stress of negative social interactions among men, whereas these effects were not found in women interacting with human partners. These findings support continued investigation into the possible efficacy of OT as a treatment for anxiety disorders.

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

    Science.gov (United States)

    Lee, Jun-Ki; Kwon, Yongju

    2012-01-01

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

  7. Achieving Consistent Near-Optimal Pattern Recognition Accuracy Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks

    Science.gov (United States)

    Nikelshpur, Dmitry O.

    2014-01-01

    Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…

  8. Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography

    International Nuclear Information System (INIS)

    Suzuki, Kenji; Armato, Samuel G. III; Li, Feng; Sone, Shusuke; Doi, Kunio

    2003-01-01

    In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the 'likelihood of being a nodule'. The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765

  9. Supporting project on international education and training in cooperated program for Radiation Technology with World Nuclear University

    Energy Technology Data Exchange (ETDEWEB)

    Yoo, Byung Duk; Nam, Y. M.; Noh, S. P.; Shin, J. Y. [KAERI, Daejeon (Korea, Republic of)

    2010-08-15

    The objective is promote national status and potential of Nuclear radiation industry, and take a world-wide leading role in radiation industry, by developing and hosting the first WNU Radiation Technology School. RI School (World Nuclear University Radioisotope School) is the three-week program designed to develop and inspire future international leaders in the field of radioisotope for the first time. The project would enable promote abilities of radioactive isotopes professions, and to build the human network with future leaders in the world-wide nuclear and radiation field. Especially by offering opportunity to construct human networks between worldwide radiation field leaders of next generation, intangible assets and pro-Korean human networks are secured among international radiation industry personnel. This might enhance the power and the status of Korean radiation industries, and establish the fundamental base for exporting of radiation technology and its products. We developed the performance measurement method for the school. This shows that 2010 WNU RI School was the first training program focusing on the radioisotope and very useful program for the participants in view of knowledge management and strengthening personal abilities. Especially, the experiences and a human network with world-wide future-leaders in radiation field are most valuable asset. It is expected that the participants could this experience and network developed in the program as a stepping stone toward the development of Korea's nuclear and radiation industry.

  10. Supporting project on international education and training in cooperated program for Radiation Technology with World Nuclear University

    International Nuclear Information System (INIS)

    Yoo, Byung Duk; Nam, Y. M.; Noh, S. P.; Shin, J. Y.

    2010-08-01

    The objective is promote national status and potential of Nuclear radiation industry, and take a world-wide leading role in radiation industry, by developing and hosting the first WNU Radiation Technology School. RI School (World Nuclear University Radioisotope School) is the three-week program designed to develop and inspire future international leaders in the field of radioisotope for the first time. The project would enable promote abilities of radioactive isotopes professions, and to build the human network with future leaders in the world-wide nuclear and radiation field. Especially by offering opportunity to construct human networks between worldwide radiation field leaders of next generation, intangible assets and pro-Korean human networks are secured among international radiation industry personnel. This might enhance the power and the status of Korean radiation industries, and establish the fundamental base for exporting of radiation technology and its products. We developed the performance measurement method for the school. This shows that 2010 WNU RI School was the first training program focusing on the radioisotope and very useful program for the participants in view of knowledge management and strengthening personal abilities. Especially, the experiences and a human network with world-wide future-leaders in radiation field are most valuable asset. It is expected that the participants could this experience and network developed in the program as a stepping stone toward the development of Korea's nuclear and radiation industry

  11. Conflictual cooperation

    DEFF Research Database (Denmark)

    Axel, Erik

    2011-01-01

    , cooperation appeared as the continuous reworking of contradictions in the local arrangement of societal con- ditions. Subjects were distributed and distributed themselves according to social privileges, resources, and dilemmas in cooperation. Here, the subjects’ activities and understandings took form from...

  12. Communication dated 10 September 2008 received from the Permanent Mission of Egypt to the Agency concerning the High Level Policy Review Seminar of African Regional Cooperative Agreement for Research, Development and Training related to Nuclear Science and Technology (AFRA)

    International Nuclear Information System (INIS)

    2008-01-01

    The Secretariat has received a communication dated 10 September 2008 from the Permanent Mission of Egypt enclosing the documents of the High Level Policy Review Seminar of the African Regional Cooperative Agreement for Research, Development and Training related to Nuclear Science and Technology (AFRA) held in Aswan, Egypt on 28-29 November 2007. The communication, and as requested therein, the enclosures containing the Declaration of Aswan, the Aswan Action Plan and the Profile of the Regional Strategic Cooperative Framework (2008-2013) are circulated herewith for information

  13. Analysis and Design of the Innovation and Entrepreneurship Training Management System based on School Enterprise Cooperation (Taking the School of Computer and Information Engineering of Beijing University of Agriculture as an example)

    Science.gov (United States)

    Qianyi, Zhang; Xiaoshun, Li; Ping, Hu; Lu, Ning

    2018-03-01

    With the promotion of undergraduate training mode of “3+1” in Beijing University of Agriculture, the mode and direction of applied and compound talents training should be further visualized, at the same time, in order to make up for the shortage of Double Teachers in the school and the lack of teaching cases that cover the advanced technology in the industry, the school actively encourages the cooperation between the two teaching units and enterprises, and closely connects the enterprise resources with the school teaching system, using the “1” in “3+1” to carry out innovative training work for students. This method is beneficial for college students to integrate theory into practice and realize the purpose of applying knowledge in Higher Education. However, in the actual student training management, this kind of cooperation involves three party units and personnel, so it is difficult to form a unified management, on the other hand, it may also result from poor communication, which leads to unsatisfactory training results. At the same time, there is no good training supervision mechanism, causes the student training work specious. To solve the above problem,this paper designs a training management system of student innovation and Entrepreneurship Based on school enterprise cooperation,the system can effectively manage the relevant work of students’ training, and effectively solve the above problems. The subject is based on the training of innovation and entrepreneurship in the school of computer and information engineering of Beijing University of Agriculture. The system software architecture is designed using B/S architecture technology, the system is divided into three layers, the application of logic layer includes student training management related business, and realized the user’s basic operation management for student training, users can not only realize the basic information management of enterprises, colleges and students through the system

  14. Piano training enhances the neural processing of pitch and improves speech perception in Mandarin-speaking children.

    Science.gov (United States)

    Nan, Yun; Liu, Li; Geiser, Eveline; Shu, Hua; Gong, Chen Chen; Dong, Qi; Gabrieli, John D E; Desimone, Robert

    2018-06-25

    Musical training confers advantages in speech-sound processing, which could play an important role in early childhood education. To understand the mechanisms of this effect, we used event-related potential and behavioral measures in a longitudinal design. Seventy-four Mandarin-speaking children aged 4-5 y old were pseudorandomly assigned to piano training, reading training, or a no-contact control group. Six months of piano training improved behavioral auditory word discrimination in general as well as word discrimination based on vowels compared with the controls. The reading group yielded similar trends. However, the piano group demonstrated unique advantages over the reading and control groups in consonant-based word discrimination and in enhanced positive mismatch responses (pMMRs) to lexical tone and musical pitch changes. The improved word discrimination based on consonants correlated with the enhancements in musical pitch pMMRs among the children in the piano group. In contrast, all three groups improved equally on general cognitive measures, including tests of IQ, working memory, and attention. The results suggest strengthened common sound processing across domains as an important mechanism underlying the benefits of musical training on language processing. In addition, although we failed to find far-transfer effects of musical training to general cognition, the near-transfer effects to speech perception establish the potential for musical training to help children improve their language skills. Piano training was not inferior to reading training on direct tests of language function, and it even seemed superior to reading training in enhancing consonant discrimination.

  15. ITDB Cooperation With International Organizations

    International Nuclear Information System (INIS)

    2010-01-01

    IAEA illicit trafficking database cooperates with many international organizations. Among these organizations are Interpol, Universal Postal Union,and World Customs Organization. Other organizations are Organization for Security and Cooperation in Europe, UN Economic Commission for Europe, UN-Department of Disarmament Affairs and UN office for Drug and Crime. The cooperation with Interpol involves consultations on issues of training and technical assistance and other matters of common interest.

  16. Training of reverse propagation neural networks applied to neutron dosimetry; Entrenamiento de redes neuronales de propagacion inversa aplicadas a la dosimetria de neutrones

    Energy Technology Data Exchange (ETDEWEB)

    Hernandez P, C. F.; Martinez B, M. R.; Leon P, A. A.; Espinoza G, J. G.; Castaneda M, V. H.; Solis S, L. O.; Castaneda M, R.; Ortiz R, M.; Vega C, H. R. [Universidad Autonoma de Zacatecas, Av. Ramon Lopez Velarde 801, Col. Centro, 98000 Zacatecas, Zac. (Mexico); Mendez V, R. [Centro de Investigaciones Energeticas, Medioambientales y Tecnologicas, Laboratorio de Patrones Neutronicos, Av. Complutense 22, 28040 Madrid (Spain); Gallego, E. [Universidad Politecnica de Madrid, Departamento de Ingenieria Nuclear, ETSI Industriales, Jose Gutierrez Abascal 2, 28006 Madrid (Spain); De Sousa L, M. A. [Centro de Desenvolvimento da Tecnologia Nuclear / CNEN, Av. Pte. Antonio Carlos 6627, 31270-901 Pampulha, Belo Horizonte, Minas Gerais (Brazil)

    2016-10-15

    Neutron dosimetry is of great importance in radiation protection as aims to provide dosimetric quantities to assess the magnitude of detrimental health effects due to exposure of neutron radiation. To quantify detriment to health is necessary to evaluate the dose received by the occupationally exposed personnel using different detection systems called dosimeters, which have very dependent responses to the energy distribution of neutrons. The neutron detection is a much more complex problem than the detection of charged particles, since it does not carry an electric charge, does not cause direct ionization and has a greater penetration power giving the possibility of interacting with matter in a different way. Because of this, various neutron detection systems have been developed, among which the Bonner spheres spectrometric system stands out due to the advantages that possesses, such as a wide range of energy, high sensitivity and easy operation. However, once obtained the counting rates, the problem lies in the neutron spectrum deconvolution, necessary for the calculation of the doses, using different mathematical methods such as Monte Carlo, maximum entropy, iterative methods among others, which present various difficulties that have motivated the development of new technologies. Nowadays, methods based on artificial intelligence technologies are being used to perform neutron dosimetry, mainly using the theory of artificial neural networks. In these new methods the need for spectrum reconstruction can be eliminated for the calculation of the doses. In this work an artificial neural network or reverse propagation was trained for the calculation of 15 equivalent doses from the counting rates of the Bonner spheres spectrometric system using a set of 7 spheres, one of 2 spheres and two of a single sphere of different sizes, testing different error values until finding the most appropriate. The optimum network topology was obtained through the robust design

  17. Neural Networks for Optimal Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1995-01-01

    Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....

  18. Neural Networks for the Beginner.

    Science.gov (United States)

    Snyder, Robin M.

    Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

  19. Neural Correlates of Selective Attention With Hearing Aid Use Followed by ReadMyQuips Auditory Training Program.

    Science.gov (United States)

    Rao, Aparna; Rishiq, Dania; Yu, Luodi; Zhang, Yang; Abrams, Harvey

    The objectives of this study were to investigate the effects of hearing aid use and the effectiveness of ReadMyQuips (RMQ), an auditory training program, on speech perception performance and auditory selective attention using electrophysiological measures. RMQ is an audiovisual training program designed to improve speech perception in everyday noisy listening environments. Participants were adults with mild to moderate hearing loss who were first-time hearing aid users. After 4 weeks of hearing aid use, the experimental group completed RMQ training in 4 weeks, and the control group received listening practice on audiobooks during the same period. Cortical late event-related potentials (ERPs) and the Hearing in Noise Test (HINT) were administered at prefitting, pretraining, and post-training to assess effects of hearing aid use and RMQ training. An oddball paradigm allowed tracking of changes in P3a and P3b ERPs to distractors and targets, respectively. Behavioral measures were also obtained while ERPs were recorded from participants. After 4 weeks of hearing aid use but before auditory training, HINT results did not show a statistically significant change, but there was a significant P3a reduction. This reduction in P3a was correlated with improvement in d prime (d') in the selective attention task. Increased P3b amplitudes were also correlated with improvement in d' in the selective attention task. After training, this correlation between P3b and d' remained in the experimental group, but not in the control group. Similarly, HINT testing showed improved speech perception post training only in the experimental group. The criterion calculated in the auditory selective attention task showed a reduction only in the experimental group after training. ERP measures in the auditory selective attention task did not show any changes related to training. Hearing aid use was associated with a decrement in involuntary attention switch to distractors in the auditory selective

  20. Regional cooperation in nuclear energy development

    International Nuclear Information System (INIS)

    Chung, K.; Muntzing, L.M.

    1987-01-01

    In November 1985, PBNCC (the Pacific Basin Nuclear Cooperation Committee) was formally established. Currently six Pacific Basin members have been participating in PBNCC: Canada, Japan, South Korea, Mexico, Taiwan of Chian, and the United States of America. The People's Republic of China has sent observes to the PBNCC meetings. The technical contents of PBWCC working groups are as follows: 1. Regional cooperative for pooled spare parts of nuclear power plants and inventory management; 2. Regional cooperation in nuclear training; 3. Regional cooperation on nuclear safety; 4. Regional cooperation in Codes and Standards; 5. Regional Cooperation in public acceptance; 6. Regional cooperation on radwaste management. (Liu)

  1. Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs.

    Science.gov (United States)

    Cicero, Mark; Bilbily, Alexander; Colak, Errol; Dowdell, Tim; Gray, Bruce; Perampaladas, Kuhan; Barfett, Joseph

    2017-05-01

    Convolutional neural networks (CNNs) are a subtype of artificial neural network that have shown strong performance in computer vision tasks including image classification. To date, there has been limited application of CNNs to chest radiographs, the most frequently performed medical imaging study. We hypothesize CNNs can learn to classify frontal chest radiographs according to common findings from a sufficiently large data set. Our institution's research ethics board approved a single-center retrospective review of 35,038 adult posterior-anterior chest radiographs and final reports performed between 2005 and 2015 (56% men, average age of 56, patient type: 24% inpatient, 39% outpatient, 37% emergency department) with a waiver for informed consent. The GoogLeNet CNN was trained using 3 graphics processing units to automatically classify radiographs as normal (n = 11,702) or into 1 or more of cardiomegaly (n = 9240), consolidation (n = 6788), pleural effusion (n = 7786), pulmonary edema (n = 1286), or pneumothorax (n = 1299). The network's performance was evaluated using receiver operating curve analysis on a test set of 2443 radiographs with the criterion standard being board-certified radiologist interpretation. Using 256 × 256-pixel images as input, the network achieved an overall sensitivity and specificity of 91% with an area under the curve of 0.964 for classifying a study as normal (n = 1203). For the abnormal categories, the sensitivity, specificity, and area under the curve, respectively, were 91%, 91%, and 0.962 for pleural effusion (n = 782), 82%, 82%, and 0.868 for pulmonary edema (n = 356), 74%, 75%, and 0.850 for consolidation (n = 214), 81%, 80%, and 0.875 for cardiomegaly (n = 482), and 78%, 78%, and 0.861 for pneumothorax (n = 167). Current deep CNN architectures can be trained with modest-sized medical data sets to achieve clinically useful performance at detecting and excluding common pathology on chest radiographs.

  2. Protein-Protein Interaction Article Classification Using a Convolutional Recurrent Neural Network with Pre-trained Word Embeddings.

    Science.gov (United States)

    Matos, Sérgio; Antunes, Rui

    2017-12-13

    Curation of protein interactions from scientific articles is an important task, since interaction networks are essential for the understanding of biological processes associated with disease or pharmacological action for example. However, the increase in the number of publications that potentially contain relevant information turns this into a very challenging and expensive task. In this work we used a convolutional recurrent neural network for identifying relevant articles for extracting information regarding protein interactions. Using the BioCreative III Article Classification Task dataset, we achieved an area under the precision-recall curve of 0.715 and a Matthew's correlation coefficient of 0.600, which represents an improvement over previous works.

  3. Simplified LQG Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1997-01-01

    A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce...

  4. AFRA: Supporting regional cooperation

    International Nuclear Information System (INIS)

    2016-01-01

    The African Regional Cooperative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) provides a framework for African Member States to intensify their collaboration through programmes and projects focused on the specific shared needs of its members. It is a formal intergovernmental agreement which entered into force in 1990. In the context of AFRA, Regional Designated Centres for training and education in radiation protection (RDCs) are established African institutions able to provide services, such as training of highly qualified specialists or instructors needed at the national level and also to facilitate exchange of experience and information through networks of services operating in the field

  5. International cooperation

    International Nuclear Information System (INIS)

    Prieto, F.E.

    1984-01-01

    It looks doubtless that the need for an international cooperation to solve the worldwide energy problems is already a concern of individuals, institutions, and governments. This is an improvement. But there is something lacking. The author refers to the Atoms for Peace speech, the origin of the IAEA and of the subsequent spreading of the nuclear option. He also refers back to the call made by the Mexican government for a worldwide energy cooperation. He stresses the need for governments to cooperate, so that this international cooperation on energy can be put into operation for the benefit of mankind

  6. Evolvable Neural Software System

    Science.gov (United States)

    Curtis, Steven A.

    2009-01-01

    The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.

  7. Application of neural networks in coastal engineering

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    the neural network attractive. A neural network is an information processing system modeled on the structure of the dynamic process. It can solve the complex/nonlinear problems quickly once trained by operating on problems using an interconnected number...

  8. Cooperation, Technology, and Performance: A Case Study.

    Science.gov (United States)

    Cavanagh, Thomas; Dickenson, Sabrina; Brandt, Suzanne

    1999-01-01

    Describes the CTP (Cooperation, Technology, and Performance) model and explains how it is used by the Department of Veterans Affairs-Veteran's Benefit Administration (VBA) for training. Discusses task analysis; computer-based training; cooperative-based learning environments; technology-based learning; performance-assessment methods; courseware…

  9. Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: Suppression of rectal tubes

    International Nuclear Information System (INIS)

    Suzuki, Kenji; Yoshida, Hiroyuki; Naeppi, Janne; Dachman, Abraham H.

    2006-01-01

    One of the limitations of the current computer-aided detection (CAD) of polyps in CT colonography (CTC) is a relatively large number of false-positive (FP) detections. Rectal tubes (RTs) are one of the typical sources of FPs because a portion of a RT, especially a portion of a bulbous tip, often exhibits a cap-like shape that closely mimics the appearance of a small polyp. Radiologists can easily recognize and dismiss RT-induced FPs; thus, they may lose their confidence in CAD as an effective tool if the CAD scheme generates such ''obvious'' FPs due to RTs consistently. In addition, RT-induced FPs may distract radiologists from less common true positives in the rectum. Therefore, removal RT-induced FPs as well as other types of FPs is desirable while maintaining a high sensitivity in the detection of polyps. We developed a three-dimensional (3D) massive-training artificial neural network (MTANN) for distinction between polyps and RTs in 3D CTC volumetric data. The 3D MTANN is a supervised volume-processing technique which is trained with input CTC volumes and the corresponding ''teaching'' volumes. The teaching volume for a polyp contains a 3D Gaussian distribution, and that for a RT contains zeros for enhancement of polyps and suppression of RTs, respectively. For distinction between polyps and nonpolyps including RTs, a 3D scoring method based on a 3D Gaussian weighting function is applied to the output of the trained 3D MTANN. Our database consisted of CTC examinations of 73 patients, scanned in both supine and prone positions (146 CTC data sets in total), with optical colonoscopy as a reference standard for the presence of polyps. Fifteen patients had 28 polyps, 15 of which were 5-9 mm and 13 were 10-25 mm in size. These CTC cases were subjected to our previously reported CAD scheme that included centerline-based segmentation of the colon, shape-based detection of polyps, and reduction of FPs by use of a Bayesian neural network based on geometric and texture

  10. Progress report from Duke University - Cooperative Research and Training Program in Biological Oceanography from 01 July 1965 to 30 June 1966 (NODC Accession 7200405)

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The progress report covers the period from 01 July 1965 to 30 June 1966. The main purpose of the report is to provide cooperating investigators with field and cruise...

  11. Effect of training and structured medication review on medication appropriateness in nursing home residents and on cooperation between health care professionals: the InTherAKT study protocol.

    Science.gov (United States)

    Mahlknecht, Angelika; Nestler, Nadja; Bauer, Ulrike; Schüßler, Nadine; Schuler, Jochen; Scharer, Sebastian; Becker, Ralf; Waltering, Isabel; Hempel, Georg; Schwalbe, Oliver; Flamm, Maria; Osterbrink, Jürgen

    2017-01-18

    Pharmacotherapy in residents of nursing homes is critical due to the special vulnerability of this population. Medical care and interprofessional communication in nursing homes are often uncoordinated. As a consequence, polypharmacy and inappropriate medication use are common and may lead to hospitalizations and health hazards. The aim of this study is to optimize communication between the involved professional groups by specific training and by establishing a structured medication review process, and to improve medication appropriateness and patient-relevant health outcomes for residents of nursing homes. The trial is designed as single-arm study. It involves 300 nursing home residents aged ≥ 65 years and the members of the different professional groups practising in nursing home care (15-20 general practitioners, nurses, pharmacists). The intervention consists of interprofessional education on safe medication use in geriatric patients, and a systematic interprofessional therapy check (recording, reviewing and adapting the medication of the participating residents by means of a specific online platform). The intervention period is divided into two phases; total project period is 3 years. Primary outcome measure is the change in medication appropriateness according to the Medication Appropriateness Index. Secondary outcomes are cognitive performance, occurrence of delirium, agitation, tendency of falls, total number of drugs, number of potentially dangerous drug-drug interactions and appropriateness of recorded analgesic therapy regimens according to the Medication Appropriateness Index. Data are collected at t 0 (before the start of the intervention), t 1 (after the first intervention period) and t 2 (after the second intervention period). Cooperation and communication between the professional groups are investigated twice by qualitative interviews. The project aims to establish a structured system for monitoring of drug therapy in nursing home residents

  12. Neural mechanisms of behavioral change in young adults with high-functioning autism receiving virtual reality social cognition training: A pilot study.

    Science.gov (United States)

    Yang, Y J Daniel; Allen, Tandra; Abdullahi, Sebiha M; Pelphrey, Kevin A; Volkmar, Fred R; Chapman, Sandra B

    2018-05-01

    Measuring treatment efficacy in individuals with Autism Spectrum Disorder (ASD) relies primarily on behaviors, with limited evidence as to the neural mechanisms underlying these behavioral gains. This pilot study addresses this void by investigating neural and behavioral changes in a Phase I trial in young adults with high-functioning ASD who received an evidence-based behavioral intervention, Virtual Reality-Social Cognition Training over 5 weeks for a total of 10 hr. The participants were tested pre- and post-training with a validated biological/social versus scrambled/nonsocial motion neuroimaging task, previously shown to activate regions within the social brain networks. Three significant brain-behavior changes were identified. First, the right posterior superior temporal sulcus, a hub for socio-cognitive processing, showed increased brain activation to social versus nonsocial stimuli in individuals with greater gains on a theory-of-mind measure. Second, the left inferior frontal gyrus, a region for socio-emotional processing, tracked individual gains in emotion recognition with decreased activation to social versus nonsocial stimuli. Finally, the left superior parietal lobule, a region for visual attention, showed significantly decreased activation to nonsocial versus social stimuli across all participants, where heightened attention to nonsocial contingencies has been considered a disabling aspect of ASD. This study provides, albeit preliminary, some of the first evidence of the harnessable neuroplasticity in adults with ASD through an age-appropriate intervention in brain regions tightly linked to social abilities. This pilot trial motivates future efforts to develop and test social interventions to improve behaviors and supporting brain networks in adults with ASD. Autism Res 2018, 11: 713-725. © 2018 The Authors Autism Research published by International Society for Autism Research and Wiley Periodicals, Inc. This study addresses how the behavioral

  13. NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

    Science.gov (United States)

    Chirayath, Ved

    2018-01-01

    We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with

  14. Brain changes following four weeks of unimanual motor training: Evidence from behavior, neural stimulation, cortical thickness, and functional MRI.

    Science.gov (United States)

    Sale, Martin V; Reid, Lee B; Cocchi, Luca; Pagnozzi, Alex M; Rose, Stephen E; Mattingley, Jason B

    2017-09-01

    Although different aspects of neuroplasticity can be quantified with behavioral probes, brain stimulation, and brain imaging assessments, no study to date has combined all these approaches into one comprehensive assessment of brain plasticity. Here, 24 healthy right-handed participants practiced a sequence of finger-thumb opposition movements for 10 min each day with their left hand. After 4 weeks, performance for the practiced sequence improved significantly (P left (mean increase: 53.0% practiced, 6.5% control) and right (21.0%; 15.8%) hands. Training also induced significant (cluster p-FWE right hemisphere, 301 voxel cluster; left hemisphere 700 voxel cluster), and sensorimotor cortices and superior parietal lobules (right hemisphere 864 voxel cluster; left hemisphere, 1947 voxel cluster). Transcranial magnetic stimulation over the right ("trained") primary motor cortex yielded a 58.6% mean increase in a measure of motor evoked potential amplitude, as recorded at the left abductor pollicis brevis muscle. Cortical thickness analyses based on structural MRI suggested changes in the right precentral gyrus, right post central gyrus, right dorsolateral prefrontal cortex, and potentially the right supplementary motor area. Such findings are consistent with LTP-like neuroplastic changes in areas that were already responsible for finger sequence execution, rather than improved recruitment of previously nonutilized tissue. Hum Brain Mapp 38:4773-4787, 2017. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

  15. The text of the third agreement to extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (RCA). Extension of agreement

    International Nuclear Information System (INIS)

    2002-01-01

    The text of the Third Agreement to Extend the 1987 Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology, 'the 1987 RCA', is reproduced herein for the information of all Members. Pursuant to Article 1 of the Third Agreement to Extend the 1987 Regional Co-operative Agreement, the 1987 RCA shall continue in force for a further period of five years with effect from 12 June 2002, i.e., through 11 June 2007. As of 15 May 2002, notifications of acceptance had been received by the Director General from the Governments of Bangladesh, China, India, Indonesia, Republic of Korea, Malaysia, Pakistan, Sri Lanka and Viet Nam. The latest status list is attached

  16. Fruit Classification by Wavelet-Entropy and Feedforward Neural Network Trained by Fitness-Scaled Chaotic ABC and Biogeography-Based Optimization

    Directory of Open Access Journals (Sweden)

    Shuihua Wang

    2015-08-01

    Full Text Available Fruit classification is quite difficult because of the various categories and similar shapes and features of fruit. In this work, we proposed two novel machine-learning based classification methods. The developed system consists of wavelet entropy (WE, principal component analysis (PCA, feedforward neural network (FNN trained by fitness-scaled chaotic artificial bee colony (FSCABC and biogeography-based optimization (BBO, respectively. The K-fold stratified cross validation (SCV was utilized for statistical analysis. The classification performance for 1653 fruit images from 18 categories showed that the proposed “WE + PCA + FSCABC-FNN” and “WE + PCA + BBO-FNN” methods achieve the same accuracy of 89.5%, higher than state-of-the-art approaches: “(CH + MP + US + PCA + GA-FNN ” of 84.8%, “(CH + MP + US + PCA + PSO-FNN” of 87.9%, “(CH + MP + US + PCA + ABC-FNN” of 85.4%, “(CH + MP + US + PCA + kSVM” of 88.2%, and “(CH + MP + US + PCA + FSCABC-FNN” of 89.1%. Besides, our methods used only 12 features, less than the number of features used by other methods. Therefore, the proposed methods are effective for fruit classification.

  17. Elaboration of a neural network for classification of Taylors bubbles in vertical pipes using Monte Carlo simulation for the training phase

    Energy Technology Data Exchange (ETDEWEB)

    Schuabb, Pablo G.; Medeiros, Jose A.C.C.; Schirru, Roberto, E-mail: pablogs@poli.ufrj.br, E-mail: canedo@lmp.ufrj.br, E-mail: schirru@lmp.ufrj.br [Corrdenacao dos Programas de Pos-Graduacao em Engenharia (PEN/COPPE/UFRJ), Rio de Janeiro, RJ (Brazil). Programa de Engenharia Nuclear

    2015-07-01

    The increase of the diameter of a spherical bubble deforms its shape, after which it moves along the vertical center of the pipeline. The Taylor's flow has bubbles with the form of a bullet and increases in the bubble's volume are seen by an enlargement of their length making that kind of bubble easily identified using gamma ray attenuation which is simulated via the software MCNPX that uses the Monte Carlo probabilistic method to simulate radiation-matter interactions. The simulations show that there exists a relation among the counts of a detector and the rising movement of a Taylor's Bubble. A database could be made to answer queries on the dimensions of a Taylor bubble for given readings of a detector, approach that would require a huge database. To make that association an Artificial Neural Network is proposed. The network can be trained with a finite number of samples that is enough to make the network able to classify data of not known bubbles simulated via MCNPX or measured on field. (author)

  18. Elaboration of a neural network for classification of Taylors bubbles in vertical pipes using Monte Carlo simulation for the training phase

    International Nuclear Information System (INIS)

    Schuabb, Pablo G.; Medeiros, Jose A.C.C.; Schirru, Roberto

    2015-01-01

    The increase of the diameter of a spherical bubble deforms its shape, after which it moves along the vertical center of the pipeline. The Taylor's flow has bubbles with the form of a bullet and increases in the bubble's volume are seen by an enlargement of their length making that kind of bubble easily identified using gamma ray attenuation which is simulated via the software MCNPX that uses the Monte Carlo probabilistic method to simulate radiation-matter interactions. The simulations show that there exists a relation among the counts of a detector and the rising movement of a Taylor's Bubble. A database could be made to answer queries on the dimensions of a Taylor bubble for given readings of a detector, approach that would require a huge database. To make that association an Artificial Neural Network is proposed. The network can be trained with a finite number of samples that is enough to make the network able to classify data of not known bubbles simulated via MCNPX or measured on field. (author)

  19. Extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA). Status of Acceptances as of 30 July 1998

    International Nuclear Information System (INIS)

    1998-01-01

    As of 30 July 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) (INFCIRC/377), had been received by the Director General of the IAEA from the Governments of 23 African States. Senegal is added to the list of 22 States reported in the previous edition (add.10) of this document. The extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  20. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA). Status of acceptances as of 30 September 1995

    International Nuclear Information System (INIS)

    1995-10-01

    As of 30 September 1995, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (see INFCIRC/377), has been received by the Director General from the Governments of: Tunisia, Egypt, Madagascar, South Africa, Ethiopia, Algeria, Mauritius, Sudan, Tanzania, Cameroon, Kenya, Zaire, Morocco, Sierra Leone, Namibia, Nigeria, Ghana. Pursuant to Article XIV.2, (of the original Agreement) the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  1. Extension of the African regional co-operative agreement for research, development and training related to nuclear science and technology (AFRA). Status of acceptances as of 30 September 1995

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1995-10-01

    As of 30 September 1995, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (see INFCIRC/377), has been received by the Director General from the Governments of: Tunisia, Egypt, Madagascar, South Africa, Ethiopia, Algeria, Mauritius, Sudan, Tanzania, Cameroon, Kenya, Zaire, Morocco, Sierra Leone, Namibia, Nigeria, Ghana. Pursuant to Article XIV.2, (of the original Agreement) the extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000.

  2. Extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA). Status of Acceptances as of 30 July 1998

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1998-08-13

    As of 30 July 1998, notifications of acceptance of the extension of the African Regional Co-operative Agreement for Research, Development and Training Related to Nuclear Science and Technology (AFRA) (INFCIRC/377), had been received by the Director General of the IAEA from the Governments of 23 African States. Senegal is added to the list of 22 States reported in the previous edition (add.10) of this document. The extension entered into force on 4 April 1995, upon expiration of the original Agreement, and will remain in force for an additional period of 5 years, i.e. through 3 April 2000

  3. Neural plasticity in amplitude of low frequency fluctuation, cortical hub construction, regional homogeneity resulting from working memory training.

    Science.gov (United States)

    Takeuchi, Hikaru; Taki, Yasuyuki; Nouchi, Rui; Sekiguchi, Atsushi; Kotozaki, Yuka; Nakagawa, Seishu; Makoto Miyauchi, Carlos; Sassa, Yuko; Kawashima, Ryuta

    2017-05-03

    Working memory training (WMT) induces changes in cognitive function and various neurological systems. Here, we investigated changes in recently developed resting state functional magnetic resonance imaging measures of global information processing [degree of the cortical hub, which may have a central role in information integration in the brain, degree centrality (DC)], the magnitude of intrinsic brain activity [fractional amplitude of low frequency fluctuation (fALFF)], and local connectivity (regional homogeneity) in young adults, who either underwent WMT or received no intervention for 4 weeks. Compared with no intervention, WMT increased DC in the anatomical cluster, including anterior cingulate cortex (ACC), to the medial prefrontal cortex (mPFC). Furthermore, WMT increased fALFF in the anatomical cluster including the right dorsolateral prefrontal cortex (DLPFC), frontopolar area and mPFC. WMT increased regional homogeneity in the anatomical cluster that spread from the precuneus to posterior cingulate cortex and posterior parietal cortex. These results suggest WMT-induced plasticity in spontaneous brain activity and global and local information processing in areas of the major networks of the brain during rest.

  4. Prevention of neural hypersensitivity after acute upper limb burns: Development and pilot of a cortical training protocol.

    Science.gov (United States)

    Edgar, Dale; Zorzi, Lisa M; Wand, Ben M; Brockman, Nathalie; Griggs, Carolyn; Clifford, Matthew; Wood, Fiona

    2011-06-01

    Acute burn patients suffer pain and secondary hyperalgesia. This alters movement patterns and impairs function. Non-pharmacological methods of treatment are limited and lack rigorous testing and evidence for use. The treatment in this case series was designed to direct conscious attention to, and normalise sensation of, the injured limb in pain free way. The aim of the study was to describe a cortical training programme (CTP) in acute upper limb burn patients and to investigate the efficacy, safety and feasibility of the protocol. The study is a descriptive case series (n=6). Study tasks engaged sensory and motor nerves to influence the perception of the injured area. Visual and tactile inputs to maintain and, or normalise the homuncular map were central to the intervention. One patient, who commenced the study without resting pain, responded negatively. The remaining five patients had reduced pain and fear avoidance behaviours with associated improvement in arm function. The CTP approach is safe and feasible for use with acute burn patients where pain is reported at rest. Comparative studies are required to determine the relative efficacy of the program to usual interventions and the patients who may benefit from the technique. Copyright © 2011 Elsevier Ltd and ISBI. All rights reserved.

  5. Investigation of School-Based Staff Development Programs as a Means to Promote International Cooperation in Curriculum Improvement Through Teacher Training.

    Science.gov (United States)

    Thurber, John C.

    This study explores the feasibility of utilizing school-focused staff development programs in promoting international cooperation through transferability and/or adaptation of relevant aspects of this type of inservice education by foreign countries. The objective of this presentation is to develop interest in ways in which teachers in various…

  6. Effects of rehabilitation training on apoptosis of nerve cells and the recovery of neural and motor functions in rats with ischemic stroke through the PI3K/Akt and Nrf2/ARE signaling pathways.

    Science.gov (United States)

    Jin, Xiao-Fei; Wang, Shan; Shen, Min; Wen, Xin; Han, Xin-Rui; Wu, Jun-Chang; Tang, Gao-Zhuo; Wu, Dong-Mei; Lu, Jun; Zheng, Yuan-Lin

    2017-09-01

    This study was designed in order to investigate the effects between rehabilitation training on the apoptosis of nerve cells and the recovery of neural and motor functions of rats with ischemic stroke by way of the phosphatidylinositol 3-kinase/protein kinase B (PI3K/Akt) and nuclear factor E2-related factor 2/antioxidant responsive element (Nrf2/ARE) signaling pathways. In total, 110 healthy adult male Sprague-Dawley (SD) rats were selected in order to take part in this study. Ninety SD rats were used in order to establish the middle cerebral artery occlusion (MCAO), among which 80 rats were randomly assigned as part of the natural recovery, natural recovery+Rp-PI3K (the rats injected with PI3K/Akt inhibitor LY294002), rehabilitation training, and rehabilitation training+Rp-PI3K groups. Meanwhile, 20 rats were selected as part of the sham operation group. The neural and motor functions of these rats were evaluated using a balance beam test and the Bederson score. The mRNA expressions of PI3K, Akt, Nrf2 and HO-1 were measured using an RT-qPCR. The protein expressions of PI3K, p-PI3K, Akt, p-Akt, Nrf2 and HO-1 were also detected by using western blotting and the immunohistochemistry process. The cell cycle and cell apoptosis were detected by using a flow cytometry and TUNEL assay. The sham operation group exhibited lower neural and motor function scores than other groups. At the 7, 14, and 21 d marks of this study, the neural and motor function scores were increased in the natural recovery, natural recovery+Rp-PI3K, and rehabilitation training+Rp-PI3K groups in comparison with the rehabilitation training group but found to be decreased in the natural recovery group in comparison with the natural recovery+Rp-PI3K group. In comparison with the sham operation group, expressions of PI3K, Nrf2 and HO-1, and proportions of p-PI3K/PI3K and p-Akt/Akt were all higher in the natural recovery, rehabilitation training, and rehabilitation training+Rp-PI3K groups. Same trends were

  7. International co-operation

    International Nuclear Information System (INIS)

    1997-01-01

    In 1996, Nuclear Regulatory Authority of the Slovak Republic (NRA SR) ensured the Slovak Republic (SR) obligations with relation to the international agreements and with the SR membership in the IAEA.International co-operation has been ensured on the basis of the bilateral international agreements. With the Ministry of Foreign Affairs co-operation, the SR fulfilled its financial obligations to this organization in due time and in the full scope. Representing Central and Eastern Europe interest in the Board of Governors, the SR participation in the highest executive in the highest executive authority was finished in 1996.The Board of Governors Vice-chairman position was executed by NRA SR Chairman. 5 national and 6 regional technical co-operation and assistance projects were realized in 1996. 12 organizations participated in these projects and accordingly 104 experts took part in training programmes, scientific visits or as the mission members abroad. Besides, Slovak experts participated at work of technical advisory and consultation groups with the significant assistance. In the framework of IAEA co-operation, the SR was visited by 11 expert missions formed by 28 experts from 19 countries including IAEA. Slovak organizations, namely institutes of the Academy of Sciences, Slovak research centres and universities participated in IAEA scientific and research activities through NRA SR. 15 scientific contracts in total were approved and realized and these contracts are utilized as supplementary financing of the own scientific and research projects. Other international co-operation and regional co-operation activities of the NRA SR in 1996 are reviewed

  8. NEURAL METHODS FOR THE FINANCIAL PREDICTION

    OpenAIRE

    Jerzy Balicki; Piotr Dryja; Waldemar Korłub; Piotr Przybyłek; Maciej Tyszka; Marcin Zadroga; Marcin Zakidalski

    2016-01-01

    Artificial neural networks can be used to predict share investment on the stock market, assess the reliability of credit client or predicting banking crises. Moreover, this paper discusses the principles of cooperation neural network algorithms with evolutionary method, and support vector machines. In addition, a reference is made to other methods of artificial intelligence, which are used in finance prediction.

  9. NEURAL METHODS FOR THE FINANCIAL PREDICTION

    Directory of Open Access Journals (Sweden)

    Jerzy Balicki

    2016-06-01

    Full Text Available Artificial neural networks can be used to predict share investment on the stock market, assess the reliability of credit client or predicting banking crises. Moreover, this paper discusses the principles of cooperation neural network algorithms with evolutionary method, and support vector machines. In addition, a reference is made to other methods of artificial intelligence, which are used in finance prediction.

  10. NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification

    Directory of Open Access Journals (Sweden)

    Min Peng

    2016-10-01

    Full Text Available Near-infrared (NIR face recognition has attracted increasing attention because of its advantage of illumination invariance. However, traditional face recognition methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN for NIR face recognition (specifically face identification in non-cooperative-user applications. The proposed NIRFaceNet is modified from GoogLeNet, but has a more compact structure designed specifically for the Chinese Academy of Sciences Institute of Automation (CASIA NIR database and can achieve higher identification rates with less training time and less processing time. The experimental results demonstrate that NIRFaceNet has an overall advantage compared to other methods in the NIR face recognition domain when image blur and noise are present. The performance suggests that the proposed NIRFaceNet method may be more suitable for non-cooperative-user applications.

  11. Interorganizational Cooperation

    Science.gov (United States)

    2016-10-12

    Administrative Services Officer , Office of Congressional and Intergovernmental Affairs, Office of the Chief Financial Officer , Office of the Chief ...Nations. • Clarifies the role of the United States Agency for International Development (USAID) Office of Transition Initiatives and its relationship...Centralize interorganizational cooperation within the command group. Under this model, the chief of staff or a special staff officer within the command

  12. Analysis of neural networks through base functions

    NARCIS (Netherlands)

    van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.

    Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more

  13. Genetic Algorithm Optimized Neural Networks Ensemble as ...

    African Journals Online (AJOL)

    NJD

    Improvements in neural network calibration models by a novel approach using neural network ensemble (NNE) for the simultaneous ... process by training a number of neural networks. .... Matlab® version 6.1 was employed for building principal component ... provide a fair simulation of calibration data set with some degree.

  14. Formation, “Gold Rule” for the cooperative development

    Directory of Open Access Journals (Sweden)

    Alcides López Labrada

    2013-06-01

    Full Text Available Before the arising of the cooperative movement in the world, cooperation already existed. So, it is logical to affirm that there can be cooperation without cooperative movement. But there cannot be cooperative movement without cooperation, because cooperation is an indispensable premise for the existence of cooperative movement. Both the precursors of the cooperative movement and the classics of Marxism agreed on the necessity of cooperative formation. Lenin called socialism “the regime of cultured cooperators” and the International Cooperative Alliance (ICA contemplated the following, among the seven universal principles of the cooperative movement: education, formation and training of cooperative members, as one of the most important and strategic principles. They have been recognized as the golden rule of the cooperative movement. The changes occurred in Cuba (the existence and evolution of different types of cooperatives, the updating of the economic model, the dynamics of the agrarian sector and the opening of the cooperative movement towards other sectors of the National Economy fully justify the achievement of a cooperative culture, not only of cooperative members but also the actors that perform around cooperatives, the decision- makers and all society. Among the most significant proposals for the achievement of a cooperative culture in Cuba the following can be found: to integrate the different actors that participate in the cooperative formation by means of a national network for cooperative formation by identifying the training demand and training the people that should really implement the change, while building capacities of all the individuals involved in the cooperative movement in a direct or indirect way.

  15. Parameterization Of Solar Radiation Using Neural Network

    International Nuclear Information System (INIS)

    Jiya, J. D.; Alfa, B.

    2002-01-01

    This paper presents a neural network technique for parameterization of global solar radiation. The available data from twenty-one stations is used for training the neural network and the data from other ten stations is used to validate the neural model. The neural network utilizes latitude, longitude, altitude, sunshine duration and period number to parameterize solar radiation values. The testing data was not used in the training to demonstrate the performance of the neural network in unknown stations to parameterize solar radiation. The results indicate a good agreement between the parameterized solar radiation values and actual measured values

  16. GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework.

    Science.gov (United States)

    Deng, Lei; Jiao, Peng; Pei, Jing; Wu, Zhenzhi; Li, Guoqi

    2018-04-01

    Although deep neural networks (DNNs) are being a revolutionary power to open up the AI era, the notoriously huge hardware overhead has challenged their applications. Recently, several binary and ternary networks, in which the costly multiply-accumulate operations can be replaced by accumulations or even binary logic operations, make the on-chip training of DNNs quite promising. Therefore there is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discrete. The second one is how to remove the full-precision hidden weights in the training phase to break the bottlenecks of memory/computation consumption. To address the first issue, we present a multi-step neuronal activation discretization method and a derivative approximation technique that enable the implementing the back propagation algorithm on discrete DNNs. While for the second issue, we propose a discrete state transition (DST) methodology to constrain the weights in a discrete space without saving the hidden weights. Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github.com/AcrossV/Gated-XNOR. More particularly, we find that when both the weights and activations become ternary values, the DNNs can be reduced to sparse binary networks, termed as gated XNOR networks (GXNOR-Nets) since only the event of non-zero weight and non-zero activation enables the control gate to start the XNOR logic operations in the original binary networks. This promises the event-driven hardware design for efficient mobile intelligence. We achieve advanced performance compared with state-of-the-art algorithms. Furthermore, the computational sparsity

  17. Neural Network Ensembles

    DEFF Research Database (Denmark)

    Hansen, Lars Kai; Salamon, Peter

    1990-01-01

    We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....

  18. Neural Networks for Non-linear Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1994-01-01

    This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....

  19. Interacting neural networks

    Science.gov (United States)

    Metzler, R.; Kinzel, W.; Kanter, I.

    2000-08-01

    Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

  20. Artificial Neural Network Modeling of an Inverse Fluidized Bed ...

    African Journals Online (AJOL)

    A Radial Basis Function neural network has been successfully employed for the modeling of the inverse fluidized bed reactor. In the proposed model, the trained neural network represents the kinetics of biological decomposition of pollutants in the reactor. The neural network has been trained with experimental data ...

  1. Activities and co-operations in 1990

    International Nuclear Information System (INIS)

    Cai Dunjiu

    1991-01-01

    The items of activities and co-operations in 1990 are listed. It includes the meetings held by CNDC at home, the international meetings held in China, the international meetings, workshop or training course attended by chinese scientists and other activities and co-operations related to CNDC

  2. Neural Architectures for Control

    Science.gov (United States)

    Peterson, James K.

    1991-01-01

    The cerebellar model articulated controller (CMAC) neural architectures are shown to be viable for the purposes of real-time learning and control. Software tools for the exploration of CMAC performance are developed for three hardware platforms, the MacIntosh, the IBM PC, and the SUN workstation. All algorithm development was done using the C programming language. These software tools were then used to implement an adaptive critic neuro-control design that learns in real-time how to back up a trailer truck. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. CMAC neural architectures are also used in conjunction with a hierarchical planning approach to find collision-free paths over 2-D analog valued obstacle fields. The method constructs a coarse resolution version of the original problem and then finds the corresponding coarse optimal path using multipass dynamic programming. CMAC artificial neural architectures are used to estimate the analog transition costs that dynamic programming requires. The CMAC architectures are trained in real-time for each obstacle field presented. The coarse optimal path is then used as a baseline for the construction of a fine scale optimal path through the original obstacle array. These results are a very good indication of the potential power of the neural architectures in control design. In order to reach as wide an audience as possible, we have run a seminar on neuro-control that has met once per week since 20 May 1991. This seminar has thoroughly discussed the CMAC architecture, relevant portions of classical control, back propagation through time, and adaptive critic designs.

  3. Task 9. Deployment of photovoltaic technologies: co-operation with developing countries. The role of quality management, hardware certification and accredited training in PV programmes in developing countries

    Energy Technology Data Exchange (ETDEWEB)

    Fitzgerald, M. C. [Institute for Sustainable Power, Highlands Ranch, CO (United States); Oldach, R.; Bates, J. [IT Power Ltd, The Manor house, Chineham (United Kingdom)

    2003-09-15

    This report for the International Energy Agency (IEA) made by Task 9 of the Photovoltaic Power Systems (PVPS) programme takes a look at the role of quality management, hardware certification and accredited training in PV programmes in developing countries. The objective of this document is to provide assistance to those project developers that are interested in implementing or improving support programmes for the deployment of PV systems for rural electrification. It is to enable them to address and implement quality assurance measures, with an emphasis on management, technical and training issues and other factors that should be considered for the sustainable implementation of rural electrification programmes. It is considered important that quality also addresses the socio-economic and the socio-technical aspects of a programme concept. The authors summarise that, for a PV programme, there are three important areas of quality control to be implemented: quality management, technical standards and quality of training.

  4. The Effects of a Ski Training Program Employing“ Buddy Systems” on the Skiing Techniques of Women’s University Students from the Cooperative Learning’s Viewpoint

    OpenAIRE

    松本, 裕史; 中西, 匠; Hiroshi, Matsumoto; Takumi, Nakanishi

    2017-01-01

    The purpose of this study was to examine the effects of a ski training program, grounded in the“ buddy system,” on the skiing techniques of students at a women’s university. A group of twelve students, serving as the intervention group, participated in the ski training program using the buddy system, while another group of twelve students participated in program lacking the buddy system, as a control group. The measurement of skiing techniques( parallel turn, stem turn and wedeln) was conduct...

  5. [Social cooperatives in Italy].

    Science.gov (United States)

    Villotti, P; Zaniboni, S; Fraccaroli, F

    2014-06-01

    This paper describes the role of social cooperatives in Italy as a type of economic, non-profit organization and their role in contributing to the economic and social growth of the country. The purpose of this paper is to learn more about the experience of the Italian social cooperatives in promoting the work integration process of disadvantaged workers, especially those suffering from mental disorders, from a theoretical and an empirical point of view. Social enterprise is the most popular and consolidated legal and organizational model for social enterprises in Italy, introduced by Law 381/91. Developed during the early 1980s, and formally recognized by law in the early 1990s, social cooperatives aim at pursuing the general interest of the community to promote the human needs and social inclusion of citizens. They are orientated towards aims that go beyond the interest of the business owners, the primary beneficiary of their activities is the community, or groups of disadvantaged people. In Italy, Law 381/91 distinguishes between two categories of social cooperatives, those producing goods of social utility, such as culture, welfare and educational services (A-type), and those providing economic activities for the integration of disadvantaged people into employment (B-type). The main purpose of B-type social cooperatives is to integrate disadvantaged people into the open labour market. This goal is reached after a period of training and working experience inside the firm, during which the staff works to improve both the social and professional abilities of disadvantaged people. During the years, B-type social co-ops acquired a particular relevance in the care of people with mental disorders by offering them with job opportunities. Having a job is central in the recovery process of people suffering from mental diseases, meaning that B-type social co-ops in Italy play an important rehabilitative and integrative role for this vulnerable population of workers. The

  6. Transboundary cooperation

    International Nuclear Information System (INIS)

    Rauber, D.

    2006-01-01

    The operation of nuclear power plants near national borders requires a close bilateral co-operation to cope with accidents having off-site radiological impacts. For example in 1978 such an agreement was signed by the German and Swiss government. The accident at the Chernobyl NPP changed the international co-operation in the framework of international consequence management. International conventions were agreed to insure a timely notification and international assistance in case of an accident with transboundary effects. In order to fulfill these conventions several procedures were introduced. In addition, bilateral agreements were signed also with countries which are not operating nuclear power plants near national borders. Since then no accident took place that would have required any notification. However, following the experience the expectations to these networks have changed considerably and hence sustainable development is required to cope with new challenges such as long term consequences management, new radiological threats, faster international assistance, media and public concerns, and technical evolution of communications systems. (author)

  7. 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.

  8. Stability prediction of berm breakwater using neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Rao, S.; Manjunath, Y.R.

    In the present study, an artificial neural network method has been applied to predict the stability of berm breakwaters. Four neural network models are constructed based on the parameters which influence the stability of breakwater. Training...

  9. One weird trick for parallelizing convolutional neural networks

    OpenAIRE

    Krizhevsky, Alex

    2014-01-01

    I present a new way to parallelize the training of convolutional neural networks across multiple GPUs. The method scales significantly better than all alternatives when applied to modern convolutional neural networks.

  10. CTBTO international cooperation workshop

    International Nuclear Information System (INIS)

    1999-01-01

    The International Cooperation Workshop took place in Vienna, Austria, on 16 and 17 November 1998, with the participation of 104 policy/decision makers, Research and Development managers and diplomatic representatives from 58 States Signatories to the Comprehensive Nuclear-Test Ban Treaty (CTBT). The Workshop attempted to develop Treaty stipulations to: promote cooperation to facilitate and participate in the fullest possible exchange relating to technologies used in the verification of the Treaty; enable member states to strengthen national implementation of verification measures, and to benefit from the application of such technologies for peaceful purposes. The potential benefits arising from the CTBT monitoring, analysis and data communication systems are multifaceted, and as yet unknown. This Workshop provided the opportunity to examine some of these possibilities. An overview of the CTBT verification regime on the general aspects of the four monitoring technologies (seismic, hydro-acoustic, infrasound and radionuclides), including some of the elements that are the subject of international cooperation, were presented and discussed. Questions were raised on the potential benefits that can be derived by participating in the CTBT regime and broad-based discussions took place. Several concrete proposals on ways and means to facilitate and promote cooperation among States Signatories were suggested. The main points discussed by the participants can be summarized as follows: the purpose of the CTBT Organization is to assist member states to monitor Treaty compliance; the CTBT can be a highly effective technological tool which can generate wide-ranging data, which can be used for peaceful purposes; there are differences in the levels of technology development in the member states that is why peaceful applications should be supported by the Prep Com for the benefit of all member states, whether developed or developing, training being a key element to optimize the CTBT

  11. Implementation of a Regional Training Program on African Swine Fever As Part of the Cooperative Biological Engagement Program across the Caucasus Region

    Directory of Open Access Journals (Sweden)

    Marco De Nardi

    2017-10-01

    Full Text Available A training and outreach program to increase public awareness of African swine fever (ASF was implemented by Defense Threat Reduction Agency and the Ministries of Agriculture in Armenia, Georgia, Kazakhstan, and Ukraine. The implementing agency was the company SAFOSO (Switzerland. Integration of this regional effort was administered by subject matter experts for each country. The main teaching effort of this project was to develop a comprehensive regional public outreach campaign through a network of expertise and knowledge for the control and prevention of ASF in four neighboring countries that experience similar issues with this disease. Gaps in disease knowledge, legislation, and outbreak preparedness in each country were all addressed. Because ASF is a pathogen with bioterrorism potential and of great veterinary health importance that is responsible for major economic instability, the project team developed public outreach programs to train veterinarians in the partner countries to accurately and rapidly identify ASF activity and report it to international veterinary health agencies. The project implementers facilitated four regional meetings to develop this outreach program, which was later disseminated in each partner country. Partner country participants were trained as trainers to implement the outreach program in their respective countries. In this paper, we describe the development, execution, and evaluation of the ASF training and outreach program that reached more than 13,000 veterinarians, farmers, and hunters in the partner countries. Additionally, more than 120,000 booklets, flyers, leaflets, guidelines, and posters were distributed during the outreach campaign. Pre- and post-ASF knowledge exams were developed. The overall success of the project was demonstrated in that the principles of developing and conducting a public outreach program were established, and these foundational teachings can be applied within a single country or

  12. 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

  13. Practical neural network recipies in C++

    CERN Document Server

    Masters

    2014-01-01

    This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum

  14. Defense Security Cooperation Agency Vision 2020. Update 1

    Science.gov (United States)

    2015-10-01

    the feasibility and pros/ cons of developing a DoD- wide security cooperation workforce development and management program including training...Synchronizing Security Cooperation Activities ..................................................................................... 7 Meeting...Security Cooperation ............................. 15 6. Remaining a Provider of Choice for Our International Customers

  15. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

  16. Neural overlap in processing music and speech.

    Science.gov (United States)

    Peretz, Isabelle; Vuvan, Dominique; Lagrois, Marie-Élaine; Armony, Jorge L

    2015-03-19

    Neural overlap in processing music and speech, as measured by the co-activation of brain regions in neuroimaging studies, may suggest that parts of the neural circuitries established for language may have been recycled during evolution for musicality, or vice versa that musicality served as a springboard for language emergence. Such a perspective has important implications for several topics of general interest besides evolutionary origins. For instance, neural overlap is an important premise for the possibility of music training to influence language acquisition and literacy. However, neural overlap in processing music and speech does not entail sharing neural circuitries. Neural separability between music and speech may occur in overlapping brain regions. In this paper, we review the evidence and outline the issues faced in interpreting such neural data, and argue that converging evidence from several methodologies is needed before neural overlap is taken as evidence of sharing. © 2015 The Author(s) Published by the Royal Society. All rights reserved.

  17. Neural overlap in processing music and speech

    Science.gov (United States)

    Peretz, Isabelle; Vuvan, Dominique; Lagrois, Marie-Élaine; Armony, Jorge L.

    2015-01-01

    Neural overlap in processing music and speech, as measured by the co-activation of brain regions in neuroimaging studies, may suggest that parts of the neural circuitries established for language may have been recycled during evolution for musicality, or vice versa that musicality served as a springboard for language emergence. Such a perspective has important implications for several topics of general interest besides evolutionary origins. For instance, neural overlap is an important premise for the possibility of music training to influence language acquisition and literacy. However, neural overlap in processing music and speech does not entail sharing neural circuitries. Neural separability between music and speech may occur in overlapping brain regions. In this paper, we review the evidence and outline the issues faced in interpreting such neural data, and argue that converging evidence from several methodologies is needed before neural overlap is taken as evidence of sharing. PMID:25646513

  18. Additive Feed Forward Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1999-01-01

    This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...

  19. SAT-based personnel training for nuclear power plants. Proceedings of a seminar jointly organized under the technical cooperation programme (UKR/4/003) by the International Atomic Energy Agency, Goskomatom of Ukraine, South-Ukrainian NPP and held in Yuzhnoukrainsk, Ukraine, 10-14 April 1995. Working material

    International Nuclear Information System (INIS)

    1995-01-01

    In 1995 the IAEA technical co-operation project ''Training for Safe Operation and Management of Nuclear Power Plants'' (UKR/4/003) has been started with the main goal to improve training systems and training infrastructures to ensure safe and reliable operation of nuclear power plants. As the first step of the project implementation, a seminar on introducing the Systematic Approach to Training for NPP personnel was recommended by the IAEA and G-24 mission on training as one of the primary training needs and priorities of Ukraine. The Seminar was held at the South-Ukrainian Nuclear Power Plant (SUNPP), Yuzhnoukrainsk, Ukraine from 10 to 13 April 1995 and was attended by 35 representatives from GOSKOMATOM, Ministry for Environment Protection and Nuclear Safety, OGPU, and all NPPs of Ukraine

  20. Strengthening of the Cooperative Framework for ANENT

    International Nuclear Information System (INIS)

    Han, K. W.; Lee, E. J.; Min, B. J.

    2007-01-01

    The Asian Network for Education in Nuclear Technology (ANENT) was established in February 2004 to promote nuclear education and training in Asia. Initially ANENT member countries cooperated with 5 group activities encompassing broad areas. As of 2006, the cooperative framework was strengthened in a way to focus on web-based nuclear education and training for a period of several years to come. In this context, the Nuclear Training Center (NTC) of KAERI has contributed, in particular, to the development of the ANENT web-portal including a cyber platform, and making available relevant courses and materials on the web-portal. This paper discusses details of the strengthened cooperative framework in terms of NTC's effort for realizing web-based education and training through regional networking

  1. Cooperation and the evolution of intelligence.

    Science.gov (United States)

    McNally, Luke; Brown, Sam P; Jackson, Andrew L

    2012-08-07

    The high levels of intelligence seen in humans, other primates, certain cetaceans and birds remain a major puzzle for evolutionary biologists, anthropologists and psychologists. It has long been held that social interactions provide the selection pressures necessary for the evolution of advanced cognitive abilities (the 'social intelligence hypothesis'), and in recent years decision-making in the context of cooperative social interactions has been conjectured to be of particular importance. Here we use an artificial neural network model to show that selection for efficient decision-making in cooperative dilemmas can give rise to selection pressures for greater cognitive abilities, and that intelligent strategies can themselves select for greater intelligence, leading to a Machiavellian arms race. Our results provide mechanistic support for the social intelligence hypothesis, highlight the potential importance of cooperative behaviour in the evolution of intelligence and may help us to explain the distribution of cooperation with intelligence across taxa.

  2. Robust speech dereverberation with a neural network-based post-filter that exploits multi-conditional training of binaural cues

    DEFF Research Database (Denmark)

    May, Tobias

    2018-01-01

    -frequency (T-F) units. A multi-conditional training (MCT) procedure was used to simulate the uncertainties of short-term binaural cues in response to room reverberation by mixing the direct part of head related impulse responses (HRIRs) with diffuse noise. Despite being trained with only anechoic HRIRs...

  3. Engineering co-operation

    Energy Technology Data Exchange (ETDEWEB)

    Hryniszak, W

    1981-06-01

    A purposeful employment policy for human energy is basic to solving the energy dilemma, but a lack of understanding about human behavior has allowed man's exploitive characteristics to dominate during the Inductrial Revolution. England is dependent on trade to survive, but the importance of size in world competition is seen in the trend toward multinational and partnership enterprises. Reflecting this increasing competition, the engineering industries see a need for government policies that acknowledge the importance of technology and the effects of those policies on productivity. Engineering progress requires the creativity of optimistic idealism and the realism of implementing new ideas. The training and nurturing of human resources should begin by broadening the education of engineers to emphasize the concepts of quality and cooperation between government and industry. Engineers and scientists, who work within society, need to understand national demands and to operate in accordance with the highest moral standards. (DCK)

  4. Awareness, training, exchange of information and co-operation among regulatory authorities and other law enforcement institutions. Experience and problems in Latvia

    International Nuclear Information System (INIS)

    Linde, I.; Salmins, A.

    1998-01-01

    Latvia is developing infrastructure to ensure adequate system for safety and security of radioactive and nuclear materials, radiation sources and nuclear facilities within its Radiation and Nuclear Safety legal framework. The first phase of implementation was to establish and develop further relevant legal acts, but in the same time there was a need to improve the technical capabilities for the control of goods movement across the border and the need to establish the relevant educational system. The Ministry of Environmental Protection and Regional Development (MEPRD) started to participate in this process from the early beginning when the problem of illicit trafficking was foreseen. After the technical expertise carried out by the Environmental Data Centre the first border guards and customs control points were equipped with portable measurement devices. By assistance of Nordic countries and USA this system is under constant development, but full scope conceptual analysis of entire problem is not yet finished. The need for further development of the training capabilities, as well as information sharing among all relevant institutions and awareness building for decision-makers still remains. (author)

  5. Direct adaptive control using feedforward neural networks

    OpenAIRE

    Cajueiro, Daniel Oliveira; Hemerly, Elder Moreira

    2003-01-01

    ABSTRACT: This paper proposes a new scheme for direct neural adaptive control that works efficiently employing only one neural network, used for simultaneously identifying and controlling the plant. The idea behind this structure of adaptive control is to compensate the control input obtained by a conventional feedback controller. The neural network training process is carried out by using two different techniques: backpropagation and extended Kalman filter algorithm. Additionally, the conver...

  6. International nuclear cooperation in Asia

    International Nuclear Information System (INIS)

    Lim, Yong-Kyu

    1987-01-01

    Nuclear power project traditionally involve huge financial investment, highly sophisticated technology, and long lead time. Many countries, particularly developing ones, find it impossible to implement their nuclear power programs without technical cooperation and assistance from advanced countries. In this Asia and Pacific Region, seven countries have commercial nuclear power units in operation and/or under construction. Korea has six nuclear power units in operation, and three under construction. Active nuclear cooperation has been instrumental in implementing her abmitious nuclear power programs successfully. Nuclear cooperation is one of the widely recognized necessities, which is quite often talked about among the countries of the Asia and Pacific Region. But the differences in nuclear maturity and national interests among those in the region seem to be standing against it. Given the constraints, it is not easy to select appropriate areas for cooperation. There is no doubt, however, that they should include the nuclear policy, nuclear safety, radwaste management, radiological protection, and the management of nuclear units. In order to effectively promote nuclear cooperation in the Region, the scope of RCA activities must be expanded to include the nuclear power area. The Regional Nuclear Data Bank, the Regional Training Center and the Nuclear Emergency Response Center, for example, would be the effective tools for cooperation to meet the demands of the countries in the Region. In view of the technological gap between Japan and all others in the region, we cannot speak of a regional nuclear cooperation without heavily counting on Japan, the most advanced nuclear state in the region. For these reasons, Japan is expected to share an increasing portion of her nuclear technology with others. (author)

  7. Nuclear Manpower Training

    International Nuclear Information System (INIS)

    Han, K. W.; Lee, H. Y.; Lee, E. J. and others

    2004-12-01

    Through the project on nuclear human resources development in 2004, the Nuclear Training Center of KAERI has provided various nuclear education and training courses for 1,962 persons from the domestic nuclear related organizations such as Government Agencies, nuclear industries, R and D institutes, universities, and public as well as from IAEA Member States. The NTC has developed education programs for master/doctorial course on advanced nuclear engineering in cooperation with the University of Science and Technology which was established in 2003. Additionally, nuclear education programs such as nuclear technical training courses for the promotion of cooperation with member countries, have developed during the project period. The center has also developed and conducted 7 training courses on nuclear related technology. In parallel, the center has produced 20 training materials including textbooks, 3 multi-media education materials, and 56 Video On Demand (VOD) cyber training materials. In order to promote international cooperation for human resources development, the NTC has implemented a sub-project on the establishment of a web-portal including database for the exchange of information and materials within the framework of ANENT. Also, the center has cooperated with FNCA member countries to establish a model of human resources development, as well as with member countries on bilateral cooperation bases to develop training programs. The International Nuclear Training and Education Center (INTEC), which was opened in 2002, has hosted 318 international and domestic events (training courses, conferences, workshops, etc.) during the project period

  8. Neural network signal understanding for instrumentation

    DEFF Research Database (Denmark)

    Pau, L. F.; Johansen, F. S.

    1990-01-01

    understanding research is surveyed, and the selected implementation and its performance in terms of correct classification rates and robustness to noise are described. Formal results on neural net training time and sensitivity to weights are given. A theory for neural control using functional link nets is given...

  9. Deciphering the Cognitive and Neural Mechanisms Underlying ...

    International Development Research Centre (IDRC) Digital Library (Canada)

    Deciphering the Cognitive and Neural Mechanisms Underlying Auditory Learning. This project seeks to understand the brain mechanisms necessary for people to learn to perceive sounds. Neural circuits and learning. The research team will test people with and without musical training to evaluate their capacity to learn ...

  10. 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

  11. International co-operation

    International Nuclear Information System (INIS)

    1998-01-01

    In this part the are reviewed: Co-operation with IAEA; Participation of the Slovakia on the 41 st session of the General Conference; The comprehensive Nuclear-Test-Ban Treaty Organization; Co-operation with the Organization for Economic Co-operation and Development; co-operation with the European Commission; Fulfillment of obligations resulting from the international contracting documents

  12. Sorting and sustaining cooperation

    DEFF Research Database (Denmark)

    Vikander, Nick

    2013-01-01

    This paper looks at cooperation in teams where some people are selfish and others are conditional cooperators, and where lay-offs will occur at a fixed future date. I show that the best way to sustain cooperation prior to the lay-offs is often in a sorting equilibrium, where conditional cooperators...... can identify and then work with one another. Changes to parameters that would seem to make cooperation more attractive, such as an increase in the discount factor or the fraction of conditional cooperators, can reduce equilibrium cooperation if they decrease a selfish player's incentive to sort....

  13. China-Africa: New Directions of Cooperation

    Directory of Open Access Journals (Sweden)

    L V Ponomarenko

    2015-12-01

    Full Text Available This article analyzes the policy of fifth generation of Chinese leadership with regard to African states. The article deals with the concept of “Chinese Dream”, which was first declared in Africa, an innovative model of international cooperation in the framework of the formation of “economic zone of the Silk Road”. The authors reveal three basic directions of cooperation - political, economic and humanitarian cooperation. Political cooperation is characterized by the activation of mutual visits at the highest level, the interaction in the framework of the UN General Assembly, participation in UN peacekeeping operations. Economic cooperation is characterized by the activation of bilateral trade, the transition to a “modernized version of” investment cooperation, implementation of the strategy of “going abroad” of Chinese products, imports of natural resources from Africa, creating jobs for the local population, financing of infrastructure projects, the transfer of labor-intensive industries in Africa. Humanitarian cooperation includes training program for Africa, the implementation of the Sino-African programs, technology partnerships, research and exchange, and the China-Africa Forum “Think Tank”. Cooperation in health care also plays an important role. The authors note that the new Chinese leadership declares transition to an upgraded version of the Sino-African cooperation.

  14. Comparison of Support Vector Machine, Neural Network, and CART Algorithms for the Land-Cover Classification Using Limited Training Data Points

    Science.gov (United States)

    Support vector machine (SVM) was applied for land-cover characterization using MODIS time-series data. Classification performance was examined with respect to training sample size, sample variability, and landscape homogeneity (purity). The results were compared to two convention...

  15. Modeling of steam generator in nuclear power plant using neural network ensemble

    International Nuclear Information System (INIS)

    Lee, S. K.; Lee, E. C.; Jang, J. W.

    2003-01-01

    Neural network is now being used in modeling the steam generator is known to be difficult due to the reverse dynamics. However, Neural network is prone to the problem of overfitting. This paper investigates the use of neural network combining methods to model steam generator water level and compares with single neural network. The results show that neural network ensemble is effective tool which can offer improved generalization, lower dependence of the training set and reduced training time

  16. Evolvable synthetic neural system

    Science.gov (United States)

    Curtis, Steven A. (Inventor)

    2009-01-01

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

  17. Neural networks and orbit control in accelerators

    International Nuclear Information System (INIS)

    Bozoki, E.; Friedman, A.

    1994-01-01

    An overview of the architecture, workings and training of Neural Networks is given. We stress the aspects which are important for the use of Neural Networks for orbit control in accelerators and storage rings, especially its ability to cope with the nonlinear behavior of the orbit response to 'kicks' and the slow drift in the orbit response during long-term operation. Results obtained for the two NSLS storage rings with several network architectures and various training methods for each architecture are given

  18. Face recognition based on improved BP neural network

    Directory of Open Access Journals (Sweden)

    Yue Gaili

    2017-01-01

    Full Text Available In order to improve the recognition rate of face recognition, face recognition algorithm based on histogram equalization, PCA and BP neural network is proposed. First, the face image is preprocessed by histogram equalization. Then, the classical PCA algorithm is used to extract the features of the histogram equalization image, and extract the principal component of the image. And then train the BP neural network using the trained training samples. This improved BP neural network weight adjustment method is used to train the network because the conventional BP algorithm has the disadvantages of slow convergence, easy to fall into local minima and training process. Finally, the BP neural network with the test sample input is trained to classify and identify the face images, and the recognition rate is obtained. Through the use of ORL database face image simulation experiment, the analysis results show that the improved BP neural network face recognition method can effectively improve the recognition rate of face recognition.

  19. Prediction based chaos control via a new neural network

    International Nuclear Information System (INIS)

    Shen Liqun; Wang Mao; Liu Wanyu; Sun Guanghui

    2008-01-01

    In this Letter, a new chaos control scheme based on chaos prediction is proposed. To perform chaos prediction, a new neural network architecture for complex nonlinear approximation is proposed. And the difficulty in building and training the neural network is also reduced. Simulation results of Logistic map and Lorenz system show the effectiveness of the proposed chaos control scheme and the proposed neural network

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

    Energy Technology Data Exchange (ETDEWEB)

    2017-03-28

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

  1. Analysis of neural networks in terms of domain functions

    NARCIS (Netherlands)

    van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, Lambert

    Despite their success-story, artificial neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more as a

  2. To cooperate or not to cooperate

    DEFF Research Database (Denmark)

    Wessels, Josepha Ivanka

    To Cooperate or not to Cooperate...? discusses results of a research project to study the rehabilitation of 1500-year old water tunnels, so called "qanats", in Syria. Communities all over the world are using traditional technologies to extract drinkingwater, irrigate their lands and feed...... their livestock. But these often sustainable and ancient ways to make use of groundwater are in rapid decline worldwide. A research project started in 1999 to study the rehabilitation of 1500-year old water tunnels called "qanats"in Syria. To Cooperate or not to Cooperate...? discusses results and outcomes...

  3. The visual development of hand-centered receptive fields in a neural network model of the primate visual system trained with experimentally recorded human gaze changes.

    Science.gov (United States)

    Galeazzi, Juan M; Navajas, Joaquín; Mender, Bedeho M W; Quian Quiroga, Rodrigo; Minini, Loredana; Stringer, Simon M

    2016-01-01

    Neurons have been found in the primate brain that respond to objects in specific locations in hand-centered coordinates. A key theoretical challenge is to explain how such hand-centered neuronal responses may develop through visual experience. In this paper we show how hand-centered visual receptive fields can develop using an artificial neural network model, VisNet, of the primate visual system when driven by gaze changes recorded from human test subjects as they completed a jigsaw. A camera mounted on the head captured images of the hand and jigsaw, while eye movements were recorded using an eye-tracking device. This combination of data allowed us to reconstruct the retinal images seen as humans undertook the jigsaw task. These retinal images were then fed into the neural network model during self-organization of its synaptic connectivity using a biologically plausible trace learning rule. A trace learning mechanism encourages neurons in the model to learn to respond to input images that tend to occur in close temporal proximity. In the data recorded from human subjects, we found that the participant's gaze often shifted through a sequence of locations around a fixed spatial configuration of the hand and one of the jigsaw pieces. In this case, trace learning should bind these retinal images together onto the same subset of output neurons. The simulation results consequently confirmed that some cells learned to respond selectively to the hand and a jigsaw piece in a fixed spatial configuration across different retinal views.

  4. International cooperation workshop. Regional workshop for CTBTO international cooperation: Africa

    International Nuclear Information System (INIS)

    1999-08-01

    Pursuant to the 1999 programme of work, and following the International Cooperation Workshop held in Vienna, Austria, in 1998, the Provisional Technical Secretariat (PTS) of the Preparatory Commission for the CTBTO (Prep Com) held a regional Workshop for CTBTO International Cooperation in Cairo. The purpose of the workshop was to identify how and by what means the Africa region can promote international cooperation in CTBT verification related technologies, and how the region can benefit from and contribute to Prep Com activity. PTS staff briefed the 40 participants from 22 African States who attended the Workshop on general aspects, including costs, of the establishment and operation of the CTBT verification system, including its four monitoring technologies. Participants were informed on opportunities for local institutions in the establishment of monitoring stations and on possible support for national and regional data centres. National experts presented their research and development activities and reviewed existing experiences on bi/multi-lateral cooperation. The main points of the discussion focused on the need to engage governments to advance signature/ratification, and further training opportunities for African states

  5. A model for integrating elementary neural functions into delayed-response behavior.

    Directory of Open Access Journals (Sweden)

    Thomas Gisiger

    2006-04-01

    Full Text Available It is well established that various cortical regions can implement a wide array of neural processes, yet the mechanisms which integrate these processes into behavior-producing, brain-scale activity remain elusive. We propose that an important role in this respect might be played by executive structures controlling the traffic of information between the cortical regions involved. To illustrate this hypothesis, we present a neural network model comprising a set of interconnected structures harboring stimulus-related activity (visual representation, working memory, and planning, and a group of executive units with task-related activity patterns that manage the information flowing between them. The resulting dynamics allows the network to perform the dual task of either retaining an image during a delay (delayed-matching to sample task, or recalling from this image another one that has been associated with it during training (delayed-pair association task. The model reproduces behavioral and electrophysiological data gathered on the inferior temporal and prefrontal cortices of primates performing these same tasks. It also makes predictions on how neural activity coding for the recall of the image associated with the sample emerges and becomes prospective during the training phase. The network dynamics proves to be very stable against perturbations, and it exhibits signs of scale-invariant organization and cooperativity. The present network represents a possible neural implementation for active, top-down, prospective memory retrieval in primates. The model suggests that brain activity leading to performance of cognitive tasks might be organized in modular fashion, simple neural functions becoming integrated into more complex behavior by executive structures harbored in prefrontal cortex and/or basal ganglia.

  6. A model for integrating elementary neural functions into delayed-response behavior.

    Science.gov (United States)

    Gisiger, Thomas; Kerszberg, Michel

    2006-04-01

    It is well established that various cortical regions can implement a wide array of neural processes, yet the mechanisms which integrate these processes into behavior-producing, brain-scale activity remain elusive. We propose that an important role in this respect might be played by executive structures controlling the traffic of information between the cortical regions involved. To illustrate this hypothesis, we present a neural network model comprising a set of interconnected structures harboring stimulus-related activity (visual representation, working memory, and planning), and a group of executive units with task-related activity patterns that manage the information flowing between them. The resulting dynamics allows the network to perform the dual task of either retaining an image during a delay (delayed-matching to sample task), or recalling from this image another one that has been associated with it during training (delayed-pair association task). The model reproduces behavioral and electrophysiological data gathered on the inferior temporal and prefrontal cortices of primates performing these same tasks. It also makes predictions on how neural activity coding for the recall of the image associated with the sample emerges and becomes prospective during the training phase. The network dynamics proves to be very stable against perturbations, and it exhibits signs of scale-invariant organization and cooperativity. The present network represents a possible neural implementation for active, top-down, prospective memory retrieval in primates. The model suggests that brain activity leading to performance of cognitive tasks might be organized in modular fashion, simple neural functions becoming integrated into more complex behavior by executive structures harbored in prefrontal cortex and/or basal ganglia.

  7. 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)

  8. Intelligent control and cooperation for mobile robots

    Science.gov (United States)

    Stingu, Petru Emanuel

    The topic discussed in this work addresses the current research being conducted at the Automation & Robotics Research Institute in the areas of UAV quadrotor control and heterogenous multi-vehicle cooperation. Autonomy can be successfully achieved by a robot under the following conditions: the robot has to be able to acquire knowledge about the environment and itself, and it also has to be able to reason under uncertainty. The control system must react quickly to immediate challenges, but also has to slowly adapt and improve based on accumulated knowledge. The major contribution of this work is the transfer of the ADP algorithms from the purely theoretical environment to the complex real-world robotic platforms that work in real-time and in uncontrolled environments. Many solutions are adopted from those present in nature because they have been proven to be close to optimal in very different settings. For the control of a single platform, reinforcement learning algorithms are used to design suboptimal controllers for a class of complex systems that can be conceptually split in local loops with simpler dynamics and relatively weak coupling to the rest of the system. Optimality is enforced by having a global critic but the curse of dimensionality is avoided by using local actors and intelligent pre-processing of the information used for learning the optimal controllers. The system model is used for constructing the structure of the control system, but on top of that the adaptive neural networks that form the actors use the knowledge acquired during normal operation to get closer to optimal control. In real-world experiments, efficient learning is a strong requirement for success. This is accomplished by using an approximation of the system model to focus the learning for equivalent configurations of the state space. Due to the availability of only local data for training, neural networks with local activation functions are implemented. For the control of a formation

  9. Cooperation in research and development

    International Nuclear Information System (INIS)

    Ramanna, R.

    1977-01-01

    In planning scientific programs for rapid and extensive peaceful applications of atomic energy in any developing country, it is not fully realized that one of the most important inputs is a strong research and development (R and D) base with a well-oriented training program. The paper discusses the various ways in which R and D is required to assist in both indigenous and turnkey projects. The R and D organization should be broad based; i.e., it should have physicists, chemists (particularly specialists in water chemistry), health physicists, and engineers (particularly metallurgists for materials development, study of corrosion problems, etc.). The role of electronic engineers is also very significant from the viewpoint of designing reactor control systems. Another important advantage of having an R and D program is its general technological fallout, which aids the entire industrial structure of the country. The concept of regional cooperation is very important, particularly for atomic energy programs in developing countries that have similar conditions and levels of technological skills. This cooperation can be bilateral or multilateral under the auspices of the International Atomic Energy Agency. Scientists from several countries have been trained in our Center, and we also had a very successful India-Philippines-Agency Project in which scientists from many countries in the region participated in cooperative research programs

  10. Fifty years of Technical Cooperation

    International Nuclear Information System (INIS)

    2007-01-01

    The International Atomic Energy Agency (IAEA) was established in Vienna in 1957. The Statute of the IAEA, approved by 81 nations, founded the organization on three pillars: nuclear verification; safety and security; and the transfer of technology. Today, these three pillars still remain at the heart of the organization's work. However, the way in which the IAEA carries out this work, particularly with regard to technology transfer, has changed greatly over the years. When the IAEA opened for business, nuclear science and technology were in their infancy. Many Member States had no nuclear capacity at all. The IAEA's 'technical assistance' programme, as it was then known, was modest. Early projects were small in scale and short lived, focusing mainly on building human capacities and creating institutions and facilities that would support the introduction of nuclear technology in a safe and effective manner. Today, the picture is more complex. Instead of merely offering assistance, the IAEA focuses on cooperation for sustainable socioeconomic development, building on the skills and infrastructure that Member States have acquired over the past five decades. Member States are full partners in the process, guiding the IAEA's technical cooperation activities, setting national and regional priorities, and offering training opportunities and technical support to the IAEA and to other Member States. Technical cooperation between developing countries is facilitated and supported through regional cooperative agreements. Regional centres of expertise play an important role in sharing the benefits of nuclear science and technology among Member States

  11. 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...

  12. Machine Learning Topological Invariants with Neural Networks

    Science.gov (United States)

    Zhang, Pengfei; Shen, Huitao; Zhai, Hui

    2018-02-01

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

  13. Cooperation, trust and confidence

    NARCIS (Netherlands)

    Korver, T.; Oeij, P.R.A.; Urze, P.C.G.D.

    2007-01-01

    Environmental complexity may strain cooperative relationships, both within and beyond organizations, for two reasons. First, when complexity implies uncertainty the predictability of change disappears. Secondly, change may and often will entail different estimates of the cooperating partners on the

  14. Cooperative Tagging Center (CTC)

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Cooperative Tagging Center (CTC) began as the Cooperative Game Fish Tagging Program (GTP) at Woods Hole Oceanographic Institute (WHOI) in 1954. The GTP was...

  15. Cooperatives as Entrants

    OpenAIRE

    Richard J. Sexton; Terri A. Sexton

    1987-01-01

    A potential shortcoming of game-theoretic models in industrial organization is their failure to consider consumers as players. We introduce a customer coalition --- a cooperative -- as a potential entrant and compare the cooperative entry threat with that posed by the usual for-profit entrant. We identify four fundamental distinctions between cooperative and for-profit entrants and demonstrate that the strategic interplay between a cooperative and an incumbent firm may differ markedly from th...

  16. Inertia in Cooperative Remodeling

    OpenAIRE

    Nilsson, Jerker

    1997-01-01

    Which organization model is appropriate for a cooperative enterprise depends on the prerequisites in its business environment. When conditions are changing, the firm must adapt itself. The entry of Sweden, Finland, and Austria into the European Union led to radical changes for agricultural cooperation, especially for Swedish cooperatives since agricultural policy was not allowed a transitional period. After two years, Swedish cooperatives have still not adapted their organization model despit...

  17. What is a cooperative?

    Science.gov (United States)

    Kimberly Zeuli

    2006-01-01

    Groups of individuals throughout time have worked together in pursuit of common goals. The earliest forms of hunting and agriculture required a great deal of cooperation among humans. Although the word "cooperative" can be applied to many different types of group activities, in this publication it refers to a formal business model. Cooperative businesses are...

  18. Alternative vision or utopian fantasy? Cooperation, empowerment and women's cooperative development in India.

    Science.gov (United States)

    Mayoux, L

    1995-01-01

    The discussion addresses the costs and benefits of working in cooperatives in India, imposed participation, methods for increasing incomes, preconceived models, the importance of meeting the actual needs of women, and participatory options. This author evaluated 10 producer cooperatives in West Bengal, Karnataka, and Tamil Nadu during 1984-92. It is argued that more discussion is needed on how ideals of cooperation and empowerment of women can occur simultaneous with the context in which cooperatives must operate. The ten study cooperatives were all officially registered cooperatives. Cooperatives varied in size, organizational structure, and forms of support. Four were determined to be successful in economic and participatory terms. Three were successful because of the efforts of the women themselves. All three cases were based on earning goals that were higher than the women could have achieved on their own. Six failed in terms of participatory decision making and cooperative operations. Lack of sufficient support and/or excessive bureaucratic red tape were involved in the six failures, but to varying degrees. Type of support and means of implementation were important in the six failures. All women used cooperatives as a means of increasing income. Participation rules were imposed by outside agencies. Women were given "cooperative" training. Disputes occurred because women selected to power positions were powerful leaders outside the cooperative. Consensus was difficult to reach. There were conflicts of interest between different departments. Quality control was made difficult by women's inability to provide discipline. Personal conflicts from outside were carried on within the cooperative. Incomes could be improved by training women in local marketing and networking, insuring adequate resources and capital, and providing savings schemes. Gender inequalities were a key factor limiting income for women, but cooperatives did not address this issue. Gains for women

  19. DOE/ABACC safeguards cooperation

    International Nuclear Information System (INIS)

    Whitaker, J.M.; Toth, P.; Rubio, J.

    1995-01-01

    In 1994, the US Department of Energy (DOE) and the Brazilian-Argentine Agency for Accounting and Control of Nuclear Materials (ABACC) signed a safeguards cooperation agreement. The agreement provides for cooperation in the areas of nuclear material control, accountancy, verification, and advanced containment and surveillance technologies for international safeguards applications. ABACC is an international safeguards organization responsible for verifying the commitments of a 1991 bilateral agreement between Argentina and Brazil in which both countries agreed to submit all nuclear material in all nuclear activities to a Common System of Accounting and Control of Nuclear Materials (SCCC). DOE provides critical assistance (including equipment and training) through the Office of Nonproliferation and National Security to countries and international organizations to enhance their capabilities to control and verify nuclear material inventories. Specific activities initiated under the safeguards agreement include: (1) active US participation in ABACC's safeguards training courses, (2) joint development of specialized measurement training workshops, (3) characterization of laboratory standards, and (4) development and application of an extensive analytical laboratory comparison program. The results realized from these initial activities have been mutually beneficial in regard to strengthening the application of international safeguards in Argentina and Brazil

  20. Designing for cooperation - cooperating in design

    DEFF Research Database (Denmark)

    Kyng, Morten

    1991-01-01

    This article will discuss how to design computer applications that enhance the quality of work and products, and will relate the discussion to current themes in the field of Computer-Supported Cooperative Work (CSCW). Cooperation is a key element of computer use and work practice, yet here...... a specific "CSCW approach is not taken." Instead the focus is cooperation as an important aspect of work that should be integrated into most computer support efforts in order to develop successful computer support, however, other aspects such as power, conflict and control must also be considered....

  1. Construction of multi-agent mobile robots control system in the problem of persecution with using a modified reinforcement learning method based on neural networks

    Science.gov (United States)

    Patkin, M. L.; Rogachev, G. N.

    2018-02-01

    A method for constructing a multi-agent control system for mobile robots based on training with reinforcement using deep neural networks is considered. Synthesis of the management system is proposed to be carried out with reinforcement training and the modified Actor-Critic method, in which the Actor module is divided into Action Actor and Communication Actor in order to simultaneously manage mobile robots and communicate with partners. Communication is carried out by sending partners at each step a vector of real numbers that are added to the observation vector and affect the behaviour. Functions of Actors and Critic are approximated by deep neural networks. The Critics value function is trained by using the TD-error method and the Actor’s function by using DDPG. The Communication Actor’s neural network is trained through gradients received from partner agents. An environment in which a cooperative multi-agent interaction is present was developed, computer simulation of the application of this method in the control problem of two robots pursuing two goals was carried out.

  2. Neural Decoder for Topological Codes

    Science.gov (United States)

    Torlai, Giacomo; Melko, Roger G.

    2017-07-01

    We present an algorithm for error correction in topological codes that exploits modern machine learning techniques. Our decoder is constructed from a stochastic neural network called a Boltzmann machine, of the type extensively used in deep learning. We provide a general prescription for the training of the network and a decoding strategy that is applicable to a wide variety of stabilizer codes with very little specialization. We demonstrate the neural decoder numerically on the well-known two-dimensional toric code with phase-flip errors.

  3. Empirical Investigation of Optimization Algorithms in Neural Machine Translation

    Directory of Open Access Journals (Sweden)

    Bahar Parnia

    2017-06-01

    Full Text Available Training neural networks is a non-convex and a high-dimensional optimization problem. In this paper, we provide a comparative study of the most popular stochastic optimization techniques used to train neural networks. We evaluate the methods in terms of convergence speed, translation quality, and training stability. In addition, we investigate combinations that seek to improve optimization in terms of these aspects. We train state-of-the-art attention-based models and apply them to perform neural machine translation. We demonstrate our results on two tasks: WMT 2016 En→Ro and WMT 2015 De→En.

  4. An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

    Energy Technology Data Exchange (ETDEWEB)

    Schuman, Catherine D [ORNL; Plank, James [University of Tennessee (UT); Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)

    2016-01-01

    As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

  5. Cooperative strategies European perspectives

    CERN Document Server

    Killing, J Peter

    1997-01-01

    Cooperative Strategies: European Perspectives is one of three geographically targeted volumes in which the contributors present the most current research on topics such as advances in theories of cooperative strategies, the formation of cooperative alliances, the dynamics of partner relationships, and the role of information and knowledge in cooperative alliances. Blending conceptual insights with empirical analyses, the contributors highlight commonalities and differences across national, cultural, and trade zones. The chapters in this volume are anchored in a wide set of theoretical approaches, conceptual frameworks, and models, illustrating how rich the area of cooperative strategies is for scholarly inquiry.

  6. Cooperation arrangements related to technology transfer

    International Nuclear Information System (INIS)

    Eysel, G.

    1986-04-01

    A developing country which considers to launch a nuclear program should put as much as possible efforts to elaborate a program which suits the country's needs as well as reflects its capabilities. It deems advantageous that a developing country makes use of the experience and knowledge in the nuclear field of a partner country already in the phase when exploring the technical and commercial aspects of a nuclear power program. For the different stages of cooperation between two countries a three-level concept appears advisable for establishing the basis for individual cooperation agreement. The first level are agreements between the governments of both countries on joint scientific research projects and technical development programs covering a broad spectrum of activities not limited to the energy sector. At the second level cooperation agreements can already concentrate on the energy sector and e.g. specifically investigate the energy structure of the developing country. If this investigation results in the decision of the developing country to establish a nuclear power program the next level will cover a broad based cooperation in the nuclear field including a large number of different cooperation contracts in various fields. In this stage of bilateral cooperation the main emphasis will be put on industrial cooperation. Cooperation agreements to be concluded between respective partners of both countries may cover fields related to research and development, engineering of a nuclear power plant, manufacturing of its components, erection and installation as well as operation of the plant. The most common agreements refer to technical cooperation, which covers not only the transfer of blueprints but also training of the recipient's personnel in the partner's country and delegation of experts to the recipient's country. The most comprehensive form of cooperation is the foundation of a joint venture company where the technology partner does not only transfer his know

  7. Statistical analysis in the design of nuclear fuel cells and training of a neural network to predict safety parameters for reactors BWR

    International Nuclear Information System (INIS)

    Jauregui Ch, V.

    2013-01-01

    In this work the obtained results for a statistical analysis are shown, with the purpose of studying the performance of the fuel lattice, taking into account the frequency of the pins that were used. For this objective, different statistical distributions were used; one approximately to normal, another type X 2 but in an inverse form and a random distribution. Also, the prediction of some parameters of the nuclear reactor in a fuel reload was made through a neuronal network, which was trained. The statistical analysis was made using the parameters of the fuel lattice, which was generated through three heuristic techniques: Ant Colony Optimization System, Neuronal Networks and a hybrid among Scatter Search and Path Re linking. The behavior of the local power peak factor was revised in the fuel lattice with the use of different frequencies of enrichment uranium pines, using the three techniques mentioned before, in the same way the infinite multiplication factor of neutrons was analyzed (k..), to determine within what range this factor in the reactor is. Taking into account all the information, which was obtained through the statistical analysis, a neuronal network was trained; that will help to predict the behavior of some parameters of the nuclear reactor, considering a fixed fuel reload with their respective control rods pattern. In the same way, the quality of the training was evaluated using different fuel lattices. The neuronal network learned to predict the next parameters: Shutdown Margin (SDM), the pin burn peaks for two different fuel batches, Thermal Limits and the Effective Neutron Multiplication Factor (k eff ). The results show that the fuel lattices in which the frequency, which the inverted form of the X 2 distribution, was used revealed the best values of local power peak factor. Additionally it is shown that the performance of a fuel lattice could be enhanced controlling the frequency of the uranium enrichment rods and the variety of the gadolinium

  8. Mirror neural training induced by virtual reality in brain-computer interfaces may provide a promising approach for the autism therapy.

    Science.gov (United States)

    Zhu, Huaping; Sun, Yaoru; Zeng, Jinhua; Sun, Hongyu

    2011-05-01

    Previous studies have suggested that the dysfunction of the human mirror neuron system (hMNS) plays an important role in the autism spectrum disorder (ASD). In this work, we propose a novel training program from our interdisciplinary research to improve mirror neuron functions of autistic individuals by using a BCI system with virtual reality technology. It is a promising approach for the autism to learn and develop social communications in a VR environment. A test method for this hypothesis is also provided. Copyright © 2011 Elsevier Ltd. All rights reserved.

  9. Neural Networks

    Directory of Open Access Journals (Sweden)

    Schwindling Jerome

    2010-04-01

    Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.

  10. A Scale Development for Teacher Competencies on Cooperative Learning Method

    Science.gov (United States)

    Kocabas, Ayfer; Erbil, Deniz Gokce

    2017-01-01

    Cooperative learning method is a learning method studied both in Turkey and in the world for long years as an active learning method. Although cooperative learning method takes place in training programs, it cannot be implemented completely in the direction of its principles. The results of the researches point out that teachers have problems with…

  11. High school music classes enhance the neural processing of speech.

    Science.gov (United States)

    Tierney, Adam; Krizman, Jennifer; Skoe, Erika; Johnston, Kathleen; Kraus, Nina

    2013-01-01

    Should music be a priority in public education? One argument for teaching music in school is that private music instruction relates to enhanced language abilities and neural function. However, the directionality of this relationship is unclear and it is unknown whether school-based music training can produce these enhancements. Here we show that 2 years of group music classes in high school enhance the neural encoding of speech. To tease apart the relationships between music and neural function, we tested high school students participating in either music or fitness-based training. These groups were matched at the onset of training on neural timing, reading ability, and IQ. Auditory brainstem responses were collected to a synthesized speech sound presented in background noise. After 2 years of training, the neural responses of the music training group were earlier than at pre-training, while the neural timing of students in the fitness training group was unchanged. These results represent the strongest evidence to date that in-school music education can cause enhanced speech encoding. The neural benefits of musical training are, therefore, not limited to expensive private instruction early in childhood but can be elicited by cost-effective group instruction during adolescence.

  12. Creating conditions for cooperative learning: Basic elements

    Directory of Open Access Journals (Sweden)

    Ševkušić-Mandić Slavica G.

    2003-01-01

    Full Text Available Although a large number of research evidence speak out in favor of cooperative learning, its effectiveness in teaching does not depend only on teacher’s and students’ enthusiasm and willingness to work in such a manner. Creating cooperative situations in learning demands a serious preparation and engagement on the part of teacher who is structuring various aspects of work in the classroom. Although there exist a large number of models and techniques of cooperative learning, which vary in the way in which students work together, in the structure of learning tasks as well as in the degree to which cooperative efforts of students are coupled with competition among groups, some elements should be present in the structure of conditions irrespective of the type of group work in question. Potential effects of cooperation are not likely to emerge unless teachers apply five basic elements of cooperative structure: 1. structuring of the learning task and students’ positive interdependence, 2. individual responsibility, 3. upgrading of "face to face" interaction, 4. training of students’ social skills, and 5. evaluation of group processes. The paper discusses various strategies for establishing the mentioned elements and concrete examples for teaching practice are provided, which should be of assistance to teachers for as much successful cooperative learning application as possible in work with children.

  13. 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.

  14. Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia.

    Science.gov (United States)

    Kim, Junghoe; Calhoun, Vince D; Shim, Eunsoo; Lee, Jong-Hwan

    2016-01-01

    Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was

  15. neural network based model o work based model of an industrial oil

    African Journals Online (AJOL)

    eobe

    technique. g, Neural Network Model, Regression, Mean Square Error, PID controller. ... during the training processes. An additio ... used to carry out simulation studies of the mode .... A two-layer feed-forward neural network with Matlab.

  16. Multi-robot Cooperation Behavior Decision Based on Psychological Values

    Directory of Open Access Journals (Sweden)

    Jian JIANG

    2014-01-01

    Full Text Available The method based on psychology concept has been proved to be a successful tool used for human-robot interaction. But its related research in multi-robot cooperation has remained scarce until recent studies. To solve the problem, a decision-making mechanism based on psychological values is presented to be regarded as the basis of the multi-robot cooperation. Robots give birth to psychological values based on the estimations of environment, teammates and themselves. The mapping relationship between psychological values and cooperation tendency threshold values is set up with artificial neural network. Robots can make decision on the bases of these threshold values in cooperation scenes. Experiments show that the multi-robot cooperation method presented in the paper not only can ensure the rationality of robots’ decision-making, but also can ensure the speediness of robots’ decision-making.

  17. Leap Motion-based virtual reality training for improving motor functional recovery of upper limbs and neural reorganization in subacute stroke patients

    Directory of Open Access Journals (Sweden)

    Zun-rong Wang

    2017-01-01

    Full Text Available Virtual reality is nowadays used to facilitate motor recovery in stroke patients. Most virtual reality studies have involved chronic stroke patients; however, brain plasticity remains good in acute and subacute patients. Most virtual reality systems are only applicable to the proximal upper limbs (arms because of the limitations of their capture systems. Nevertheless, the functional recovery of an affected hand is most difficult in the case of hemiparesis rehabilitation after a stroke. The recently developed Leap Motion controller can track the fine movements of both hands and fingers. Therefore, the present study explored the effects of a Leap Motion-based virtual reality system on subacute stroke. Twenty-six subacute stroke patients were assigned to an experimental group that received virtual reality training along with conventional occupational rehabilitation, and a control group that only received conventional rehabilitation. The Wolf motor function test (WMFT was used to assess the motor function of the affected upper limb; functional magnetic resonance imaging was used to measure the cortical activation. After four weeks of treatment, the motor functions of the affected upper limbs were significantly improved in all the patients, with the improvement in the experimental group being significantly better than in the control group. The action performance time in the WMFT significantly decreased in the experimental group. Furthermore, the activation intensity and the laterality index of the contralateral primary sensorimotor cortex increased in both the experimental and control groups. These results confirmed that Leap Motion-based virtual reality training was a promising and feasible supplementary rehabilitation intervention, could facilitate the recovery of motor functions in subacute stroke patients. The study has been registered in the Chinese Clinical Trial Registry (registration number: ChiCTR-OCH-12002238.

  18. Leap Motion-based virtual reality training for improving motor functional recovery of upper limbs and neural reorganization in subacute stroke patients

    Science.gov (United States)

    Wang, Zun-rong; Wang, Ping; Xing, Liang; Mei, Li-ping; Zhao, Jun; Zhang, Tong

    2017-01-01

    Virtual reality is nowadays used to facilitate motor recovery in stroke patients. Most virtual reality studies have involved chronic stroke patients; however, brain plasticity remains good in acute and subacute patients. Most virtual reality systems are only applicable to the proximal upper limbs (arms) because of the limitations of their capture systems. Nevertheless, the functional recovery of an affected hand is most difficult in the case of hemiparesis rehabilitation after a stroke. The recently developed Leap Motion controller can track the fine movements of both hands and fingers. Therefore, the present study explored the effects of a Leap Motion-based virtual reality system on subacute stroke. Twenty-six subacute stroke patients were assigned to an experimental group that received virtual reality training along with conventional occupational rehabilitation, and a control group that only received conventional rehabilitation. The Wolf motor function test (WMFT) was used to assess the motor function of the affected upper limb; functional magnetic resonance imaging was used to measure the cortical activation. After four weeks of treatment, the motor functions of the affected upper limbs were significantly improved in all the patients, with the improvement in the experimental group being significantly better than in the control group. The action performance time in the WMFT significantly decreased in the experimental group. Furthermore, the activation intensity and the laterality index of the contralateral primary sensorimotor cortex increased in both the experimental and control groups. These results confirmed that Leap Motion-based virtual reality training was a promising and feasible supplementary rehabilitation intervention, could facilitate the recovery of motor functions in subacute stroke patients. The study has been registered in the Chinese Clinical Trial Registry (registration number: ChiCTR-OCH-12002238). PMID:29239328

  19. Leap Motion-based virtual reality training for improving motor functional recovery of upper limbs and neural reorganization in subacute stroke patients.

    Science.gov (United States)

    Wang, Zun-Rong; Wang, Ping; Xing, Liang; Mei, Li-Ping; Zhao, Jun; Zhang, Tong

    2017-11-01

    Virtual reality is nowadays used to facilitate motor recovery in stroke patients. Most virtual reality studies have involved chronic stroke patients; however, brain plasticity remains good in acute and subacute patients. Most virtual reality systems are only applicable to the proximal upper limbs (arms) because of the limitations of their capture systems. Nevertheless, the functional recovery of an affected hand is most difficult in the case of hemiparesis rehabilitation after a stroke. The recently developed Leap Motion controller can track the fine movements of both hands and fingers. Therefore, the present study explored the effects of a Leap Motion-based virtual reality system on subacute stroke. Twenty-six subacute stroke patients were assigned to an experimental group that received virtual reality training along with conventional occupational rehabilitation, and a control group that only received conventional rehabilitation. The Wolf motor function test (WMFT) was used to assess the motor function of the affected upper limb; functional magnetic resonance imaging was used to measure the cortical activation. After four weeks of treatment, the motor functions of the affected upper limbs were significantly improved in all the patients, with the improvement in the experimental group being significantly better than in the control group. The action performance time in the WMFT significantly decreased in the experimental group. Furthermore, the activation intensity and the laterality index of the contralateral primary sensorimotor cortex increased in both the experimental and control groups. These results confirmed that Leap Motion-based virtual reality training was a promising and feasible supplementary rehabilitation intervention, could facilitate the recovery of motor functions in subacute stroke patients. The study has been registered in the Chinese Clinical Trial Registry (registration number: ChiCTR-OCH-12002238).

  20. Analysis of connectivity in NeuCube spiking neural network models trained on EEG data for the understanding of functional changes in the brain: A case study on opiate dependence treatment.

    Science.gov (United States)

    Capecci, Elisa; Kasabov, Nikola; Wang, Grace Y

    2015-08-01

    The paper presents a methodology for the analysis of functional changes in brain activity across different conditions and different groups of subjects. This analysis is based on the recently proposed NeuCube spiking neural network (SNN) framework and more specifically on the analysis of the connectivity of a NeuCube model trained with electroencephalography (EEG) data. The case study data used to illustrate this method is EEG data collected from three groups-subjects with opiate addiction, patients undertaking methadone maintenance treatment, and non-drug users/healthy control group. The proposed method classifies more accurately the EEG data than traditional statistical and artificial intelligence (AI) methods and can be used to predict response to treatment and dose-related drug effect. But more importantly, the method can be used to compare functional brain activities of different subjects and the changes of these activities as a result of treatment, which is a step towards a better understanding of both the EEG data and the brain processes that generated it. The method can also be used for a wide range of applications, such as a better understanding of disease progression or aging. Copyright © 2015 Elsevier Ltd. All rights reserved.

  1. Neural activation in stress-related exhaustion

    DEFF Research Database (Denmark)

    Gavelin, Hanna Malmberg; Neely, Anna Stigsdotter; Andersson, Micael

    2017-01-01

    The primary purpose of this study was to investigate the association between burnout and neural activation during working memory processing in patients with stress-related exhaustion. Additionally, we investigated the neural effects of cognitive training as part of stress rehabilitation. Fifty...... association between burnout level and working memory performance was found, however, our findings indicate that frontostriatal neural responses related to working memory were modulated by burnout severity. We suggest that patients with high levels of burnout need to recruit additional cognitive resources...... to uphold task performance. Following cognitive training, increased neural activation was observed during 3-back in working memory-related regions, including the striatum, however, low sample size limits any firm conclusions....

  2. Cooperative Trust Games

    Science.gov (United States)

    2013-01-01

    the more widely recognized competitive (non-cooperative) game theory. Cooperative game theory focuses on what groups of self-interested agents can...provides immediate justification for using non-cooperative game theory as the basis for modeling the purely competitive agents. 2.4. Superadditive...the competitive and altruistic contributions of the subset team. Definition: Given a payoff function ( ) in a subset team game , the total marginal

  3. Two distinct neural mechanisms underlying indirect reciprocity.

    Science.gov (United States)

    Watanabe, Takamitsu; Takezawa, Masanori; Nakawake, Yo; Kunimatsu, Akira; Yamasue, Hidenori; Nakamura, Mitsuhiro; Miyashita, Yasushi; Masuda, Naoki

    2014-03-18

    Cooperation is a hallmark of human society. Humans often cooperate with strangers even if they will not meet each other again. This so-called indirect reciprocity enables large-scale cooperation among nonkin and can occur based on a reputation mechanism or as a succession of pay-it-forward behavior. Here, we provide the functional and anatomical neural evidence for two distinct mechanisms governing the two types of indirect reciprocity. Cooperation occurring as reputation-based reciprocity specifically recruited the precuneus, a region associated with self-centered cognition. During such cooperative behavior, the precuneus was functionally connected with the caudate, a region linking rewards to behavior. Furthermore, the precuneus of a cooperative subject had a strong resting-state functional connectivity (rsFC) with the caudate and a large gray matter volume. In contrast, pay-it-forward reciprocity recruited the anterior insula (AI), a brain region associated with affective empathy. The AI was functionally connected with the caudate during cooperation occurring as pay-it-forward reciprocity, and its gray matter volume and rsFC with the caudate predicted the tendency of such cooperation. The revealed difference is consistent with the existing results of evolutionary game theory: although reputation-based indirect reciprocity robustly evolves as a self-interested behavior in theory, pay-it-forward indirect reciprocity does not on its own. The present study provides neural mechanisms underlying indirect reciprocity and suggests that pay-it-forward reciprocity may not occur as myopic profit maximization but elicit emotional rewards.

  4. International co-operation

    International Nuclear Information System (INIS)

    Klinda, J.; Lieskovska, Z.

    1998-01-01

    Within the Union Nations (UN) framework, the Slovak Republic participated in following activities on environment protection co-operation: UN European Economic Commission, UN Industrial Development Organization, UN Development Programme, UN Human Habitat Organization, UN Environment Programme, and UN Commission on Sustainable Development. Relevant activities of the Slovak Republic in these co-operations as well as in European Union and OECD activities are reviewed. International conventions and other forms of multilateral co-operation, bilateral co-operation, and international programmes and projects in which the Slovak Republic took participate are presented

  5. Cooperative Station History Forms

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Various forms, photographs and correspondence documenting the history of Cooperative station instrumentation, location changes, inspections, and...

  6. Neural network error correction for solving coupled ordinary differential equations

    Science.gov (United States)

    Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

    1992-01-01

    A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

  7. 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...

  8. Decentralized neural control application to robotics

    CERN Document Server

    Garcia-Hernandez, Ramon; Sanchez, Edgar N; Alanis, Alma y; Ruz-Hernandez, Jose A

    2017-01-01

    This book provides a decentralized approach for the identification and control of robotics systems. It also presents recent research in decentralized neural control and includes applications to robotics. Decentralized control is free from difficulties due to complexity in design, debugging, data gathering and storage requirements, making it preferable for interconnected systems. Furthermore, as opposed to the centralized approach, it can be implemented with parallel processors. This approach deals with four decentralized control schemes, which are able to identify the robot dynamics. The training of each neural network is performed on-line using an extended Kalman filter (EKF). The first indirect decentralized control scheme applies the discrete-time block control approach, to formulate a nonlinear sliding manifold. The second direct decentralized neural control scheme is based on the backstepping technique, approximated by a high order neural network. The third control scheme applies a decentralized neural i...

  9. Nonlinear programming with feedforward neural networks.

    Energy Technology Data Exchange (ETDEWEB)

    Reifman, J.

    1999-06-02

    We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf optimization tool.

  10. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    Lindsey, C.S.; Denby, B.; Haggerty, H.

    1992-10-01

    We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed

  11. A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

    Science.gov (United States)

    Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

    2018-01-01

    In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

  12. 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.)

  13. Neural network recognition of mammographic lesions

    International Nuclear Information System (INIS)

    Oldham, W.J.B.; Downes, P.T.; Hunter, V.

    1987-01-01

    A method for recognition of mammographic lesions through the use of neural networks is presented. Neural networks have exhibited the ability to learn the shape andinternal structure of patterns. Digitized mammograms containing circumscribed and stelate lesions were used to train a feedfoward synchronous neural network that self-organizes to stable attractor states. Encoding of data for submission to the network was accomplished by performing a fractal analysis of the digitized image. This results in scale invariant representation of the lesions. Results are discussed

  14. International human cooperation in Japan Atomic Energy Research Institute

    International Nuclear Information System (INIS)

    Shiba, Koreyuki; Kaieda, Keisuke; Makuuchi, Keizo; Takada, Kazuo; Nomura, Masayuki

    1997-01-01

    Rearing of talented persons in the area of nuclear energy is one of the important works in Japan Atomic Energy Research Institute. In this report, the present situations and future schedules of international human cooperation in this area wsere summarized. First, the recent activities of International Nuclear Technology Center were outlined in respect of international human cooperation. A study and training course which was started in cooperation with JICA and IAEA from the middle of eighties and the international nuclear safety seminar aiming at advancing the nuclear safety level of the world are now being put into practice. In addition, a study and training for rearing talented persons was started from 1996 to improve the nuclear safety level of the neighbouring countries. The activities of the nuclear research interchange system by Science and Technology Agency established in 1985 and Bilateral Co-operation Agreement from 1984 were explained and also various difficulties in the international cooperation were pointed out. (M.N.)

  15. Regional cooperation to stimulate technical progress

    International Nuclear Information System (INIS)

    Ridvan, M.; Ehjrej, P.L.

    1987-01-01

    The main principles of the IAEA regional agreement on co-operation in the field of researches, elaboration and training of specialists in nuclear science and engineering for the states of Asia and Pacific Ocean region (RAC) and of the ARCAL program in Latin America are considered. The RAC projects envisage co-operation in the field of medicine (radiotherapy and nuclear methods, sterilization, etc.), agriculture (nuclear methods, raising of plants, using radiation mutations, food irradiation, etc.), industry (application of isotopes and radiation technology) and others. The ARCAL projects comprise radiation protection, nuclear control instruments, nuclear analytic methods, radioimmune analysis in stock-breeding, product irradiation, nuclear information, etc

  16. Reconstruction of neutron spectra through neural networks

    International Nuclear Information System (INIS)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.

    2003-01-01

    A neural network has been used to reconstruct the neutron spectra starting from the counting rates of the detectors of the Bonner sphere spectrophotometric system. A group of 56 neutron spectra was selected to calculate the counting rates that would produce in a Bonner sphere system, with these data and the spectra it was trained the neural network. To prove the performance of the net, 12 spectra were used, 6 were taken of the group used for the training, 3 were obtained of mathematical functions and those other 3 correspond to real spectra. When comparing the original spectra of those reconstructed by the net we find that our net has a poor performance when reconstructing monoenergetic spectra, this attributes it to those characteristic of the spectra used for the training of the neural network, however for the other groups of spectra the results of the net are appropriate with the prospective ones. (Author)

  17. 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.

  18. Application of artificial neural network in radiographic diagnosis

    International Nuclear Information System (INIS)

    Piraino, D.; Amartur, S.; Richmond, B.; Schils, J.; Belhobek, G.

    1990-01-01

    This paper reports on an artificial neural network trained to rate the likelihood of different bone neoplasms when given a standard description of a radiograph. A three-layer back propagation algorithm was trained with descriptions of examples of bone neoplasms obtained from standard radiographic textbooks. Fifteen bone neoplasms obtained from clinical material were used as unknowns to test the trained artificial neural network. The artificial neural network correctly rated the pathologic diagnosis as the most likely diagnosis in 10 of the 15 unknown cases

  19. 76 FR 13663 - Cooper Tools, Currently Known as Apex Tool Group, LLC, Hicksville, OH; Amended Certification...

    Science.gov (United States)

    2011-03-14

    ... DEPARTMENT OF LABOR Employment and Training Administration [TA-W-71,652] Cooper Tools, Currently... Adjustment Assistance on April 27, 2010, applicable to workers of Cooper Tools, Hicksville, Ohio. The workers.... purchased Cooper Tools and is currently known as Apex Tool Group, LLC. Some workers separated from...

  20. Predisposed to cooperate

    Directory of Open Access Journals (Sweden)

    Cathryn Costello

    2013-09-01

    Full Text Available Recent research in Toronto and Geneva indicates that asylum seekers and refugees are predisposed to be cooperative with the refugee status determination system and other immigration procedures, and that the design of alternatives to detention can create, foster and support this cooperative predisposition – or can undermine or even demolish it.