Deep learning for computational chemistry.

PubMed

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

2017-06-15

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

Deep learning for computational chemistry

DOE Office of Scientific and Technical Information (OSTI.GOV)

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

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

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

ERIC Educational Resources Information Center

Peng, Yefei

2010-01-01

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

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

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.

Deinterlacing using modular neural network

NASA Astrophysics Data System (ADS)

Woo, Dong H.; Eom, Il K.; Kim, Yoo S.

2004-05-01

Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.

Prototype-Incorporated Emotional Neural Network.

PubMed

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

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

Establishing a Dynamic Self-Adaptation Learning Algorithm of the BP Neural Network and Its Applications

NASA Astrophysics Data System (ADS)

Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min

2015-12-01

In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.

Efficient and self-adaptive in-situ learning in multilayer memristor neural networks.

PubMed

Li, Can; Belkin, Daniel; Li, Yunning; Yan, Peng; Hu, Miao; Ge, Ning; Jiang, Hao; Montgomery, Eric; Lin, Peng; Wang, Zhongrui; Song, Wenhao; Strachan, John Paul; Barnell, Mark; Wu, Qing; Williams, R Stanley; Yang, J Joshua; Xia, Qiangfei

2018-06-19

Memristors with tunable resistance states are emerging building blocks of artificial neural networks. However, in situ learning on a large-scale multiple-layer memristor network has yet to be demonstrated because of challenges in device property engineering and circuit integration. Here we monolithically integrate hafnium oxide-based memristors with a foundry-made transistor array into a multiple-layer neural network. We experimentally demonstrate in situ learning capability and achieve competitive classification accuracy on a standard machine learning dataset, which further confirms that the training algorithm allows the network to adapt to hardware imperfections. Our simulation using the experimental parameters suggests that a larger network would further increase the classification accuracy. The memristor neural network is a promising hardware platform for artificial intelligence with high speed-energy efficiency.

Neural constraints on learning.

PubMed

Sadtler, Patrick T; Quick, Kristin M; Golub, Matthew D; Chase, Steven M; Ryu, Stephen I; Tyler-Kabara, Elizabeth C; Yu, Byron M; Batista, Aaron P

2014-08-28

Learning, whether motor, sensory or cognitive, requires networks of neurons to generate new activity patterns. As some behaviours are easier to learn than others, we asked if some neural activity patterns are easier to generate than others. Here we investigate whether an existing network constrains the patterns that a subset of its neurons is capable of exhibiting, and if so, what principles define this constraint. We employed a closed-loop intracortical brain-computer interface learning paradigm in which Rhesus macaques (Macaca mulatta) controlled a computer cursor by modulating neural activity patterns in the primary motor cortex. Using the brain-computer interface paradigm, we could specify and alter how neural activity mapped to cursor velocity. At the start of each session, we observed the characteristic activity patterns of the recorded neural population. The activity of a neural population can be represented in a high-dimensional space (termed the neural space), wherein each dimension corresponds to the activity of one neuron. These characteristic activity patterns comprise a low-dimensional subspace (termed the intrinsic manifold) within the neural space. The intrinsic manifold presumably reflects constraints imposed by the underlying neural circuitry. Here we show that the animals could readily learn to proficiently control the cursor using neural activity patterns that were within the intrinsic manifold. However, animals were less able to learn to proficiently control the cursor using activity patterns that were outside of the intrinsic manifold. These results suggest that the existing structure of a network can shape learning. On a timescale of hours, it seems to be difficult to learn to generate neural activity patterns that are not consistent with the existing network structure. These findings offer a network-level explanation for the observation that we are more readily able to learn new skills when they are related to the skills that we already possess.

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

PubMed

Nitta, Tohru

2017-10-01

We present a theoretical analysis of singular points of artificial deep neural networks, resulting in providing deep neural network models having no critical points introduced by a hierarchical structure. It is considered that such deep neural network models have good nature for gradient-based optimization. First, we show that there exist a large number of critical points introduced by a hierarchical structure in deep neural networks as straight lines, depending on the number of hidden layers and the number of hidden neurons. Second, we derive a sufficient condition for deep neural networks having no critical points introduced by a hierarchical structure, which can be applied to general deep neural networks. It is also shown that the existence of critical points introduced by a hierarchical structure is determined by the rank and the regularity of weight matrices for a specific class of deep neural networks. Finally, two kinds of implementation methods of the sufficient conditions to have no critical points are provided. One is a learning algorithm that can avoid critical points introduced by the hierarchical structure during learning (called avoidant learning algorithm). The other is a neural network that does not have some critical points introduced by the hierarchical structure as an inherent property (called avoidant neural network).

Learning control of inverted pendulum system by neural network driven fuzzy reasoning: The learning function of NN-driven fuzzy reasoning under changes of reasoning environment

NASA Technical Reports Server (NTRS)

Hayashi, Isao; Nomura, Hiroyoshi; Wakami, Noboru

1991-01-01

Whereas conventional fuzzy reasonings are associated with tuning problems, which are lack of membership functions and inference rule designs, a neural network driven fuzzy reasoning (NDF) capable of determining membership functions by neural network is formulated. In the antecedent parts of the neural network driven fuzzy reasoning, the optimum membership function is determined by a neural network, while in the consequent parts, an amount of control for each rule is determined by other plural neural networks. By introducing an algorithm of neural network driven fuzzy reasoning, inference rules for making a pendulum stand up from its lowest suspended point are determined for verifying the usefulness of the algorithm.

On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

PubMed Central

Tonelli, Paul; Mouret, Jean-Baptiste

2013-01-01

A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2) synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT). Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1) in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2) whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities. PMID:24236099

Neural-Network-Development Program

NASA Technical Reports Server (NTRS)

Phillips, Todd A.

1993-01-01

NETS, software tool for development and evaluation of neural networks, provides simulation of neural-network algorithms plus computing environment for development of such algorithms. Uses back-propagation learning method for all of networks it creates. Enables user to customize patterns of connections between layers of network. Also provides features for saving, during learning process, values of weights, providing more-precise control over learning process. Written in ANSI standard C language. Machine-independent version (MSC-21588) includes only code for command-line-interface version of NETS 3.0.

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

PubMed

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

2018-04-01

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

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

PubMed Central

Miconi, Thomas

2017-01-01

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior. DOI: http://dx.doi.org/10.7554/eLife.20899.001 PMID:28230528

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks.

PubMed

Miconi, Thomas

2017-02-23

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.

Neural networks for aircraft control

NASA Technical Reports Server (NTRS)

Linse, Dennis

1990-01-01

Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

Back-propagation learning of infinite-dimensional dynamical systems.

PubMed

Tokuda, Isao; Tokunaga, Ryuji; Aihara, Kazuyuki

2003-10-01

This paper presents numerical studies of applying back-propagation learning to a delayed recurrent neural network (DRNN). The DRNN is a continuous-time recurrent neural network having time delayed feedbacks and the back-propagation learning is to teach spatio-temporal dynamics to the DRNN. Since the time-delays make the dynamics of the DRNN infinite-dimensional, the learning algorithm and the learning capability of the DRNN are different from those of the ordinary recurrent neural network (ORNN) having no time-delays. First, two types of learning algorithms are developed for a class of DRNNs. Then, using chaotic signals generated from the Mackey-Glass equation and the Rössler equations, learning capability of the DRNN is examined. Comparing the learning algorithms, learning capability, and robustness against noise of the DRNN with those of the ORNN and time delay neural network, advantages as well as disadvantages of the DRNN are investigated.

Machine Learning Topological Invariants with Neural Networks

NASA Astrophysics Data System (ADS)

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.

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

PubMed Central

Sinapayen, Lana; Ikegami, Takashi

2017-01-01

Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle “Learning by Stimulation Avoidance” (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system. PMID:28158309

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

PubMed

Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi

2017-01-01

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

Neural network applications in telecommunications

NASA Technical Reports Server (NTRS)

Alspector, Joshua

1994-01-01

Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.

DCS-Neural-Network Program for Aircraft Control and Testing

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

2006-01-01

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

A renaissance of neural networks in drug discovery.

PubMed

Baskin, Igor I; Winkler, David; Tetko, Igor V

2016-08-01

Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach. In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps and associated methods, and a relatively new technique, deep learning. The most important technical issues are discussed including overfitting and its prevention through regularization, ensemble and multitask modeling, model interpretation, and estimation of applicability domain. Different aspects of using neural networks in drug discovery are considered: building structure-activity models with respect to various targets; predicting drug selectivity, toxicity profiles, ADMET and physicochemical properties; characteristics of drug-delivery systems and virtual screening. Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.

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

PubMed Central

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

2017-01-01

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. DOI: http://dx.doi.org/10.7554/eLife.21492.001 PMID:28084991

Geometrical structure of Neural Networks: Geodesics, Jeffrey's Prior and Hyper-ribbons

NASA Astrophysics Data System (ADS)

Hayden, Lorien; Alemi, Alex; Sethna, James

2014-03-01

Neural networks are learning algorithms which are employed in a host of Machine Learning problems including speech recognition, object classification and data mining. In practice, neural networks learn a low dimensional representation of high dimensional data and define a model manifold which is an embedding of this low dimensional structure in the higher dimensional space. In this work, we explore the geometrical structure of a neural network model manifold. A Stacked Denoising Autoencoder and a Deep Belief Network are trained on handwritten digits from the MNIST database. Construction of geodesics along the surface and of slices taken from the high dimensional manifolds reveal a hierarchy of widths corresponding to a hyper-ribbon structure. This property indicates that neural networks fall into the class of sloppy models, in which certain parameter combinations dominate the behavior. Employing this information could prove valuable in designing both neural network architectures and training algorithms. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No . DGE-1144153.

Neural learning of constrained nonlinear transformations

NASA Technical Reports Server (NTRS)

Barhen, Jacob; Gulati, Sandeep; Zak, Michail

1989-01-01

Two issues that are fundamental to developing autonomous intelligent robots, namely, rudimentary learning capability and dexterous manipulation, are examined. A powerful neural learning formalism is introduced for addressing a large class of nonlinear mapping problems, including redundant manipulator inverse kinematics, commonly encountered during the design of real-time adaptive control mechanisms. Artificial neural networks with terminal attractor dynamics are used. The rapid network convergence resulting from the infinite local stability of these attractors allows the development of fast neural learning algorithms. Approaches to manipulator inverse kinematics are reviewed, the neurodynamics model is discussed, and the neural learning algorithm is presented.

Multiple neural network approaches to clinical expert systems

NASA Astrophysics Data System (ADS)

Stubbs, Derek F.

1990-08-01

We briefly review the concept of computer aided medical diagnosis and more extensively review the the existing literature on neural network applications in the field. Neural networks can function as simple expert systems for diagnosis or prognosis. Using a public database we develop a neural network for the diagnosis of a major presenting symptom while discussing the development process and possible approaches. MEDICAL EXPERTS SYSTEMS COMPUTER AIDED DIAGNOSIS Biomedicine is an incredibly diverse and multidisciplinary field and it is not surprising that neural networks with their many applications are finding more and more applications in the highly non-linear field of biomedicine. I want to concentrate on neural networks as medical expert systems for clinical diagnosis or prognosis. Expert Systems started out as a set of computerized " ifthen" rules. Everything was reduced to boolean logic and the promised land of computer experts was said to be in sight. It never came. Why? First the computer code explodes as the number of " ifs" increases. All the " ifs" have to interact. Second experts are not very good at reducing expertise to language. It turns out that experts recognize patterns and have non-verbal left-brain intuition decision processes. Third learning by example rather than learning by rule is the way natural brains works and making computers work by rule-learning is hideously labor intensive. Neural networks can learn from example. They learn the results

Evolutionary neural networks for anomaly detection based on the behavior of a program.

PubMed

Han, Sang-Jun; Cho, Sung-Bae

2006-06-01

The process of learning the behavior of a given program by using machine-learning techniques (based on system-call audit data) is effective to detect intrusions. Rule learning, neural networks, statistics, and hidden Markov models (HMMs) are some of the kinds of representative methods for intrusion detection. Among them, neural networks are known for good performance in learning system-call sequences. In order to apply this knowledge to real-world problems successfully, it is important to determine the structures and weights of these call sequences. However, finding the appropriate structures requires very long time periods because there are no suitable analytical solutions. In this paper, a novel intrusion-detection technique based on evolutionary neural networks (ENNs) is proposed. One advantage of using ENNs is that it takes less time to obtain superior neural networks than when using conventional approaches. This is because they discover the structures and weights of the neural networks simultaneously. Experimental results with the 1999 Defense Advanced Research Projects Agency (DARPA) Intrusion Detection Evaluation (IDEVAL) data confirm that ENNs are promising tools for intrusion detection.

Hybrid computing using a neural network with dynamic external memory.

PubMed

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

2016-10-27

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

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

PubMed

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

Introduction to Concepts in Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Niebur, Dagmar

1995-01-01

This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.

Fuzzy and neural control

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1992-01-01

Fuzzy logic and neural networks provide new methods for designing control systems. Fuzzy logic controllers do not require a complete analytical model of a dynamic system and can provide knowledge-based heuristic controllers for ill-defined and complex systems. Neural networks can be used for learning control. In this chapter, we discuss hybrid methods using fuzzy logic and neural networks which can start with an approximate control knowledge base and refine it through reinforcement learning.

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

Hebbian based learning with winner-take-all for spiking neural networks

NASA Astrophysics Data System (ADS)

Gupta, Ankur; Long, Lyle

2009-03-01

Learning methods for spiking neural networks are not as well developed as the traditional neural networks that widely use back-propagation training. We propose and implement a Hebbian based learning method with winner-take-all competition for spiking neural networks. This approach is spike time dependent which makes it naturally well suited for a network of spiking neurons. Homeostasis with Hebbian learning is implemented which ensures stability and quicker learning. Homeostasis implies that the net sum of incoming weights associated with a neuron remains the same. Winner-take-all is also implemented for competitive learning between output neurons. We implemented this learning rule on a biologically based vision processing system that we are developing, and use layers of leaky integrate and fire neurons. The network when presented with 4 bars (or Gabor filters) of different orientation learns to recognize the bar orientations (or Gabor filters). After training, each output neuron learns to recognize a bar at specific orientation and responds by firing more vigorously to that bar and less vigorously to others. These neurons are found to have bell shaped tuning curves and are similar to the simple cells experimentally observed by Hubel and Wiesel in the striate cortex of cat and monkey.

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

PubMed

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

2017-01-01

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

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

PubMed Central

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

2017-01-01

The recent “deep learning revolution” in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems. PMID:28377709

An Introduction to Neural Networks for Hearing Aid Noise Recognition.

ERIC Educational Resources Information Center

Kim, Jun W.; Tyler, Richard S.

1995-01-01

This article introduces the use of multilayered artificial neural networks in hearing aid noise recognition. It reviews basic principles of neural networks, and offers an example of an application in which a neural network is used to identify the presence or absence of noise in speech. The ability of neural networks to "learn" the…

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

PubMed

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

2008-12-01

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

GA-based fuzzy reinforcement learning for control of a magnetic bearing system.

PubMed

Lin, C T; Jou, C P

2000-01-01

This paper proposes a TD (temporal difference) and GA (genetic algorithm)-based reinforcement (TDGAR) learning method and applies it to the control of a real magnetic bearing system. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to perform the reinforcement learning task. The TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network to guide the learning of the other network (the action network) which determines the outputs (actions) of the TDGAR learning system. The action network can be a normal neural network or a neural fuzzy network. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. The key concept of the TDGAR learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA such that the GA can evaluate the candidate solutions (chromosomes) regularly, even during periods without external feedback from the environment. This enables the GA to proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning since a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problem. The proposed TDGAR learning system has been used to control an active magnetic bearing (AMB) system in practice. A systematic design procedure is developed to achieve successful integration of all the subsystems including magnetic suspension, mechanical structure, and controller training. The results show that the TDGAR learning scheme can successfully find a neural controller or a neural fuzzy controller for a self-designed magnetic bearing system.

Model Of Neural Network With Creative Dynamics

NASA Technical Reports Server (NTRS)

Zak, Michail; Barhen, Jacob

1993-01-01

Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.

Application of machine learning methods for traffic signs recognition

NASA Astrophysics Data System (ADS)

Filatov, D. V.; Ignatev, K. V.; Deviatkin, A. V.; Serykh, E. V.

2018-02-01

This paper focuses on solving a relevant and pressing safety issue on intercity roads. Two approaches were considered for solving the problem of traffic signs recognition; the approaches involved neural networks to analyze images obtained from a camera in the real-time mode. The first approach is based on a sequential image processing. At the initial stage, with the help of color filters and morphological operations (dilatation and erosion), the area containing the traffic sign is located on the image, then the selected and scaled fragment of the image is analyzed using a feedforward neural network to determine the meaning of the found traffic sign. Learning of the neural network in this approach is carried out using a backpropagation method. The second approach involves convolution neural networks at both stages, i.e. when searching and selecting the area of the image containing the traffic sign, and when determining its meaning. Learning of the neural network in the second approach is carried out using the intersection over union function and a loss function. For neural networks to learn and the proposed algorithms to be tested, a series of videos from a dash cam were used that were shot under various weather and illumination conditions. As a result, the proposed approaches for traffic signs recognition were analyzed and compared by key indicators such as recognition rate percentage and the complexity of neural networks’ learning process.

Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases

PubMed Central

Ritchie, Marylyn D; White, Bill C; Parker, Joel S; Hahn, Lance W; Moore, Jason H

2003-01-01

Background Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. Results Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. Conclusion This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases. PMID:12846935

Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1990-01-01

Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.

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

NASA Technical Reports Server (NTRS)

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

1993-01-01

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

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

NASA Technical Reports Server (NTRS)

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

1992-01-01

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

A spiking neural network model of model-free reinforcement learning with high-dimensional sensory input and perceptual ambiguity.

PubMed

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach.

A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity

PubMed Central

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach. PMID:25734662

Parsing learning in networks using brain-machine interfaces.

PubMed

Orsborn, Amy L; Pesaran, Bijan

2017-10-01

Brain-machine interfaces (BMIs) define new ways to interact with our environment and hold great promise for clinical therapies. Motor BMIs, for instance, re-route neural activity to control movements of a new effector and could restore movement to people with paralysis. Increasing experience shows that interfacing with the brain inevitably changes the brain. BMIs engage and depend on a wide array of innate learning mechanisms to produce meaningful behavior. BMIs precisely define the information streams into and out of the brain, but engage wide-spread learning. We take a network perspective and review existing observations of learning in motor BMIs to show that BMIs engage multiple learning mechanisms distributed across neural networks. Recent studies demonstrate the advantages of BMI for parsing this learning and its underlying neural mechanisms. BMIs therefore provide a powerful tool for studying the neural mechanisms of learning that highlights the critical role of learning in engineered neural therapies. Copyright © 2017 Elsevier Ltd. All rights reserved.

Spatial features of synaptic adaptation affecting learning performance.

PubMed

Berger, Damian L; de Arcangelis, Lucilla; Herrmann, Hans J

2017-09-08

Recent studies have proposed that the diffusion of messenger molecules, such as monoamines, can mediate the plastic adaptation of synapses in supervised learning of neural networks. Based on these findings we developed a model for neural learning, where the signal for plastic adaptation is assumed to propagate through the extracellular space. We investigate the conditions allowing learning of Boolean rules in a neural network. Even fully excitatory networks show very good learning performances. Moreover, the investigation of the plastic adaptation features optimizing the performance suggests that learning is very sensitive to the extent of the plastic adaptation and the spatial range of synaptic connections.

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

PubMed

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance (similarity) measures. Results with the larger consistency will be more reliable.

A neural network with modular hierarchical learning

NASA Technical Reports Server (NTRS)

Baldi, Pierre F. (Inventor); Toomarian, Nikzad (Inventor)

1994-01-01

This invention provides a new hierarchical approach for supervised neural learning of time dependent trajectories. The modular hierarchical methodology leads to architectures which are more structured than fully interconnected networks. The networks utilize a general feedforward flow of information and sparse recurrent connections to achieve dynamic effects. The advantages include the sparsity of units and connections, the modular organization. A further advantage is that the learning is much more circumscribed learning than in fully interconnected systems. The present invention is embodied by a neural network including a plurality of neural modules each having a pre-established performance capability wherein each neural module has an output outputting present results of the performance capability and an input for changing the present results of the performance capabilitiy. For pattern recognition applications, the performance capability may be an oscillation capability producing a repeating wave pattern as the present results. In the preferred embodiment, each of the plurality of neural modules includes a pre-established capability portion and a performance adjustment portion connected to control the pre-established capability portion.

Learning and diagnosing faults using neural networks

NASA Technical Reports Server (NTRS)

Whitehead, Bruce A.; Kiech, Earl L.; Ali, Moonis

1990-01-01

Neural networks have been employed for learning fault behavior from rocket engine simulator parameters and for diagnosing faults on the basis of the learned behavior. Two problems in applying neural networks to learning and diagnosing faults are (1) the complexity of the sensor data to fault mapping to be modeled by the neural network, which implies difficult and lengthy training procedures; and (2) the lack of sufficient training data to adequately represent the very large number of different types of faults which might occur. Methods are derived and tested in an architecture which addresses these two problems. First, the sensor data to fault mapping is decomposed into three simpler mappings which perform sensor data compression, hypothesis generation, and sensor fusion. Efficient training is performed for each mapping separately. Secondly, the neural network which performs sensor fusion is structured to detect new unknown faults for which training examples were not presented during training. These methods were tested on a task of fault diagnosis by employing rocket engine simulator data. Results indicate that the decomposed neural network architecture can be trained efficiently, can identify faults for which it has been trained, and can detect the occurrence of faults for which it has not been trained.

Higher-order neural network software for distortion invariant object recognition

NASA Technical Reports Server (NTRS)

Reid, Max B.; Spirkovska, Lilly

1991-01-01

The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

Learning in Artificial Neural Systems

NASA Technical Reports Server (NTRS)

Matheus, Christopher J.; Hohensee, William E.

1987-01-01

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

How synapses can enhance sensibility of a neural network

NASA Astrophysics Data System (ADS)

Protachevicz, P. R.; Borges, F. S.; Iarosz, K. C.; Caldas, I. L.; Baptista, M. S.; Viana, R. L.; Lameu, E. L.; Macau, E. E. N.; Batista, A. M.

2018-02-01

In this work, we study the dynamic range in a neural network modelled by cellular automaton. We consider deterministic and non-deterministic rules to simulate electrical and chemical synapses. Chemical synapses have an intrinsic time-delay and are susceptible to parameter variations guided by learning Hebbian rules of behaviour. The learning rules are related to neuroplasticity that describes change to the neural connections in the brain. Our results show that chemical synapses can abruptly enhance sensibility of the neural network, a manifestation that can become even more predominant if learning rules of evolution are applied to the chemical synapses.

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

PubMed

Zenke, Friedemann; Ganguli, Surya

2018-06-01

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

Thermodynamic efficiency of learning a rule in neural networks

NASA Astrophysics Data System (ADS)

Goldt, Sebastian; Seifert, Udo

2017-11-01

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

Two-Stage Approach to Image Classification by Deep Neural Networks

NASA Astrophysics Data System (ADS)

Ososkov, Gennady; Goncharov, Pavel

2018-02-01

The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

Neural network-based model reference adaptive control system.

PubMed

Patino, H D; Liu, D

2000-01-01

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

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

PubMed

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.

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

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

1992-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

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

1995-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

Neural network based speech synthesizer: A preliminary report

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Mcintire, Gary

1987-01-01

A neural net based speech synthesis project is discussed. The novelty is that the reproduced speech was extracted from actual voice recordings. In essence, the neural network learns the timing, pitch fluctuations, connectivity between individual sounds, and speaking habits unique to that individual person. The parallel distributed processing network used for this project is the generalized backward propagation network which has been modified to also learn sequences of actions or states given in a particular plan.

Neural-network-directed alignment of optical systems using the laser-beam spatial filter as an example

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Krasowski, Michael J.; Weiland, Kenneth E.

1993-01-01

This report describes an effort at NASA Lewis Research Center to use artificial neural networks to automate the alignment and control of optical measurement systems. Specifically, it addresses the use of commercially available neural network software and hardware to direct alignments of the common laser-beam-smoothing spatial filter. The report presents a general approach for designing alignment records and combining these into training sets to teach optical alignment functions to neural networks and discusses the use of these training sets to train several types of neural networks. Neural network configurations used include the adaptive resonance network, the back-propagation-trained network, and the counter-propagation network. This work shows that neural networks can be used to produce robust sequencers. These sequencers can learn by example to execute the step-by-step procedures of optical alignment and also can learn adaptively to correct for environmentally induced misalignment. The long-range objective is to use neural networks to automate the alignment and operation of optical measurement systems in remote, harsh, or dangerous aerospace environments. This work also shows that when neural networks are trained by a human operator, training sets should be recorded, training should be executed, and testing should be done in a manner that does not depend on intellectual judgments of the human operator.

Generalized Adaptive Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1993-01-01

Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.

Function approximation using combined unsupervised and supervised learning.

PubMed

Andras, Peter

2014-03-01

Function approximation is one of the core tasks that are solved using neural networks in the context of many engineering problems. However, good approximation results need good sampling of the data space, which usually requires exponentially increasing volume of data as the dimensionality of the data increases. At the same time, often the high-dimensional data is arranged around a much lower dimensional manifold. Here we propose the breaking of the function approximation task for high-dimensional data into two steps: (1) the mapping of the high-dimensional data onto a lower dimensional space corresponding to the manifold on which the data resides and (2) the approximation of the function using the mapped lower dimensional data. We use over-complete self-organizing maps (SOMs) for the mapping through unsupervised learning, and single hidden layer neural networks for the function approximation through supervised learning. We also extend the two-step procedure by considering support vector machines and Bayesian SOMs for the determination of the best parameters for the nonlinear neurons in the hidden layer of the neural networks used for the function approximation. We compare the approximation performance of the proposed neural networks using a set of functions and show that indeed the neural networks using combined unsupervised and supervised learning outperform in most cases the neural networks that learn the function approximation using the original high-dimensional data.

A novel neural-wavelet approach for process diagnostics and complex system modeling

NASA Astrophysics Data System (ADS)

Gao, Rong

Neural networks have been effective in several engineering applications because of their learning abilities and robustness. However certain shortcomings, such as slow convergence and local minima, are always associated with neural networks, especially neural networks applied to highly nonlinear and non-stationary problems. These problems can be effectively alleviated by integrating a new powerful tool, wavelets, into conventional neural networks. The multi-resolution analysis and feature localization capabilities of the wavelet transform offer neural networks new possibilities for learning. A neural wavelet network approach developed in this thesis enjoys fast convergence rate with little possibility to be caught at a local minimum. It combines the localization properties of wavelets with the learning abilities of neural networks. Two different testbeds are used for testing the efficiency of the new approach. The first is magnetic flowmeter-based process diagnostics: here we extend previous work, which has demonstrated that wavelet groups contain process information, to more general process diagnostics. A loop at Applied Intelligent Systems Lab (AISL) is used for collecting and analyzing data through the neural-wavelet approach. The research is important for thermal-hydraulic processes in nuclear and other engineering fields. The neural-wavelet approach developed is also tested with data from the electric power grid. More specifically, the neural-wavelet approach is used for performing short-term and mid-term prediction of power load demand. In addition, the feasibility of determining the type of load using the proposed neural wavelet approach is also examined. The notion of cross scale product has been developed as an expedient yet reliable discriminator of loads. Theoretical issues involved in the integration of wavelets and neural networks are discussed and future work outlined.

Neural network regulation driven by autonomous neural firings

NASA Astrophysics Data System (ADS)

Cho, Myoung Won

2016-07-01

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

Deep learning for brain tumor classification

NASA Astrophysics Data System (ADS)

Paul, Justin S.; Plassard, Andrew J.; Landman, Bennett A.; Fabbri, Daniel

2017-03-01

Recent research has shown that deep learning methods have performed well on supervised machine learning, image classification tasks. The purpose of this study is to apply deep learning methods to classify brain images with different tumor types: meningioma, glioma, and pituitary. A dataset was publicly released containing 3,064 T1-weighted contrast enhanced MRI (CE-MRI) brain images from 233 patients with either meningioma, glioma, or pituitary tumors split across axial, coronal, or sagittal planes. This research focuses on the 989 axial images from 191 patients in order to avoid confusing the neural networks with three different planes containing the same diagnosis. Two types of neural networks were used in classification: fully connected and convolutional neural networks. Within these two categories, further tests were computed via the augmentation of the original 512×512 axial images. Training neural networks over the axial data has proven to be accurate in its classifications with an average five-fold cross validation of 91.43% on the best trained neural network. This result demonstrates that a more general method (i.e. deep learning) can outperform specialized methods that require image dilation and ring-forming subregions on tumors.

Feature to prototype transition in neural networks

NASA Astrophysics Data System (ADS)

Krotov, Dmitry; Hopfield, John

Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.

Center for Neural Engineering at Tennessee State University, ASSERT Annual Progress Report.

DTIC Science & Technology

1995-07-01

neural networks . Their research topics are: (1) developing frequency dependent oscillatory neural networks ; (2) long term pontentiation learning rules...as applied to spatial navigation; (3) design and build a servo joint robotic arm and (4) neural network based prothesis control. One graduate student

Feedback control stabilization of critical dynamics via resource transport on multilayer networks: How glia enable learning dynamics in the brain

NASA Astrophysics Data System (ADS)

Virkar, Yogesh S.; Shew, Woodrow L.; Restrepo, Juan G.; Ott, Edward

2016-10-01

Learning and memory are acquired through long-lasting changes in synapses. In the simplest models, such synaptic potentiation typically leads to runaway excitation, but in reality there must exist processes that robustly preserve overall stability of the neural system dynamics. How is this accomplished? Various approaches to this basic question have been considered. Here we propose a particularly compelling and natural mechanism for preserving stability of learning neural systems. This mechanism is based on the global processes by which metabolic resources are distributed to the neurons by glial cells. Specifically, we introduce and study a model composed of two interacting networks: a model neural network interconnected by synapses that undergo spike-timing-dependent plasticity; and a model glial network interconnected by gap junctions that diffusively transport metabolic resources among the glia and, ultimately, to neural synapses where they are consumed. Our main result is that the biophysical constraints imposed by diffusive transport of metabolic resources through the glial network can prevent runaway growth of synaptic strength, both during ongoing activity and during learning. Our findings suggest a previously unappreciated role for glial transport of metabolites in the feedback control stabilization of neural network dynamics during learning.

Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics

PubMed Central

Burms, Jeroen; Caluwaerts, Ken; Dambre, Joni

2015-01-01

In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics. PMID:26347645

Pattern learning with deep neural networks in EMG-based speech recognition.

PubMed

Wand, Michael; Schultz, Tanja

2014-01-01

We report on classification of phones and phonetic features from facial electromyographic (EMG) data, within the context of our EMG-based Silent Speech interface. In this paper we show that a Deep Neural Network can be used to perform this classification task, yielding a significant improvement over conventional Gaussian Mixture models. Our central contribution is the visualization of patterns which are learned by the neural network. With increasing network depth, these patterns represent more and more intricate electromyographic activity.

Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction

Machine learning topological states

NASA Astrophysics Data System (ADS)

Deng, Dong-Ling; Li, Xiaopeng; Das Sarma, S.

2017-11-01

Artificial neural networks and machine learning have now reached a new era after several decades of improvement where applications are to explode in many fields of science, industry, and technology. Here, we use artificial neural networks to study an intriguing phenomenon in quantum physics—the topological phases of matter. We find that certain topological states, either symmetry-protected or with intrinsic topological order, can be represented with classical artificial neural networks. This is demonstrated by using three concrete spin systems, the one-dimensional (1D) symmetry-protected topological cluster state and the 2D and 3D toric code states with intrinsic topological orders. For all three cases, we show rigorously that the topological ground states can be represented by short-range neural networks in an exact and efficient fashion—the required number of hidden neurons is as small as the number of physical spins and the number of parameters scales only linearly with the system size. For the 2D toric-code model, we find that the proposed short-range neural networks can describe the excited states with Abelian anyons and their nontrivial mutual statistics as well. In addition, by using reinforcement learning we show that neural networks are capable of finding the topological ground states of nonintegrable Hamiltonians with strong interactions and studying their topological phase transitions. Our results demonstrate explicitly the exceptional power of neural networks in describing topological quantum states, and at the same time provide valuable guidance to machine learning of topological phases in generic lattice models.

Inversion of surface parameters using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.

1992-01-01

A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.

A neural network prototyping package within IRAF

NASA Technical Reports Server (NTRS)

Bazell, D.; Bankman, I.

1992-01-01

We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.

Neural network to diagnose lining condition

NASA Astrophysics Data System (ADS)

Yemelyanov, V. A.; Yemelyanova, N. Y.; Nedelkin, A. A.; Zarudnaya, M. V.

2018-03-01

The paper presents data on the problem of diagnosing the lining condition at the iron and steel works. The authors describe the neural network structure and software that are designed and developed to determine the lining burnout zones. The simulation results of the proposed neural networks are presented. The authors note the low learning and classification errors of the proposed neural networks. To realize the proposed neural network, the specialized software has been developed.

Understanding the neural basis of cognitive bias modification as a clinical treatment for depression.

PubMed

Eguchi, Akihiro; Walters, Daniel; Peerenboom, Nele; Dury, Hannah; Fox, Elaine; Stringer, Simon

2017-03-01

[Correction Notice: An Erratum for this article was reported in Vol 85(3) of Journal of Consulting and Clinical Psychology (see record 2017-07144-002). In the article, there was an error in the Discussion section's first paragraph for Implications and Future Work. The in-text reference citation for Penton-Voak et al. (2013) was incorrectly listed as "Blumenfeld, Preminger, Sagi, and Tsodyks (2006)". All versions of this article have been corrected.] Objective: Cognitive bias modification (CBM) eliminates cognitive biases toward negative information and is efficacious in reducing depression recurrence, but the mechanisms behind the bias elimination are not fully understood. The present study investigated, through computer simulation of neural network models, the neural dynamics underlying the use of CBM in eliminating the negative biases in the way that depressed patients evaluate facial expressions. We investigated 2 new CBM methodologies using biologically plausible synaptic learning mechanisms-continuous transformation learning and trace learning-which guide learning by exploiting either the spatial or temporal continuity between visual stimuli presented during training. We first describe simulations with a simplified 1-layer neural network, and then we describe simulations in a biologically detailed multilayer neural network model of the ventral visual pathway. After training with either the continuous transformation learning rule or the trace learning rule, the 1-layer neural network eliminated biases in interpreting neutral stimuli as sad. The multilayer neural network trained with realistic face stimuli was also shown to be able to use continuous transformation learning or trace learning to reduce biases in the interpretation of neutral stimuli. The simulation results suggest 2 biologically plausible synaptic learning mechanisms, continuous transformation learning and trace learning, that may subserve CBM. The results are highly informative for the development of experimental protocols to produce optimal CBM training methodologies with human participants. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Privacy-preserving backpropagation neural network learning.

PubMed

Chen, Tingting; Zhong, Sheng

2009-10-01

With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets.

An architecture for designing fuzzy logic controllers using neural networks

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

Described here is an architecture for designing fuzzy controllers through a hierarchical process of control rule acquisition and by using special classes of neural network learning techniques. A new method for learning to refine a fuzzy logic controller is introduced. A reinforcement learning technique is used in conjunction with a multi-layer neural network model of a fuzzy controller. The model learns by updating its prediction of the plant's behavior and is related to the Sutton's Temporal Difference (TD) method. The method proposed here has the advantage of using the control knowledge of an experienced operator and fine-tuning it through the process of learning. The approach is applied to a cart-pole balancing system.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

PubMed

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

PubMed Central

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-01-01

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks. PMID:28394270

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

ERIC Educational Resources Information Center

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…

RM-SORN: a reward-modulated self-organizing recurrent neural network.

PubMed

Aswolinskiy, Witali; Pipa, Gordon

2015-01-01

Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain.

Deep Gate Recurrent Neural Network

DTIC Science & Technology

2016-11-22

Schmidhuber. A system for robotic heart surgery that learns to tie knots using recurrent neural networks. In IEEE International Conference on...tasks, such as Machine Translation (Bahdanau et al. (2015)) or Robot Reinforcement Learning (Bakker (2001)). The main idea behind these networks is to...and J. Peters. Reinforcement learning in robotics : A survey. The International Journal of Robotics Research, 32:1238–1274, 2013. ISSN 0278-3649. doi

A regularization approach to continuous learning with an application to financial derivatives pricing.

PubMed

Ormoneit, D

1999-12-01

We consider the training of neural networks in cases where the nonlinear relationship of interest gradually changes over time. One possibility to deal with this problem is by regularization where a variation penalty is added to the usual mean squared error criterion. To learn the regularized network weights we suggest the Iterative Extended Kalman Filter (IEKF) as a learning rule, which may be derived from a Bayesian perspective on the regularization problem. A primary application of our algorithm is in financial derivatives pricing, where neural networks may be used to model the dependency of the derivatives' price on one or several underlying assets. After giving a brief introduction to the problem of derivatives pricing we present experiments with German stock index options data showing that a regularized neural network trained with the IEKF outperforms several benchmark models and alternative learning procedures. In particular, the performance may be greatly improved using a newly designed neural network architecture that accounts for no-arbitrage pricing restrictions.

Learning in neural networks based on a generalized fluctuation theorem

NASA Astrophysics Data System (ADS)

Hayakawa, Takashi; Aoyagi, Toshio

2015-11-01

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

Different propagation speeds of recalled sequences in plastic spiking neural networks

NASA Astrophysics Data System (ADS)

Huang, Xuhui; Zheng, Zhigang; Hu, Gang; Wu, Si; Rasch, Malte J.

2015-03-01

Neural networks can generate spatiotemporal patterns of spike activity. Sequential activity learning and retrieval have been observed in many brain areas, and e.g. is crucial for coding of episodic memory in the hippocampus or generating temporal patterns during song production in birds. In a recent study, a sequential activity pattern was directly entrained onto the neural activity of the primary visual cortex (V1) of rats and subsequently successfully recalled by a local and transient trigger. It was observed that the speed of activity propagation in coordinates of the retinotopically organized neural tissue was constant during retrieval regardless how the speed of light stimulation sweeping across the visual field during training was varied. It is well known that spike-timing dependent plasticity (STDP) is a potential mechanism for embedding temporal sequences into neural network activity. How training and retrieval speeds relate to each other and how network and learning parameters influence retrieval speeds, however, is not well described. We here theoretically analyze sequential activity learning and retrieval in a recurrent neural network with realistic synaptic short-term dynamics and STDP. Testing multiple STDP rules, we confirm that sequence learning can be achieved by STDP. However, we found that a multiplicative nearest-neighbor (NN) weight update rule generated weight distributions and recall activities that best matched the experiments in V1. Using network simulations and mean-field analysis, we further investigated the learning mechanisms and the influence of network parameters on recall speeds. Our analysis suggests that a multiplicative STDP rule with dominant NN spike interaction might be implemented in V1 since recall speed was almost constant in an NMDA-dominant regime. Interestingly, in an AMPA-dominant regime, neural circuits might exhibit recall speeds that instead follow the change in stimulus speeds. This prediction could be tested in experiments.

Gradient calculations for dynamic recurrent neural networks: a survey.

PubMed

Pearlmutter, B A

1995-01-01

Surveys learning algorithms for recurrent neural networks with hidden units and puts the various techniques into a common framework. The authors discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture. Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the unified presentation leads to generalizations of various sorts. The author discusses advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continues with some "tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. The author presents some simulations, and at the end, addresses issues of computational complexity and learning speed.

Efficient self-organizing multilayer neural network for nonlinear system modeling.

PubMed

Han, Hong-Gui; Wang, Li-Dan; Qiao, Jun-Fei

2013-07-01

It has been shown extensively that the dynamic behaviors of a neural system are strongly influenced by the network architecture and learning process. To establish an artificial neural network (ANN) with self-organizing architecture and suitable learning algorithm for nonlinear system modeling, an automatic axon-neural network (AANN) is investigated in the following respects. First, the network architecture is constructed automatically to change both the number of hidden neurons and topologies of the neural network during the training process. The approach introduced in adaptive connecting-and-pruning algorithm (ACP) is a type of mixed mode operation, which is equivalent to pruning or adding the connecting of the neurons, as well as inserting some required neurons directly. Secondly, the weights are adjusted, using a feedforward computation (FC) to obtain the information for the gradient during learning computation. Unlike most of the previous studies, AANN is able to self-organize the architecture and weights, and to improve the network performances. Also, the proposed AANN has been tested on a number of benchmark problems, ranging from nonlinear function approximating to nonlinear systems modeling. The experimental results show that AANN can have better performances than that of some existing neural networks. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

Tensor Basis Neural Network v. 1.0 (beta)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ling, Julia; Templeton, Jeremy

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.

Noise in Neural Networks: Thresholds, Hysteresis, and Neuromodulation of Signal-To-Noise

NASA Astrophysics Data System (ADS)

Keeler, James D.; Pichler, Elgar E.; Ross, John

1989-03-01

We study a neural-network model including Gaussian noise, higher-order neuronal interactions, and neuromodulation. For a first-order network, there is a threshold in the noise level (phase transition) above which the network displays only disorganized behavior and critical slowing down near the noise threshold. The network can tolerate more noise if it has higher-order feedback interactions, which also lead to hysteresis and multistability in the network dynamics. The signal-to-noise ratio can be adjusted in a biological neural network by neuromodulators such as norepinephrine. Comparisons are made to experimental results and further investigations are suggested to test the effects of hysteresis and neuromodulation in pattern recognition and learning. We propose that norepinephrine may ``quench'' the neural patterns of activity to enhance the ability to learn details.

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

PubMed

Chrol-Cannon, Joseph; Jin, Yaochu

2014-11-01

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

Neural networks and applications tutorial

NASA Astrophysics Data System (ADS)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

Using an Extended Kalman Filter Learning Algorithm for Feed-Forward Neural Networks to Describe Tracer Correlations

NASA Technical Reports Server (NTRS)

Lary, David J.; Mussa, Yussuf

2004-01-01

In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.

Convergence analysis of sliding mode trajectories in multi-objective neural networks learning.

PubMed

Costa, Marcelo Azevedo; Braga, Antonio Padua; de Menezes, Benjamin Rodrigues

2012-09-01

The Pareto-optimality concept is used in this paper in order to represent a constrained set of solutions that are able to trade-off the two main objective functions involved in neural networks supervised learning: data-set error and network complexity. The neural network is described as a dynamic system having error and complexity as its state variables and learning is presented as a process of controlling a learning trajectory in the resulting state space. In order to control the trajectories, sliding mode dynamics is imposed to the network. It is shown that arbitrary learning trajectories can be achieved by maintaining the sliding mode gains within their convergence intervals. Formal proofs of convergence conditions are therefore presented. The concept of trajectory learning presented in this paper goes further beyond the selection of a final state in the Pareto set, since it can be reached through different trajectories and states in the trajectory can be assessed individually against an additional objective function. Copyright © 2012 Elsevier Ltd. All rights reserved.

Evaluation of Deep Learning Models for Predicting CO2 Flux

NASA Astrophysics Data System (ADS)

Halem, M.; Nguyen, P.; Frankel, D.

2017-12-01

Artificial neural networks have been employed to calculate surface flux measurements from station data because they are able to fit highly nonlinear relations between input and output variables without knowing the detail relationships between the variables. However, the accuracy in performing neural net estimates of CO2 flux from observations of CO2 and other atmospheric variables is influenced by the architecture of the neural model, the availability, and complexity of interactions between physical variables such as wind, temperature, and indirect variables like latent heat, and sensible heat, etc. We evaluate two deep learning models, feed forward and recurrent neural network models to learn how they each respond to the physical measurements, time dependency of the measurements of CO2 concentration, humidity, pressure, temperature, wind speed etc. for predicting the CO2 flux. In this paper, we focus on a) building neural network models for estimating CO2 flux based on DOE data from tower Atmospheric Radiation Measurement data; b) evaluating the impact of choosing the surface variables and model hyper-parameters on the accuracy and predictions of surface flux; c) assessing the applicability of the neural network models on estimate CO2 flux by using OCO-2 satellite data; d) studying the efficiency of using GPU-acceleration for neural network performance using IBM Power AI deep learning software and packages on IBM Minsky system.

Using input feature information to improve ultraviolet retrieval in neural networks

NASA Astrophysics Data System (ADS)

Sun, Zhibin; Chang, Ni-Bin; Gao, Wei; Chen, Maosi; Zempila, Melina

2017-09-01

In neural networks, the training/predicting accuracy and algorithm efficiency can be improved significantly via accurate input feature extraction. In this study, some spatial features of several important factors in retrieving surface ultraviolet (UV) are extracted. An extreme learning machine (ELM) is used to retrieve the surface UV of 2014 in the continental United States, using the extracted features. The results conclude that more input weights can improve the learning capacities of neural networks.

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

PubMed

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

2016-12-01

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

Predicate calculus for an architecture of multiple neural networks

NASA Astrophysics Data System (ADS)

Consoli, Robert H.

1990-08-01

Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.

The research of "blind" spot in the LVQ network

NASA Astrophysics Data System (ADS)

Guo, Zhanjie; Nan, Shupo; Wang, Xiaoli

2017-04-01

Nowadays competitive neural network has been widely used in the pattern recognition, classification and other aspects, and show the great advantages compared with the traditional clustering methods. But the competitive neural networks still has inadequate in many aspects, and it needs to be further improved. Based on the learning Vector Quantization Network proposed by Learning Kohonen [1], this paper resolve the issue of the large training error, when there are "blind" spots in a network through the introduction of threshold value learning rules and finally programs the realization with Matlab.

Simple artificial neural networks that match probability and exploit and explore when confronting a multiarmed bandit.

PubMed

Dawson, Michael R W; Dupuis, Brian; Spetch, Marcia L; Kelly, Debbie M

2009-08-01

The matching law (Herrnstein 1961) states that response rates become proportional to reinforcement rates; this is related to the empirical phenomenon called probability matching (Vulkan 2000). Here, we show that a simple artificial neural network generates responses consistent with probability matching. This behavior was then used to create an operant procedure for network learning. We use the multiarmed bandit (Gittins 1989), a classic problem of choice behavior, to illustrate that operant training balances exploiting the bandit arm expected to pay off most frequently with exploring other arms. Perceptrons provide a medium for relating results from neural networks, genetic algorithms, animal learning, contingency theory, reinforcement learning, and theories of choice.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule.

PubMed

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-11-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

DOE Office of Scientific and Technical Information (OSTI.GOV)

Liu, Hui; Song, Yongduan; Xue, Fangzheng

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less

Neural coordination can be enhanced by occasional interruption of normal firing patterns: a self-optimizing spiking neural network model.

PubMed

Woodward, Alexander; Froese, Tom; Ikegami, Takashi

2015-02-01

The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfies constraints between neurons in a globally optimal fashion. It has recently been demonstrated that combining Hebbian learning with occasional alterations of normal neural states avoids this problem by means of self-organized enlargement of the best basins of attraction. However, so far it is not clear to what extent this process of self-optimization is also operative in real brains. Here we demonstrate that it can be transferred to more biologically plausible neural networks by implementing a self-optimizing spiking neural network model. In addition, by using this spiking neural network to emulate a Hopfield network with Hebbian learning, we attempt to make a connection between rate-based and temporal coding based neural systems. Although further work is required to make this model more realistic, it already suggests that the efficacy of the self-optimizing process is independent from the simplifying assumptions of a conventional Hopfield network. We also discuss natural and cultural processes that could be responsible for occasional alteration of neural firing patterns in actual brains. Copyright © 2014 Elsevier Ltd. All rights reserved.

Artificial Neural Network with Regular Graph for Maximum Air Temperature Forecasting:. the Effect of Decrease in Nodes Degree on Learning

NASA Astrophysics Data System (ADS)

Ghaderi, A. H.; Darooneh, A. H.

The behavior of nonlinear systems can be analyzed by artificial neural networks. Air temperature change is one example of the nonlinear systems. In this work, a new neural network method is proposed for forecasting maximum air temperature in two cities. In this method, the regular graph concept is used to construct some partially connected neural networks that have regular structures. The learning results of fully connected ANN and networks with proposed method are compared. In some case, the proposed method has the better result than conventional ANN. After specifying the best network, the effect of input pattern numbers on the prediction is studied and the results show that the increase of input patterns has a direct effect on the prediction accuracy.

Neural Network Computing and Natural Language Processing.

ERIC Educational Resources Information Center

Borchardt, Frank

1988-01-01

Considers the application of neural network concepts to traditional natural language processing and demonstrates that neural network computing architecture can: (1) learn from actual spoken language; (2) observe rules of pronunciation; and (3) reproduce sounds from the patterns derived by its own processes. (Author/CB)

Neural Correlates of Motor Learning, Transfer of Learning, and Learning to Learn

PubMed Central

Seidler, Rachael D.

2009-01-01

Recent studies on the neural bases of sensorimotor adaptation demonstrate that the cerebellar and striatal thalamocortical pathways contribute to early learning. Transfer of learning involves a reduction in the contribution of early learning networks, and increased reliance on the cerebellum. The neural correlates of learning to learn remain to be determined, but likely involve enhanced functioning of general aspects of early learning. PMID:20016293

Genetic learning in rule-based and neural systems

NASA Technical Reports Server (NTRS)

Smith, Robert E.

1993-01-01

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

Pragmatically Framed Cross-Situational Noun Learning Using Computational Reinforcement Models

PubMed Central

Najnin, Shamima; Banerjee, Bonny

2018-01-01

Cross-situational learning and social pragmatic theories are prominent mechanisms for learning word meanings (i.e., word-object pairs). In this paper, the role of reinforcement is investigated for early word-learning by an artificial agent. When exposed to a group of speakers, the agent comes to understand an initial set of vocabulary items belonging to the language used by the group. Both cross-situational learning and social pragmatic theory are taken into account. As social cues, joint attention and prosodic cues in caregiver's speech are considered. During agent-caregiver interaction, the agent selects a word from the caregiver's utterance and learns the relations between that word and the objects in its visual environment. The “novel words to novel objects” language-specific constraint is assumed for computing rewards. The models are learned by maximizing the expected reward using reinforcement learning algorithms [i.e., table-based algorithms: Q-learning, SARSA, SARSA-λ, and neural network-based algorithms: Q-learning for neural network (Q-NN), neural-fitted Q-network (NFQ), and deep Q-network (DQN)]. Neural network-based reinforcement learning models are chosen over table-based models for better generalization and quicker convergence. Simulations are carried out using mother-infant interaction CHILDES dataset for learning word-object pairings. Reinforcement is modeled in two cross-situational learning cases: (1) with joint attention (Attentional models), and (2) with joint attention and prosodic cues (Attentional-prosodic models). Attentional-prosodic models manifest superior performance to Attentional ones for the task of word-learning. The Attentional-prosodic DQN outperforms existing word-learning models for the same task. PMID:29441027

Deep Learning and Developmental Learning: Emergence of Fine-to-Coarse Conceptual Categories at Layers of Deep Belief Network.

PubMed

Sadeghi, Zahra

2016-09-01

In this paper, I investigate conceptual categories derived from developmental processing in a deep neural network. The similarity matrices of deep representation at each layer of neural network are computed and compared with their raw representation. While the clusters generated by raw representation stand at the basic level of abstraction, conceptual categories obtained from deep representation shows a bottom-up transition procedure. Results demonstrate a developmental course of learning from specific to general level of abstraction through learned layers of representations in a deep belief network. © The Author(s) 2016.

Self Improving Methods for Materials and Process Design

DTIC Science & Technology

1998-08-31

using inductive coupling techniques. The first phase of the work focuses on developing an artificial neural network learning for function approximation...developing an artificial neural network learning algorithm for time-series prediction. The third phase of the work focuses on model selection. We have

Learning polynomial feedforward neural networks by genetic programming and backpropagation.

PubMed

Nikolaev, N Y; Iba, H

2003-01-01

This paper presents an approach to learning polynomial feedforward neural networks (PFNNs). The approach suggests, first, finding the polynomial network structure by means of a population-based search technique relying on the genetic programming paradigm, and second, further adjustment of the best discovered network weights by an especially derived backpropagation algorithm for higher order networks with polynomial activation functions. These two stages of the PFNN learning process enable us to identify networks with good training as well as generalization performance. Empirical results show that this approach finds PFNN which outperform considerably some previous constructive polynomial network algorithms on processing benchmark time series.

Adaptive critic learning techniques for engine torque and air-fuel ratio control.

PubMed

Liu, Derong; Javaherian, Hossein; Kovalenko, Olesia; Huang, Ting

2008-08-01

A new approach for engine calibration and control is proposed. In this paper, we present our research results on the implementation of adaptive critic designs for self-learning control of automotive engines. A class of adaptive critic designs that can be classified as (model-free) action-dependent heuristic dynamic programming is used in this research project. The goals of the present learning control design for automotive engines include improved performance, reduced emissions, and maintained optimum performance under various operating conditions. Using the data from a test vehicle with a V8 engine, we developed a neural network model of the engine and neural network controllers based on the idea of approximate dynamic programming to achieve optimal control. We have developed and simulated self-learning neural network controllers for both engine torque (TRQ) and exhaust air-fuel ratio (AFR) control. The goal of TRQ control and AFR control is to track the commanded values. For both control problems, excellent neural network controller transient performance has been achieved.

Mastering the game of Go without human knowledge.

PubMed

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-18

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo's own move selections and also the winner of AlphaGo's games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

Mastering the game of Go without human knowledge

NASA Astrophysics Data System (ADS)

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-01

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

Criteria for Choosing the Best Neural Network: Part 1

DTIC Science & Technology

1991-07-24

Touretzky, pp. 177-185. San Mateo: Morgan Kaufmann. Harp, S.A., Samad , T., and Guha, A . (1990). Designing application-specific neural networks using genetic...determining a parsimonious neural network for use in prediction/generalization based on a given fixed learning sample. Both the classification and...statistical settings, algorithms for selecting the number of hidden layer nodes in a three layer, feedforward neural network are presented. The selection

Neural network system for purposeful behavior based on foveal visual preprocessor

NASA Astrophysics Data System (ADS)

Golovan, Alexander V.; Shevtsova, Natalia A.; Klepatch, Arkadi A.

1996-10-01

Biologically plausible model of the system with an adaptive behavior in a priori environment and resistant to impairment has been developed. The system consists of input, learning, and output subsystems. The first subsystems classifies input patterns presented as n-dimensional vectors in accordance with some associative rule. The second one being a neural network determines adaptive responses of the system to input patterns. Arranged neural groups coding possible input patterns and appropriate output responses are formed during learning by means of negative reinforcement. Output subsystem maps a neural network activity into the system behavior in the environment. The system developed has been studied by computer simulation imitating a collision-free motion of a mobile robot. After some learning period the system 'moves' along a road without collisions. It is shown that in spite of impairment of some neural network elements the system functions reliably after relearning. Foveal visual preprocessor model developed earlier has been tested to form a kind of visual input to the system.

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

PubMed

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

2015-01-01

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

Time Series Forecasting of Daily Reference Evapotranspiration by Neural Network Ensemble Learning for Irrigation System

NASA Astrophysics Data System (ADS)

Manikumari, N.; Murugappan, A.; Vinodhini, G.

2017-07-01

Time series forecasting has gained remarkable interest of researchers in the last few decades. Neural networks based time series forecasting have been employed in various application areas. Reference Evapotranspiration (ETO) is one of the most important components of the hydrologic cycle and its precise assessment is vital in water balance and crop yield estimation, water resources system design and management. This work aimed at achieving accurate time series forecast of ETO using a combination of neural network approaches. This work was carried out using data collected in the command area of VEERANAM Tank during the period 2004 - 2014 in India. In this work, the Neural Network (NN) models were combined by ensemble learning in order to improve the accuracy for forecasting Daily ETO (for the year 2015). Bagged Neural Network (Bagged-NN) and Boosted Neural Network (Boosted-NN) ensemble learning were employed. It has been proved that Bagged-NN and Boosted-NN ensemble models are better than individual NN models in terms of accuracy. Among the ensemble models, Boosted-NN reduces the forecasting errors compared to Bagged-NN and individual NNs. Regression co-efficient, Mean Absolute Deviation, Mean Absolute Percentage error and Root Mean Square Error also ascertain that Boosted-NN lead to improved ETO forecasting performance.

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

NASA Technical Reports Server (NTRS)

Williams-Hayes, Peggy S.

2004-01-01

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

Vibration control of building structures using self-organizing and self-learning neural networks

NASA Astrophysics Data System (ADS)

Madan, Alok

2005-11-01

Past research in artificial intelligence establishes that artificial neural networks (ANN) are effective and efficient computational processors for performing a variety of tasks including pattern recognition, classification, associative recall, combinatorial problem solving, adaptive control, multi-sensor data fusion, noise filtering and data compression, modelling and forecasting. The paper presents a potentially feasible approach for training ANN in active control of earthquake-induced vibrations in building structures without the aid of teacher signals (i.e. target control forces). A counter-propagation neural network is trained to output the control forces that are required to reduce the structural vibrations in the absence of any feedback on the correctness of the output control forces (i.e. without any information on the errors in output activations of the network). The present study shows that, in principle, the counter-propagation network (CPN) can learn from the control environment to compute the required control forces without the supervision of a teacher (unsupervised learning). Simulated case studies are presented to demonstrate the feasibility of implementing the unsupervised learning approach in ANN for effective vibration control of structures under the influence of earthquake ground motions. The proposed learning methodology obviates the need for developing a mathematical model of structural dynamics or training a separate neural network to emulate the structural response for implementation in practice.

Neural-Network Computer Transforms Coordinates

NASA Technical Reports Server (NTRS)

Josin, Gary M.

1990-01-01

Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

Neural Network Development Tool (NETS)

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1990-01-01

Artificial neural networks formed from hundreds or thousands of simulated neurons, connected in manner similar to that in human brain. Such network models learning behavior. Using NETS involves translating problem to be solved into input/output pairs, designing network configuration, and training network. Written in C.

Neural networks for learning and prediction with applications to remote sensing and speech perception

NASA Astrophysics Data System (ADS)

Gjaja, Marin N.

1997-11-01

Neural networks for supervised and unsupervised learning are developed and applied to problems in remote sensing, continuous map learning, and speech perception. Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART networks synthesize fuzzy logic and neural networks, and supervised ARTMAP networks incorporate ART modules for prediction and classification. New ART and ARTMAP methods resulting from analyses of data structure, parameter specification, and category selection are developed. Architectural modifications providing flexibility for a variety of applications are also introduced and explored. A new methodology for automatic mapping from Landsat Thematic Mapper (TM) and terrain data, based on fuzzy ARTMAP, is developed. System capabilities are tested on a challenging remote sensing problem, prediction of vegetation classes in the Cleveland National Forest from spectral and terrain features. After training at the pixel level, performance is tested at the stand level, using sites not seen during training. Results are compared to those of maximum likelihood classifiers, back propagation neural networks, and K-nearest neighbor algorithms. Best performance is obtained using a hybrid system based on a convex combination of fuzzy ARTMAP and maximum likelihood predictions. This work forms the foundation for additional studies exploring fuzzy ARTMAP's capability to estimate class mixture composition for non-homogeneous sites. Exploratory simulations apply ARTMAP to the problem of learning continuous multidimensional mappings. A novel system architecture retains basic ARTMAP properties of incremental and fast learning in an on-line setting while adding components to solve this class of problems. The perceptual magnet effect is a language-specific phenomenon arising early in infant speech development that is characterized by a warping of speech sound perception. An unsupervised neural network model is proposed that embodies two principal hypotheses supported by experimental data--that sensory experience guides language-specific development of an auditory neural map and that a population vector can predict psychological phenomena based on map cell activities. Model simulations show how a nonuniform distribution of map cell firing preferences can develop from language-specific input and give rise to the magnet effect.

Adaptive Neurons For Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1990-01-01

Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

NASA Astrophysics Data System (ADS)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

Systematic construction and control of stereo nerve vision network in intelligent manufacturing

NASA Astrophysics Data System (ADS)

Liu, Hua; Wang, Helong; Guo, Chunjie; Ding, Quanxin; Zhou, Liwei

2017-10-01

A system method of constructing stereo vision by using neural network is proposed, and the operation and control mechanism in actual operation are proposed. This method makes effective use of the neural network in learning and memory function, by after training with samples. Moreover, the neural network can learn the nonlinear relationship in the stereoscopic vision system and the internal and external orientation elements. These considerations are Worthy of attention, which includes limited constraints, the scientific of critical group, the operating speed and the operability in technical aspects. The results support our theoretical forecast.

Learning Universal Computations with Spikes

PubMed Central

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

2016-01-01

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

Experimental Verification of Electric Drive Technologies Based on Artificial Intelligence Tools

NASA Technical Reports Server (NTRS)

Rubaai, Ahmed; Ricketts, Daniel; Kotaru, Raj; Thomas, Robert; Noga, Donald F. (Technical Monitor); Kankam, Mark D. (Technical Monitor)

2000-01-01

In this report, a fully integrated prototype of a flight servo control system is successfully developed and implemented using brushless dc motors. The control system is developed by the fuzzy logic theory, and implemented with a multilayer neural network. First, a neural network-based architecture is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the neural network structure. The network structure and the parameter learning are performed simultaneously and online in the fuzzy-neural network system. The structure learning is based on the partition of input space. The parameter learning is based on the supervised gradient decent method, using a delta adaptation law. Using experimental setup, the performance of the proposed control system is evaluated under various operating conditions. Test results are presented and discussed in the report. The proposed learning control system has several advantages, namely, simple structure and learning capability, robustness and high tracking performance and few nodes at hidden layers. In comparison with the PI controller, the proposed fuzzy-neural network system can yield a better dynamic performance with shorter settling time, and without overshoot. Experimental results have shown that the proposed control system is adaptive and robust in responding to a wide range of operating conditions. In summary, the goal of this study is to design and implement-advanced servosystems to actuate control surfaces for flight vehicles, namely, aircraft and helicopters, missiles and interceptors, and mini- and micro-air vehicles.

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Finite time convergent learning law for continuous neural networks.

PubMed

Chairez, Isaac

2014-02-01

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

Competitive Learning Neural Network Ensemble Weighted by Predicted Performance

ERIC Educational Resources Information Center

Ye, Qiang

2010-01-01

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

Artificial intelligence expert systems with neural network machine learning may assist decision-making for extractions in orthodontic treatment planning.

PubMed

Takada, Kenji

2016-09-01

New approach for the diagnosis of extractions with neural network machine learning. Seok-Ki Jung and Tae-Woo Kim. Am J Orthod Dentofacial Orthop 2016;149:127-33. Not reported. Mathematical modeling. Copyright © 2016 Elsevier Inc. All rights reserved.

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting

PubMed Central

Ghazali, Rozaida; Herawan, Tutut

2016-01-01

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network. PMID:27959927

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

PubMed

Waheeb, Waddah; Ghazali, Rozaida; Herawan, Tutut

2016-01-01

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

Modeling and control of magnetorheological fluid dampers using neural networks

NASA Astrophysics Data System (ADS)

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

2005-02-01

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

Nature vs Nurture: Effects of Learning on Evolution

NASA Astrophysics Data System (ADS)

Nagrani, Nagina

In the field of Evolutionary Robotics, the design, development and application of artificial neural networks as controllers have derived their inspiration from biology. Biologists and artificial intelligence researchers are trying to understand the effects of neural network learning during the lifetime of the individuals on evolution of these individuals by qualitative and quantitative analyses. The conclusion of these analyses can help develop optimized artificial neural networks to perform any given task. The purpose of this thesis is to study the effects of learning on evolution. This has been done by applying Temporal Difference Reinforcement Learning methods to the evolution of Artificial Neural Tissue controller. The controller has been assigned the task to collect resources in a designated area in a simulated environment. The performance of the individuals is measured by the amount of resources collected. A comparison has been made between the results obtained by incorporating learning in evolution and evolution alone. The effects of learning parameters: learning rate, training period, discount rate, and policy on evolution have also been studied. It was observed that learning delays the performance of the evolving individuals over the generations. However, the non zero learning rate throughout the evolution process signifies natural selection preferring individuals possessing plasticity.

Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography

PubMed Central

2018-01-01

Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one. PMID:29695066

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

PubMed

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

2018-04-24

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

Artificial Intelligence in Prediction of Secondary Protein Structure Using CB513 Database

PubMed Central

Avdagic, Zikrija; Purisevic, Elvir; Omanovic, Samir; Coralic, Zlatan

2009-01-01

In this paper we describe CB513 a non-redundant dataset, suitable for development of algorithms for prediction of secondary protein structure. A program was made in Borland Delphi for transforming data from our dataset to make it suitable for learning of neural network for prediction of secondary protein structure implemented in MATLAB Neural-Network Toolbox. Learning (training and testing) of neural network is researched with different sizes of windows, different number of neurons in the hidden layer and different number of training epochs, while using dataset CB513. PMID:21347158

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

PubMed

Biswas, Surama; Acharyya, Sriyankar

2016-06-01

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

Program Helps Simulate Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James; Mcintire, Gary

1993-01-01

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

Neural networks applications to control and computations

NASA Technical Reports Server (NTRS)

Luxemburg, Leon A.

1994-01-01

Several interrelated problems in the area of neural network computations are described. First an interpolation problem is considered, then a control problem is reduced to a problem of interpolation by a neural network via Lyapunov function approach, and finally a new, faster method of learning as compared with the gradient descent method, was introduced.

Kohonen and counterpropagation neural networks applied for mapping and interpretation of IR spectra.

PubMed

Novic, Marjana

2008-01-01

The principles of learning strategy of Kohonen and counterpropagation neural networks are introduced. The advantages of unsupervised learning are discussed. The self-organizing maps produced in both methods are suitable for a wide range of applications. Here, we present an example of Kohonen and counterpropagation neural networks used for mapping, interpretation, and simulation of infrared (IR) spectra. The artificial neural network models were trained for prediction of structural fragments of an unknown compound from its infrared spectrum. The training set contained over 3,200 IR spectra of diverse compounds of known chemical structure. The structure-spectra relationship was encompassed by the counterpropagation neural network, which assigned structural fragments to individual compounds within certain probability limits, assessed from the predictions of test compounds. The counterpropagation neural network model for prediction of fragments of chemical structure is reversible, which means that, for a given structural domain, limited to the training data set in the study, it can be used to simulate the IR spectrum of a chemical defined with a set of structural fragments.

Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR.

PubMed

Winkler, David A; Le, Tu C

2017-01-01

Neural networks have generated valuable Quantitative Structure-Activity/Property Relationships (QSAR/QSPR) models for a wide variety of small molecules and materials properties. They have grown in sophistication and many of their initial problems have been overcome by modern mathematical techniques. QSAR studies have almost always used so-called "shallow" neural networks in which there is a single hidden layer between the input and output layers. Recently, a new and potentially paradigm-shifting type of neural network based on Deep Learning has appeared. Deep learning methods have generated impressive improvements in image and voice recognition, and are now being applied to QSAR and QSAR modelling. This paper describes the differences in approach between deep and shallow neural networks, compares their abilities to predict the properties of test sets for 15 large drug data sets (the kaggle set), discusses the results in terms of the Universal Approximation theorem for neural networks, and describes how DNN may ameliorate or remove troublesome "activity cliffs" in QSAR data sets. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

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

NASA Astrophysics Data System (ADS)

Simon, Solomon H.

1992-08-01

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

Clinical Named Entity Recognition Using Deep Learning Models.

PubMed

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER.

Clinical Named Entity Recognition Using Deep Learning Models

PubMed Central

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER. PMID:29854252

Supervised Learning in CINets

DTIC Science & Technology

2011-07-01

supervised learning process is compared to that of Artificial Neural Network ( ANNs ), fuzzy logic rule set, and Bayesian network approaches...of both fuzzy logic systems and Artificial Neural Networks ( ANNs ). Like fuzzy logic systems, the CINet technique allows the use of human- intuitive...fuzzy rule systems [3] CINets also maintain features common to both fuzzy systems and ANNs . The technique can be be shown to possess the property

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

PubMed

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

2017-12-01

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

Neural Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Smith, Patrick I.

2003-09-23

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. Neuralmore » 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 information [2]. Each one of these cells acts as a simple processor. When individual cells interact with one another, the complex abilities of the brain are made possible. In neural networks, the input or data are processed by a propagation function that adds up the values of all the incoming data. The ending value is then compared with a threshold or specific value. The resulting value must exceed the activation function value in order to become output. The activation function is a mathematical function that a neuron uses to produce an output referring to its input value. [8] Figure 1 depicts this process. Neural networks usually have three components an input, a hidden, and an output. These layers create the end result of the neural network. A real world example is a child associating the word dog with a picture. The child says dog and simultaneously looks a picture of a dog. The input is the spoken word ''dog'', the hidden is the brain processing, and the output will be the category of the word dog based on the picture. This illustration describes how a neural network functions.« less

Neural Network Processing of Natural Language: II. Towards a Unified Model of Corticostriatal Function in Learning Sentence Comprehension and Non-Linguistic Sequencing

ERIC Educational Resources Information Center

Dominey, Peter Ford; Inui, Toshio; Hoen, Michel

2009-01-01

A central issue in cognitive neuroscience today concerns how distributed neural networks in the brain that are used in language learning and processing can be involved in non-linguistic cognitive sequence learning. This issue is informed by a wealth of functional neurophysiology studies of sentence comprehension, along with a number of recent…

Nonparametric Representations for Integrated Inference, Control, and Sensing

DTIC Science & Technology

2015-10-01

Learning (ICML), 2013. [20] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. DeCAF: A deep ...unlimited. Multi-layer feature learning “SuperVision” Convolutional Neural Network (CNN) ImageNet Classification with Deep Convolutional Neural Networks...to develop a new framework for autonomous operations that will extend the state of the art in distributed learning and modeling from data, and

Research on artificial neural network intrusion detection photochemistry based on the improved wavelet analysis and transformation

NASA Astrophysics Data System (ADS)

Li, Hong; Ding, Xue

2017-03-01

This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.

Toolkits and Libraries for Deep Learning.

PubMed

Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy; Philbrick, Kenneth

2017-08-01

Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images.

Biologically inspired intelligent decision making: a commentary on the use of artificial neural networks in bioinformatics.

PubMed

Manning, Timmy; Sleator, Roy D; Walsh, Paul

2014-01-01

Artificial neural networks (ANNs) are a class of powerful machine learning models for classification and function approximation which have analogs in nature. An ANN learns to map stimuli to responses through repeated evaluation of exemplars of the mapping. This learning approach results in networks which are recognized for their noise tolerance and ability to generalize meaningful responses for novel stimuli. It is these properties of ANNs which make them appealing for applications to bioinformatics problems where interpretation of data may not always be obvious, and where the domain knowledge required for deductive techniques is incomplete or can cause a combinatorial explosion of rules. In this paper, we provide an introduction to artificial neural network theory and review some interesting recent applications to bioinformatics problems.

Neural networks for function approximation in nonlinear control

NASA Technical Reports Server (NTRS)

Linse, Dennis J.; Stengel, Robert F.

1990-01-01

Two neural network architectures are compared with a classical spline interpolation technique for the approximation of functions useful in a nonlinear control system. A standard back-propagation feedforward neural network and a cerebellar model articulation controller (CMAC) neural network are presented, and their results are compared with a B-spline interpolation procedure that is updated using recursive least-squares parameter identification. Each method is able to accurately represent a one-dimensional test function. Tradeoffs between size requirements, speed of operation, and speed of learning indicate that neural networks may be practical for identification and adaptation in a nonlinear control environment.

Application of dynamic recurrent neural networks in nonlinear system identification

NASA Astrophysics Data System (ADS)

Du, Yun; Wu, Xueli; Sun, Huiqin; Zhang, Suying; Tian, Qiang

2006-11-01

An adaptive identification method of simple dynamic recurrent neural network (SRNN) for nonlinear dynamic systems is presented in this paper. This method based on the theory that by using the inner-states feed-back of dynamic network to describe the nonlinear kinetic characteristics of system can reflect the dynamic characteristics more directly, deduces the recursive prediction error (RPE) learning algorithm of SRNN, and improves the algorithm by studying topological structure on recursion layer without the weight values. The simulation results indicate that this kind of neural network can be used in real-time control, due to its less weight values, simpler learning algorithm, higher identification speed, and higher precision of model. It solves the problems of intricate in training algorithm and slow rate in convergence caused by the complicate topological structure in usual dynamic recurrent neural network.

Training strategy for convolutional neural networks in pedestrian gender classification

NASA Astrophysics Data System (ADS)

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.

Synchronization of heteroclinic circuits through learning in coupled neural networks

NASA Astrophysics Data System (ADS)

Selskii, Anton; Makarov, Valeri A.

2016-01-01

The synchronization of oscillatory activity in neural networks is usually implemented by coupling the state variables describing neuronal dynamics. Here we study another, but complementary mechanism based on a learning process with memory. A driver network, acting as a teacher, exhibits winner-less competition (WLC) dynamics, while a driven network, a learner, tunes its internal couplings according to the oscillations observed in the teacher. We show that under appropriate training the learner can "copy" the coupling structure and thus synchronize oscillations with the teacher. The replication of the WLC dynamics occurs for intermediate memory lengths only, consequently, the learner network exhibits a phenomenon of learning resonance.

Bio-inspired spiking neural network for nonlinear systems control.

PubMed

Pérez, Javier; Cabrera, Juan A; Castillo, Juan J; Velasco, Juan M

2018-08-01

Spiking neural networks (SNN) are the third generation of artificial neural networks. SNN are the closest approximation to biological neural networks. SNNs make use of temporal spike trains to command inputs and outputs, allowing a faster and more complex computation. As demonstrated by biological organisms, they are a potentially good approach to designing controllers for highly nonlinear dynamic systems in which the performance of controllers developed by conventional techniques is not satisfactory or difficult to implement. SNN-based controllers exploit their ability for online learning and self-adaptation to evolve when transferred from simulations to the real world. SNN's inherent binary and temporary way of information codification facilitates their hardware implementation compared to analog neurons. Biological neural networks often require a lower number of neurons compared to other controllers based on artificial neural networks. In this work, these neuronal systems are imitated to perform the control of non-linear dynamic systems. For this purpose, a control structure based on spiking neural networks has been designed. Particular attention has been paid to optimizing the structure and size of the neural network. The proposed structure is able to control dynamic systems with a reduced number of neurons and connections. A supervised learning process using evolutionary algorithms has been carried out to perform controller training. The efficiency of the proposed network has been verified in two examples of dynamic systems control. Simulations show that the proposed control based on SNN exhibits superior performance compared to other approaches based on Neural Networks and SNNs. Copyright © 2018 Elsevier Ltd. All rights reserved.

Why Traditional Expository Teaching-Learning Approaches May Founder? An Experimental Examination of Neural Networks in Biology Learning

ERIC Educational Resources Information Center

Lee, Jun-Ki; Kwon, Yong-Ju

2011-01-01

Using functional magnetic resonance imaging (fMRI), this study investigates and discusses neurological explanations for, and the educational implications of, the neural network activations involved in hypothesis-generating and hypothesis-understanding for biology education. Two sets of task paradigms about biological phenomena were designed:…

Pragmatic Bootstrapping: A Neural Network Model of Vocabulary Acquisition

ERIC Educational Resources Information Center

Caza, Gregory A.; Knott, Alistair

2012-01-01

The social-pragmatic theory of language acquisition proposes that children only become efficient at learning the meanings of words once they acquire the ability to understand the intentions of other agents, in particular the intention to communicate (Akhtar & Tomasello, 2000). In this paper we present a neural network model of word learning which…

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control

NASA Technical Reports Server (NTRS)

Hageman, Jacob J.; Smith, Mark S.; Stachowiak, Susan

2003-01-01

An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.

Distributed synaptic weights in a LIF neural network and learning rules

NASA Astrophysics Data System (ADS)

Perthame, Benoît; Salort, Delphine; Wainrib, Gilles

2017-09-01

Leaky integrate-and-fire (LIF) models are mean-field limits, with a large number of neurons, used to describe neural networks. We consider inhomogeneous networks structured by a connectivity parameter (strengths of the synaptic weights) with the effect of processing the input current with different intensities. We first study the properties of the network activity depending on the distribution of synaptic weights and in particular its discrimination capacity. Then, we consider simple learning rules and determine the synaptic weight distribution it generates. We outline the role of noise as a selection principle and the capacity to memorize a learned signal.

Learning in stochastic neural networks for constraint satisfaction problems

NASA Technical Reports Server (NTRS)

Johnston, Mark D.; Adorf, Hans-Martin

1989-01-01

Researchers describe a newly-developed artificial neural network algorithm for solving constraint satisfaction problems (CSPs) which includes a learning component that can significantly improve the performance of the network from run to run. The network, referred to as the Guarded Discrete Stochastic (GDS) network, is based on the discrete Hopfield network but differs from it primarily in that auxiliary networks (guards) are asymmetrically coupled to the main network to enforce certain types of constraints. Although the presence of asymmetric connections implies that the network may not converge, it was found that, for certain classes of problems, the network often quickly converges to find satisfactory solutions when they exist. The network can run efficiently on serial machines and can find solutions to very large problems (e.g., N-queens for N as large as 1024). One advantage of the network architecture is that network connection strengths need not be instantiated when the network is established: they are needed only when a participating neural element transitions from off to on. They have exploited this feature to devise a learning algorithm, based on consistency techniques for discrete CSPs, that updates the network biases and connection strengths and thus improves the network performance.

Exploring the limits of learning: Segregation of information integration and response selection is required for learning a serial reversal task

PubMed Central

Zanutto, B. Silvano

2017-01-01

Animals are proposed to learn the latent rules governing their environment in order to maximize their chances of survival. However, rules may change without notice, forcing animals to keep a memory of which one is currently at work. Rule switching can lead to situations in which the same stimulus/response pairing is positively and negatively rewarded in the long run, depending on variables that are not accessible to the animal. This fact raises questions on how neural systems are capable of reinforcement learning in environments where the reinforcement is inconsistent. Here we address this issue by asking about which aspects of connectivity, neural excitability and synaptic plasticity are key for a very general, stochastic spiking neural network model to solve a task in which rules change without being cued, taking the serial reversal task (SRT) as paradigm. Contrary to what could be expected, we found strong limitations for biologically plausible networks to solve the SRT. Especially, we proved that no network of neurons can learn a SRT if it is a single neural population that integrates stimuli information and at the same time is responsible of choosing the behavioural response. This limitation is independent of the number of neurons, neuronal dynamics or plasticity rules, and arises from the fact that plasticity is locally computed at each synapse, and that synaptic changes and neuronal activity are mutually dependent processes. We propose and characterize a spiking neural network model that solves the SRT, which relies on separating the functions of stimuli integration and response selection. The model suggests that experimental efforts to understand neural function should focus on the characterization of neural circuits according to their connectivity, neural dynamics, and the degree of modulation of synaptic plasticity with reward. PMID:29077735

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap S.

1992-01-01

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

A Deep Neural Network Model for Rainfall Estimation UsingPolarimetric WSR-88DP Radar Observations

NASA Astrophysics Data System (ADS)

Tan, H.; Chandra, C. V.; Chen, H.

2016-12-01

Rainfall estimation based on radar measurements has been an important topic for a few decades. Generally, radar rainfall estimation is conducted through parametric algorisms such as reflectivity-rainfall relation (i.e., Z-R relation). On the other hand, neural networks are developed for ground rainfall estimation based on radar measurements. This nonparametric method, which takes into account of both radar observations and rainfall measurements from ground rain gauges, has been demonstrated successfully for rainfall rate estimation. However, the neural network-based rainfall estimation is limited in practice due to the model complexity and structure, data quality, as well as different rainfall microphysics. Recently, the deep learning approach has been introduced in pattern recognition and machine learning areas. Compared to traditional neural networks, the deep learning based methodologies have larger number of hidden layers and more complex structure for data representation. Through a hierarchical learning process, the high level structured information and knowledge can be extracted automatically from low level features of the data. In this paper, we introduce a novel deep neural network model for rainfall estimation based on ground polarimetric radar measurements .The model is designed to capture the complex abstractions of radar measurements at different levels using multiple layers feature identification and extraction. The abstractions at different levels can be used independently or fused with other data resource such as satellite-based rainfall products and/or topographic data to represent the rain characteristics at certain location. In particular, the WSR-88DP radar and rain gauge data collected in Dallas - Fort Worth Metroplex and Florida are used extensively to train the model, and for demonstration purposes. Quantitative evaluation of the deep neural network based rainfall products will also be presented, which is based on an independent rain gauge network.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

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

USDA-ARS?s Scientific Manuscript database

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

Co-Attention Based Neural Network for Source-Dependent Essay Scoring

ERIC Educational Resources Information Center

Zhang, Haoran; Litman, Diane

2018-01-01

This paper presents an investigation of using a co-attention based neural network for source-dependent essay scoring. We use a co-attention mechanism to help the model learn the importance of each part of the essay more accurately. Also, this paper shows that the co-attention based neural network model provides reliable score prediction of…

NETS

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1993-01-01

NETS development tool provides environment for simulation and development of neural networks - computer programs that "learn" from experience. Written in ANSI standard C, program allows user to generate C code for implementation of neural network.

Synchronization in a noise-driven developing neural network

NASA Astrophysics Data System (ADS)

Lin, I.-H.; Wu, R.-K.; Chen, C.-M.

2011-11-01

We use computer simulations to investigate the structural and dynamical properties of a developing neural network whose activity is driven by noise. Structurally, the constructed neural networks in our simulations exhibit the small-world properties that have been observed in several neural networks. The dynamical change of neuronal membrane potential is described by the Hodgkin-Huxley model, and two types of learning rules, including spike-timing-dependent plasticity (STDP) and inverse STDP, are considered to restructure the synaptic strength between neurons. Clustered synchronized firing (SF) of the network is observed when the network connectivity (number of connections/maximal connections) is about 0.75, in which the firing rate of neurons is only half of the network frequency. At the connectivity of 0.86, all neurons fire synchronously at the network frequency. The network SF frequency increases logarithmically with the culturing time of a growing network and decreases exponentially with the delay time in signal transmission. These conclusions are consistent with experimental observations. The phase diagrams of SF in a developing network are investigated for both learning rules.

Dynamics of neural cryptography

NASA Astrophysics Data System (ADS)

Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

2007-05-01

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

Dynamics of neural cryptography.

PubMed

Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

2007-05-01

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

Dynamics of neural cryptography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido

2007-05-15

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

Genetic algorithm for neural networks optimization

NASA Astrophysics Data System (ADS)

Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta

2004-11-01

This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.

Machine learning approaches to the social determinants of health in the health and retirement study.

PubMed

Seligman, Benjamin; Tuljapurkar, Shripad; Rehkopf, David

2018-04-01

Social and economic factors are important predictors of health and of recognized importance for health systems. However, machine learning, used elsewhere in the biomedical literature, has not been extensively applied to study relationships between society and health. We investigate how machine learning may add to our understanding of social determinants of health using data from the Health and Retirement Study. A linear regression of age and gender, and a parsimonious theory-based regression additionally incorporating income, wealth, and education, were used to predict systolic blood pressure, body mass index, waist circumference, and telomere length. Prediction, fit, and interpretability were compared across four machine learning methods: linear regression, penalized regressions, random forests, and neural networks. All models had poor out-of-sample prediction. Most machine learning models performed similarly to the simpler models. However, neural networks greatly outperformed the three other methods. Neural networks also had good fit to the data ( R 2 between 0.4-0.6, versus <0.3 for all others). Across machine learning models, nine variables were frequently selected or highly weighted as predictors: dental visits, current smoking, self-rated health, serial-seven subtractions, probability of receiving an inheritance, probability of leaving an inheritance of at least $10,000, number of children ever born, African-American race, and gender. Some of the machine learning methods do not improve prediction or fit beyond simpler models, however, neural networks performed well. The predictors identified across models suggest underlying social factors that are important predictors of biological indicators of chronic disease, and that the non-linear and interactive relationships between variables fundamental to the neural network approach may be important to consider.

Quantum neural networks: Current status and prospects for development

NASA Astrophysics Data System (ADS)

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

2014-11-01

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

Development and Flight Testing of a Neural Network Based Flight Control System on the NF-15B Aircraft

NASA Technical Reports Server (NTRS)

Bomben, Craig R.; Smolka, James W.; Bosworth, John T.; Silliams-Hayes, Peggy S.; Burken, John J.; Larson, Richard R.; Buschbacher, Mark J.; Maliska, Heather A.

2006-01-01

The Intelligent Flight Control System (IFCS) project at the NASA Dryden Flight Research Center, Edwards AFB, CA, has been investigating the use of neural network based adaptive control on a unique NF-15B test aircraft. The IFCS neural network is a software processor that stores measured aircraft response information to dynamically alter flight control gains. In 2006, the neural network was engaged and allowed to learn in real time to dynamically alter the aircraft handling qualities characteristics in the presence of actual aerodynamic failure conditions injected into the aircraft through the flight control system. The use of neural network and similar adaptive technologies in the design of highly fault and damage tolerant flight control systems shows promise in making future aircraft far more survivable than current technology allows. This paper will present the results of the IFCS flight test program conducted at the NASA Dryden Flight Research Center in 2006, with emphasis on challenges encountered and lessons learned.

Self-teaching neural network learns difficult reactor control problem

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jouse, W.C.

1989-01-01

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

An adaptive Hinfinity controller design for bank-to-turn missiles using ridge Gaussian neural networks.

PubMed

Lin, Chuan-Kai; Wang, Sheng-De

2004-11-01

A new autopilot design for bank-to-turn (BTT) missiles is presented. In the design of autopilot, a ridge Gaussian neural network with local learning capability and fewer tuning parameters than Gaussian neural networks is proposed to model the controlled nonlinear systems. We prove that the proposed ridge Gaussian neural network, which can be a universal approximator, equals the expansions of rotated and scaled Gaussian functions. Although ridge Gaussian neural networks can approximate the nonlinear and complex systems accurately, the small approximation errors may affect the tracking performance significantly. Therefore, by employing the Hinfinity control theory, it is easy to attenuate the effects of the approximation errors of the ridge Gaussian neural networks to a prescribed level. Computer simulation results confirm the effectiveness of the proposed ridge Gaussian neural networks-based autopilot with Hinfinity stabilization.

Least square neural network model of the crude oil blending process.

PubMed

Rubio, José de Jesús

2016-06-01

In this paper, the recursive least square algorithm is designed for the big data learning of a feedforward neural network. The proposed method as the combination of the recursive least square and feedforward neural network obtains four advantages over the alone algorithms: it requires less number of regressors, it is fast, it has the learning ability, and it is more compact. Stability, convergence, boundedness of parameters, and local minimum avoidance of the proposed technique are guaranteed. The introduced strategy is applied for the modeling of the crude oil blending process. Copyright © 2016 Elsevier Ltd. All rights reserved.

Network Modeling of Adult Neurogenesis: Shifting Rates of Neuronal Turnover Optimally Gears Network Learning according to Novelty Gradient

PubMed Central

Chambers, R. Andrew; Conroy, Susan K.

2010-01-01

Apoptotic and neurogenic events in the adult hippocampus are hypothesized to play a role in cognitive responses to new contexts. Corticosteroid-mediated stress responses and other neural processes invoked by substantially novel contextual changes may regulate these processes. Using elementary three-layer neural networks that learn by incremental synaptic plasticity, we explored whether the cognitive effects of differential regimens of neuronal turnover depend on the environmental context in terms of the degree of novelty in the new information to be learned. In “adult” networks that had achieved mature synaptic connectivity upon prior learning of the Roman alphabet, imposition of apoptosis/neurogenesis before learning increasingly novel information (alternate Roman < Russian < Hebrew) reveals optimality of informatic cost benefits when rates of turnover are geared in proportion to the degree of novelty. These findings predict that flexible control of rates of apoptosis–neurogenesis within plastic, mature neural systems optimizes learning attributes under varying degrees of contextual change, and that failures in this regulation may define a role for adult hippocampal neurogenesis in novelty- and stress-responsive psychiatric disorders. PMID:17214558

Network modeling of adult neurogenesis: shifting rates of neuronal turnover optimally gears network learning according to novelty gradient.

PubMed

Chambers, R Andrew; Conroy, Susan K

2007-01-01

Apoptotic and neurogenic events in the adult hippocampus are hypothesized to play a role in cognitive responses to new contexts. Corticosteroid-mediated stress responses and other neural processes invoked by substantially novel contextual changes may regulate these processes. Using elementary three-layer neural networks that learn by incremental synaptic plasticity, we explored whether the cognitive effects of differential regimens of neuronal turnover depend on the environmental context in terms of the degree of novelty in the new information to be learned. In "adult" networks that had achieved mature synaptic connectivity upon prior learning of the Roman alphabet, imposition of apoptosis/neurogenesis before learning increasingly novel information (alternate Roman < Russian < Hebrew) reveals optimality of informatic cost benefits when rates of turnover are geared in proportion to the degree of novelty. These findings predict that flexible control of rates of apoptosis-neurogenesis within plastic, mature neural systems optimizes learning attributes under varying degrees of contextual change, and that failures in this regulation may define a role for adult hippocampal neurogenesis in novelty- and stress-responsive psychiatric disorders.

Do neural nets learn statistical laws behind natural language?

PubMed

Takahashi, Shuntaro; Tanaka-Ishii, Kumiko

2017-01-01

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

Do neural nets learn statistical laws behind natural language?

PubMed Central

Takahashi, Shuntaro

2017-01-01

The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM) effectively reproduces Zipf’s law and Heaps’ law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf’s law and Heaps’ law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks. PMID:29287076

Neural dynamic programming and its application to control systems

NASA Astrophysics Data System (ADS)

Seong, Chang-Yun

There are few general practical feedback control methods for nonlinear MIMO (multi-input-multi-output) systems, although such methods exist for their linear counterparts. Neural Dynamic Programming (NDP) is proposed as a practical design method of optimal feedback controllers for nonlinear MIMO systems. NDP is an offspring of both neural networks and optimal control theory. In optimal control theory, the optimal solution to any nonlinear MIMO control problem may be obtained from the Hamilton-Jacobi-Bellman equation (HJB) or the Euler-Lagrange equations (EL). The two sets of equations provide the same solution in different forms: EL leads to a sequence of optimal control vectors, called Feedforward Optimal Control (FOC); HJB yields a nonlinear optimal feedback controller, called Dynamic Programming (DP). DP produces an optimal solution that can reject disturbances and uncertainties as a result of feedback. Unfortunately, computation and storage requirements associated with DP solutions can be problematic, especially for high-order nonlinear systems. This dissertation presents an approximate technique for solving the DP problem based on neural network techniques that provides many of the performance benefits (e.g., optimality and feedback) of DP and benefits from the numerical properties of neural networks. We formulate neural networks to approximate optimal feedback solutions whose existence DP justifies. We show the conditions under which NDP closely approximates the optimal solution. Finally, we introduce the learning operator characterizing the learning process of the neural network in searching the optimal solution. The analysis of the learning operator provides not only a fundamental understanding of the learning process in neural networks but also useful guidelines for selecting the number of weights of the neural network. As a result, NDP finds---with a reasonable amount of computation and storage---the optimal feedback solutions to nonlinear MIMO control problems that would be very difficult to solve with DP. NDP was demonstrated on several applications such as the lateral autopilot logic for a Boeing 747, the minimum fuel control of a double-integrator plant with bounded control, the backward steering of a two-trailer truck, and the set-point control of a two-link robot arm.

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

PubMed

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

2018-02-01

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

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James A. (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Texas, Houston. Topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

The Livermore Brain: Massive Deep Learning Networks Enabled by High Performance Computing

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen, Barry Y.

The proliferation of inexpensive sensor technologies like the ubiquitous digital image sensors has resulted in the collection and sharing of vast amounts of unsorted and unexploited raw data. Companies and governments who are able to collect and make sense of large datasets to help them make better decisions more rapidly will have a competitive advantage in the information era. Machine Learning technologies play a critical role for automating the data understanding process; however, to be maximally effective, useful intermediate representations of the data are required. These representations or “features” are transformations of the raw data into a form where patternsmore » are more easily recognized. Recent breakthroughs in Deep Learning have made it possible to learn these features from large amounts of labeled data. The focus of this project is to develop and extend Deep Learning algorithms for learning features from vast amounts of unlabeled data and to develop the HPC neural network training platform to support the training of massive network models. This LDRD project succeeded in developing new unsupervised feature learning algorithms for images and video and created a scalable neural network training toolkit for HPC. Additionally, this LDRD helped create the world’s largest freely-available image and video dataset supporting open multimedia research and used this dataset for training our deep neural networks. This research helped LLNL capture several work-for-others (WFO) projects, attract new talent, and establish collaborations with leading academic and commercial partners. Finally, this project demonstrated the successful training of the largest unsupervised image neural network using HPC resources and helped establish LLNL leadership at the intersection of Machine Learning and HPC research.« less

Deep learning with coherent nanophotonic circuits

NASA Astrophysics Data System (ADS)

Shen, Yichen; Harris, Nicholas C.; Skirlo, Scott; Prabhu, Mihika; Baehr-Jones, Tom; Hochberg, Michael; Sun, Xin; Zhao, Shijie; Larochelle, Hugo; Englund, Dirk; Soljačić, Marin

2017-07-01

Artificial neural networks are computational network models inspired by signal processing in the brain. These models have dramatically improved performance for many machine-learning tasks, including speech and image recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made towards developing electronic architectures tuned to implement artificial neural networks that exhibit improved computational speed and accuracy. Here, we propose a new architecture for a fully optical neural network that, in principle, could offer an enhancement in computational speed and power efficiency over state-of-the-art electronics for conventional inference tasks. We experimentally demonstrate the essential part of the concept using a programmable nanophotonic processor featuring a cascaded array of 56 programmable Mach-Zehnder interferometers in a silicon photonic integrated circuit and show its utility for vowel recognition.

Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship

ERIC Educational Resources Information Center

Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.

2010-01-01

The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…

Are Student Evaluations of Teaching Effectiveness Valid for Measuring Student Learning Outcomes in Business Related Classes? A Neural Network and Bayesian Analyses

ERIC Educational Resources Information Center

Galbraith, Craig S.; Merrill, Gregory B.; Kline, Doug M.

2012-01-01

In this study we investigate the underlying relational structure between student evaluations of teaching effectiveness (SETEs) and achievement of student learning outcomes in 116 business related courses. Utilizing traditional statistical techniques, a neural network analysis and a Bayesian data reduction and classification algorithm, we find…

Learning the Relationship between the Primary Structure of HIV Envelope Glycoproteins and Neutralization Activity of Particular Antibodies by Using Artificial Neural Networks

PubMed Central

Buiu, Cătălin; Putz, Mihai V.; Avram, Speranta

2016-01-01

The dependency between the primary structure of HIV envelope glycoproteins (ENV) and the neutralization data for given antibodies is very complicated and depends on a large number of factors, such as the binding affinity of a given antibody for a given ENV protein, and the intrinsic infection kinetics of the viral strain. This paper presents a first approach to learning these dependencies using an artificial feedforward neural network which is trained to learn from experimental data. The results presented here demonstrate that the trained neural network is able to generalize on new viral strains and to predict reliable values of neutralizing activities of given antibodies against HIV-1. PMID:27727189

Neuromorphic Optical Signal Processing and Image Understanding for Automated Target Recognition

DTIC Science & Technology

1989-12-01

34 Stochastic Learning Machine " Neuromorphic Target Identification * Cognitive Networks 3. Conclusions ..... ................ .. 12 4. Publications...16 5. References ...... ................... . 17 6. Appendices ....... .................. 18 I. Optoelectronic Neural Networks and...Learning Machines. II. Stochastic Optical Learning Machine. III. Learning Network for Extrapolation AccesFon For and Radar Target Identification

Tracking Plasticity: Effects of Long-Term Rehearsal in Expert Dancers Encoding Music to Movement

PubMed Central

Bar, Rachel J.; DeSouza, Joseph F. X.

2016-01-01

Our knowledge of neural plasticity suggests that neural networks show adaptation to environmental and intrinsic change. In particular, studies investigating the neuroplastic changes associated with learning and practicing motor tasks have shown that practicing such tasks results in an increase in neural activation in several specific brain regions. However, studies comparing experts and non-experts suggest that experts employ less neuronal activation than non-experts when performing a familiar motor task. Here, we aimed to determine the long-term changes in neural networks associated with learning a new dance in professional ballet dancers over 34 weeks. Subjects visualized dance movements to music while undergoing fMRI scanning at four time points over 34-weeks. Results demonstrated that initial learning and performance at seven weeks led to increases in activation in cortical regions during visualization compared to the first week. However, at 34 weeks, the cortical networks showed reduced activation compared to week seven. Specifically, motor learning and performance over the 34 weeks showed the typical inverted-U-shaped function of learning. Further, our result demonstrate that learning of a motor sequence of dance movements to music in the real world can be visualized by expert dancers using fMRI and capture highly significant modeled fits of the brain network variance of BOLD signals from early learning to expert level performance. PMID:26824475

A comparison of back propagation and Generalized Regression Neural Networks performance in neutron spectrometry.

PubMed

Martínez-Blanco, Ma Del Rosario; Ornelas-Vargas, Gerardo; Solís-Sánchez, Luis Octavio; Castañeda-Miranada, Rodrigo; Vega-Carrillo, Héctor René; Celaya-Padilla, José M; Garza-Veloz, Idalia; Martínez-Fierro, Margarita; Ortiz-Rodríguez, José Manuel

2016-11-01

The process of unfolding the neutron energy spectrum has been subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the research of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in neutron spectrometry and dosimetry domains, however, the structure and learning parameters are factors that highly impact in the networks performance. In ANN domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, requiring no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training on the development data. In the network development phase, the only hurdle is to optimize the hyper-parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained it can be observed that despite the very similar results, GRNN performs better than BPNN. Copyright © 2016 Elsevier Ltd. All rights reserved.

Experiments in Neural-Network Control of a Free-Flying Space Robot

NASA Technical Reports Server (NTRS)

Wilson, Edward

1995-01-01

Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.

Building on prior knowledge without building it in.

PubMed

Hansen, Steven S; Lampinen, Andrew K; Suri, Gaurav; McClelland, James L

2017-01-01

Lake et al. propose that people rely on "start-up software," "causal models," and "intuitive theories" built using compositional representations to learn new tasks more efficiently than some deep neural network models. We highlight the many drawbacks of a commitment to compositional representations and describe our continuing effort to explore how the ability to build on prior knowledge and to learn new tasks efficiently could arise through learning in deep neural networks.

Gait Recognition Based on Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Sokolova, A.; Konushin, A.

2017-05-01

In this work we investigate the problem of people recognition by their gait. For this task, we implement deep learning approach using the optical flow as the main source of motion information and combine neural feature extraction with the additional embedding of descriptors for representation improvement. In order to find the best heuristics, we compare several deep neural network architectures, learning and classification strategies. The experiments were made on two popular datasets for gait recognition, so we investigate their advantages and disadvantages and the transferability of considered methods.

Neural Decoder for Topological Codes

NASA Astrophysics Data System (ADS)

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.

Towards representation of a perceptual color manifold using associative memory for color constancy.

PubMed

Seow, Ming-Jung; Asari, Vijayan K

2009-01-01

In this paper, we propose the concept of a manifold of color perception through empirical observation that the center-surround properties of images in a perceptually similar environment define a manifold in the high dimensional space. Such a manifold representation can be learned using a novel recurrent neural network based learning algorithm. Unlike the conventional recurrent neural network model in which the memory is stored in an attractive fixed point at discrete locations in the state space, the dynamics of the proposed learning algorithm represent memory as a nonlinear line of attraction. The region of convergence around the nonlinear line is defined by the statistical characteristics of the training data. This learned manifold can then be used as a basis for color correction of the images having different color perception to the learned color perception. Experimental results show that the proposed recurrent neural network learning algorithm is capable of color balance the lighting variations in images captured in different environments successfully.

Using Deep Learning for Gamma Ray Source Detection at the First G-APD Cherenkov Telescope (FACT)

NASA Astrophysics Data System (ADS)

Bieker, Jacob

2018-06-01

Finding gamma-ray sources is of paramount importance for Imaging Air Cherenkov Telescopes (IACT). This study looks at using deep neural networks on data from the First G-APD Cherenkov Telescope (FACT) as a proof-of-concept of finding gamma-ray sources with deep learning for the upcoming Cherenkov Telescope Array (CTA). In this study, FACT’s individual photon level observation data from the last 5 years was used with convolutional neural networks to determine if one or more sources were present. The neural networks used various architectures to determine which architectures were most successful in finding sources. Neural networks offer a promising method for finding faint and extended gamma-ray sources for IACTs. With further improvement and modifications, they offer a compelling method for source detection for the next generation of IACTs.

Competitive STDP Learning of Overlapping Spatial Patterns.

PubMed

Krunglevicius, Dalius

2015-08-01

Spike-timing-dependent plasticity (STDP) is a set of Hebbian learning rules firmly based on biological evidence. It has been demonstrated that one of the STDP learning rules is suited for learning spatiotemporal patterns. When multiple neurons are organized in a simple competitive spiking neural network, this network is capable of learning multiple distinct patterns. If patterns overlap significantly (i.e., patterns are mutually inclusive), however, competition would not preclude trained neuron's responding to a new pattern and adjusting synaptic weights accordingly. This letter presents a simple neural network that combines vertical inhibition and Euclidean distance-dependent synaptic strength factor. This approach helps to solve the problem of pattern size-dependent parameter optimality and significantly reduces the probability of a neuron's forgetting an already learned pattern. For demonstration purposes, the network was trained for the first ten letters of the Braille alphabet.

Heuristic pattern correction scheme using adaptively trained generalized regression neural networks.

PubMed

Hoya, T; Chambers, J A

2001-01-01

In many pattern classification problems, an intelligent neural system is required which can learn the newly encountered but misclassified patterns incrementally, while keeping a good classification performance over the past patterns stored in the network. In the paper, an heuristic pattern correction scheme is proposed using adaptively trained generalized regression neural networks (GRNNs). The scheme is based upon both network growing and dual-stage shrinking mechanisms. In the network growing phase, a subset of the misclassified patterns in each incoming data set is iteratively added into the network until all the patterns in the incoming data set are classified correctly. Then, the redundancy in the growing phase is removed in the dual-stage network shrinking. Both long- and short-term memory models are considered in the network shrinking, which are motivated from biological study of the brain. The learning capability of the proposed scheme is investigated through extensive simulation studies.

Prefrontal Cortex Networks Shift from External to Internal Modes during Learning.

PubMed

Brincat, Scott L; Miller, Earl K

2016-09-14

As we learn about items in our environment, their neural representations become increasingly enriched with our acquired knowledge. But there is little understanding of how network dynamics and neural processing related to external information changes as it becomes laden with "internal" memories. We sampled spiking and local field potential activity simultaneously from multiple sites in the lateral prefrontal cortex (PFC) and the hippocampus (HPC)-regions critical for sensory associations-of monkeys performing an object paired-associate learning task. We found that in the PFC, evoked potentials to, and neural information about, external sensory stimulation decreased while induced beta-band (∼11-27 Hz) oscillatory power and synchrony associated with "top-down" or internal processing increased. By contrast, the HPC showed little evidence of learning-related changes in either spiking activity or network dynamics. The results suggest that during associative learning, PFC networks shift their resources from external to internal processing. As we learn about items in our environment, their representations in our brain become increasingly enriched with our acquired "top-down" knowledge. We found that in the prefrontal cortex, but not the hippocampus, processing of external sensory inputs decreased while internal network dynamics related to top-down processing increased. The results suggest that during learning, prefrontal cortex networks shift their resources from external (sensory) to internal (memory) processing. Copyright © 2016 the authors 0270-6474/16/369739-16$15.00/0.

Prefrontal Cortex Networks Shift from External to Internal Modes during Learning

PubMed Central

Brincat, Scott L.

2016-01-01

As we learn about items in our environment, their neural representations become increasingly enriched with our acquired knowledge. But there is little understanding of how network dynamics and neural processing related to external information changes as it becomes laden with “internal” memories. We sampled spiking and local field potential activity simultaneously from multiple sites in the lateral prefrontal cortex (PFC) and the hippocampus (HPC)—regions critical for sensory associations—of monkeys performing an object paired-associate learning task. We found that in the PFC, evoked potentials to, and neural information about, external sensory stimulation decreased while induced beta-band (∼11–27 Hz) oscillatory power and synchrony associated with “top-down” or internal processing increased. By contrast, the HPC showed little evidence of learning-related changes in either spiking activity or network dynamics. The results suggest that during associative learning, PFC networks shift their resources from external to internal processing. SIGNIFICANCE STATEMENT As we learn about items in our environment, their representations in our brain become increasingly enriched with our acquired “top-down” knowledge. We found that in the prefrontal cortex, but not the hippocampus, processing of external sensory inputs decreased while internal network dynamics related to top-down processing increased. The results suggest that during learning, prefrontal cortex networks shift their resources from external (sensory) to internal (memory) processing. PMID:27629722

Superior Generalization Capability of Hardware-Learing Algorithm Developed for Self-Learning Neuron-MOS Neural Networks

NASA Astrophysics Data System (ADS)

Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro

1995-02-01

We have investigated the learning performance of the hardware backpropagation (HBP) algorithm, a hardware-oriented learning algorithm developed for the self-learning architecture of neural networks constructed using neuron MOS (metal-oxide-semiconductor) transistors. The solution to finding a mirror symmetry axis in a 4×4 binary pixel array was tested by computer simulation based on the HBP algorithm. Despite the inherent restrictions imposed on the hardware-learning algorithm, HBP exhibits equivalent learning performance to that of the original backpropagation (BP) algorithm when all the pertinent parameters are optimized. Very importantly, we have found that HBP has a superior generalization capability over BP; namely, HBP exhibits higher performance in solving problems that the network has not yet learnt.

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation.

PubMed

Hohman, Fred; Hodas, Nathan; Chau, Duen Horng

2017-05-01

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as "black-boxes" due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user's data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

A common neural network differentially mediates direct and social fear learning.

PubMed

Lindström, Björn; Haaker, Jan; Olsson, Andreas

2018-02-15

Across species, fears often spread between individuals through social learning. Yet, little is known about the neural and computational mechanisms underlying social learning. Addressing this question, we compared social and direct (Pavlovian) fear learning showing that they showed indistinguishable behavioral effects, and involved the same cross-modal (self/other) aversive learning network, centered on the amygdala, the anterior insula (AI), and the anterior cingulate cortex (ACC). Crucially, the information flow within this network differed between social and direct fear learning. Dynamic causal modeling combined with reinforcement learning modeling revealed that the amygdala and AI provided input to this network during direct and social learning, respectively. Furthermore, the AI gated learning signals based on surprise (associability), which were conveyed to the ACC, in both learning modalities. Our findings provide insights into the mechanisms underlying social fear learning, with implications for understanding common psychological dysfunctions, such as phobias and other anxiety disorders. Copyright © 2017 Elsevier Inc. All rights reserved.

Higher-Order Neural Networks Recognize Patterns

NASA Technical Reports Server (NTRS)

Reid, Max B.; Spirkovska, Lilly; Ochoa, Ellen

1996-01-01

Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.

Comparative Analysis of Soft Computing Models in Prediction of Bending Rigidity of Cotton Woven Fabrics

NASA Astrophysics Data System (ADS)

Guruprasad, R.; Behera, B. K.

2015-10-01

Quantitative prediction of fabric mechanical properties is an essential requirement for design engineering of textile and apparel products. In this work, the possibility of prediction of bending rigidity of cotton woven fabrics has been explored with the application of Artificial Neural Network (ANN) and two hybrid methodologies, namely Neuro-genetic modeling and Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling. For this purpose, a set of cotton woven grey fabrics was desized, scoured and relaxed. The fabrics were then conditioned and tested for bending properties. With the database thus created, a neural network model was first developed using back propagation as the learning algorithm. The second model was developed by applying a hybrid learning strategy, in which genetic algorithm was first used as a learning algorithm to optimize the number of neurons and connection weights of the neural network. The Genetic algorithm optimized network structure was further allowed to learn using back propagation algorithm. In the third model, an ANFIS modeling approach was attempted to map the input-output data. The prediction performances of the models were compared and a sensitivity analysis was reported. The results show that the prediction by neuro-genetic and ANFIS models were better in comparison with that of back propagation neural network model.

Temporal neural networks and transient analysis of complex engineering systems

NASA Astrophysics Data System (ADS)

Uluyol, Onder

A theory is introduced for a multi-layered Local Output Gamma Feedback (LOGF) neural network within the paradigm of Locally-Recurrent Globally-Feedforward neural networks. It is developed for the identification, prediction, and control tasks of spatio-temporal systems and allows for the presentation of different time scales through incorporation of a gamma memory. It is initially applied to the tasks of sunspot and Mackey-Glass series prediction as benchmarks, then it is extended to the task of power level control of a nuclear reactor at different fuel cycle conditions. The developed LOGF neuron model can also be viewed as a Transformed Input and State (TIS) Gamma memory for neural network architectures for temporal processing. The novel LOGF neuron model extends the static neuron model by incorporating into it a short-term memory structure in the form of a digital gamma filter. A feedforward neural network made up of LOGF neurons can thus be used to model dynamic systems. A learning algorithm based upon the Backpropagation-Through-Time (BTT) approach is derived. It is applicable for training a general L-layer LOGF neural network. The spatial and temporal weights and parameters of the network are iteratively optimized for a given problem using the derived learning algorithm.

Neural Network Machine Learning and Dimension Reduction for Data Visualization

NASA Technical Reports Server (NTRS)

Liles, Charles A.

2014-01-01

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

The application of neural network PID controller to control the light gasoline etherification

NASA Astrophysics Data System (ADS)

Cheng, Huanxin; Zhang, Yimin; Kong, Lingling; Meng, Xiangyong

2017-06-01

Light gasoline etherification technology can effectively improve the quality of gasoline, which is environmental- friendly and economical. By combining BP neural network and PID control and using BP neural network self-learning ability for online parameter tuning, this method optimizes the parameters of PID controller and applies this to the Fcc gas flow control to achieve the control of the final product- heavy oil concentration. Finally, through MATLAB simulation, it is found that the PID control based on BP neural network has better controlling effect than traditional PID control.

A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems.

PubMed

Zhao, Haiquan; Zeng, Xiangping; Zhang, Jiashu; Liu, Yangguang; Wang, Xiaomin; Li, Tianrui

2011-01-01

To eliminate nonlinear channel distortion in chaotic communication systems, a novel joint-processing adaptive nonlinear equalizer based on a pipelined recurrent neural network (JPRNN) is proposed, using a modified real-time recurrent learning (RTRL) algorithm. Furthermore, an adaptive amplitude RTRL algorithm is adopted to overcome the deteriorating effect introduced by the nesting process. Computer simulations illustrate that the proposed equalizer outperforms the pipelined recurrent neural network (PRNN) and recurrent neural network (RNN) equalizers. Copyright © 2010 Elsevier Ltd. All rights reserved.

Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks.

PubMed

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

2018-06-13

Deep learning has been increasingly used to solve a number of problems with state-of-the-art performance in a wide variety of fields. In biology, deep learning can be applied to reduce feature extraction time and achieve high levels of performance. In our present work, we apply deep learning via two-dimensional convolutional neural networks and position-specific scoring matrices to classify Rab protein molecules, which are main regulators in membrane trafficking for transferring proteins and other macromolecules throughout the cell. The functional loss of specific Rab molecular functions has been implicated in a variety of human diseases, e.g., choroideremia, intellectual disabilities, cancer. Therefore, creating a precise model for classifying Rabs is crucial in helping biologists understand the molecular functions of Rabs and design drug targets according to such specific human disease information. We constructed a robust deep neural network for classifying Rabs that achieved an accuracy of 99%, 99.5%, 96.3%, and 97.6% for each of four specific molecular functions. Our approach demonstrates superior performance to traditional artificial neural networks. Therefore, from our proposed study, we provide both an effective tool for classifying Rab proteins and a basis for further research that can improve the performance of biological modeling using deep neural networks. Copyright © 2018 Elsevier Inc. All rights reserved.

Neural joint control for Space Shuttle Remote Manipulator System

NASA Technical Reports Server (NTRS)

Atkins, Mark A.; Cox, Chadwick J.; Lothers, Michael D.; Pap, Robert M.; Thomas, Charles R.

1992-01-01

Neural networks are being used to control a robot arm in a telerobotic operation. The concept uses neural networks for both joint and inverse kinematics in a robotic control application. An upper level neural network is trained to learn inverse kinematic mappings. The output, a trajectory, is then fed to the Decentralized Adaptive Joint Controllers. This neural network implementation has shown that the controlled arm recovers from unexpected payload changes while following the reference trajectory. The neural network-based decentralized joint controller is faster, more robust and efficient than conventional approaches. Implementations of this architecture are discussed that would relax assumptions about dynamics, obstacles, and heavy loads. This system is being developed to use with the Space Shuttle Remote Manipulator System.

Real-Time Adaptive Color Segmentation by Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2004-01-01

Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural network and algorithm is that each update of synaptic weights takes place in conjunction with the addition of another hidden unit, which then remains in place as still other hidden units are added on subsequent iterations. For a given training pattern, the synaptic weight between (1) the inputs and the previously added hidden units and (2) the newly added hidden unit is updated by an amount proportional to the partial derivative of a quadratic error function with respect to the synaptic weight. The synaptic weight between the newly added hidden unit and each output unit is given by a more complex function that involves the errors between the outputs and their target values, the transfer functions (hyperbolic tangents) of the neural units, and the derivatives of the transfer functions.

Using fuzzy logic to integrate neural networks and knowledge-based systems

NASA Technical Reports Server (NTRS)

Yen, John

1991-01-01

Outlined here is a novel hybrid architecture that uses fuzzy logic to integrate neural networks and knowledge-based systems. The author's approach offers important synergistic benefits to neural nets, approximate reasoning, and symbolic processing. Fuzzy inference rules extend symbolic systems with approximate reasoning capabilities, which are used for integrating and interpreting the outputs of neural networks. The symbolic system captures meta-level information about neural networks and defines its interaction with neural networks through a set of control tasks. Fuzzy action rules provide a robust mechanism for recognizing the situations in which neural networks require certain control actions. The neural nets, on the other hand, offer flexible classification and adaptive learning capabilities, which are crucial for dynamic and noisy environments. By combining neural nets and symbolic systems at their system levels through the use of fuzzy logic, the author's approach alleviates current difficulties in reconciling differences between low-level data processing mechanisms of neural nets and artificial intelligence systems.

Design of a universal two-layered neural network derived from the PLI theory

NASA Astrophysics Data System (ADS)

Hu, Chia-Lun J.

2004-05-01

The if-and-only-if (IFF) condition that a set of M analog-to-digital vector-mapping relations can be learned by a one-layered-feed-forward neural network (OLNN) is that all the input analog vectors dichotomized by the i-th output bit must be positively, linearly independent, or PLI. If they are not PLI, then the OLNN just cannot learn no matter what learning rules is employed because the solution of the connection matrix does not exist mathematically. However, in this case, one can still design a parallel-cascaded, two-layered, perceptron (PCTLP) to acheive this general mapping goal. The design principle of this "universal" neural network is derived from the major mathematical properties of the PLI theory - changing the output bits of the dependent relations existing among the dichotomized input vectors to make the PLD relations PLI. Then with a vector concatenation technique, the required mapping can still be learned by this PCTLP system with very high efficiency. This paper will report in detail the mathematical derivation of the general design principle and the design procedures of the PCTLP neural network system. It then will be verified in general by a practical numerical example.

Neural Networks for Modeling and Control of Particle Accelerators

DOE Office of Scientific and Technical Information (OSTI.GOV)

Edelen, A. L.; Biedron, S. G.; Chase, B. E.

Myriad nonlinear and complex physical phenomena are host to particle accelerators. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems,more » as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Moreover, many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. For the purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We also describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.« less

Neural Networks for Modeling and Control of Particle Accelerators

NASA Astrophysics Data System (ADS)

Edelen, A. L.; Biedron, S. G.; Chase, B. E.; Edstrom, D.; Milton, S. V.; Stabile, P.

2016-04-01

Particle accelerators are host to myriad nonlinear and complex physical phenomena. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems, as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. The purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.

Neural Networks for Modeling and Control of Particle Accelerators

DOE PAGES

Edelen, A. L.; Biedron, S. G.; Chase, B. E.; ...

2016-04-01

Myriad nonlinear and complex physical phenomena are host to particle accelerators. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems,more » as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Moreover, many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. For the purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We also describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.« less

Improving Maritime Domain Awareness Using Neural Networks for Target of Interest Classification

DTIC Science & Technology

2015-03-01

spreading SCG scaled conjugate gradient xv THIS PAGE INTENTIONALLY LEFT BLANK xvi EXECUTIVE SUMMARY The research detailed in this thesis is a...algorithms were explored for training the neural networks: resilient backpropagation (RP) and scaled conjugate gradient backpropagation ( SCG ). The...results of the neural network training performance are presented using mean squared error convergence plots. In all implementations, the SCG learning

Where’s the Noise? Key Features of Spontaneous Activity and Neural Variability Arise through Learning in a Deterministic Network

PubMed Central

Hartmann, Christoph; Lazar, Andreea; Nessler, Bernhard; Triesch, Jochen

2015-01-01

Even in the absence of sensory stimulation the brain is spontaneously active. This background “noise” seems to be the dominant cause of the notoriously high trial-to-trial variability of neural recordings. Recent experimental observations have extended our knowledge of trial-to-trial variability and spontaneous activity in several directions: 1. Trial-to-trial variability systematically decreases following the onset of a sensory stimulus or the start of a motor act. 2. Spontaneous activity states in sensory cortex outline the region of evoked sensory responses. 3. Across development, spontaneous activity aligns itself with typical evoked activity patterns. 4. The spontaneous brain activity prior to the presentation of an ambiguous stimulus predicts how the stimulus will be interpreted. At present it is unclear how these observations relate to each other and how they arise in cortical circuits. Here we demonstrate that all of these phenomena can be accounted for by a deterministic self-organizing recurrent neural network model (SORN), which learns a predictive model of its sensory environment. The SORN comprises recurrently coupled populations of excitatory and inhibitory threshold units and learns via a combination of spike-timing dependent plasticity (STDP) and homeostatic plasticity mechanisms. Similar to balanced network architectures, units in the network show irregular activity and variable responses to inputs. Additionally, however, the SORN exhibits sequence learning abilities matching recent findings from visual cortex and the network’s spontaneous activity reproduces the experimental findings mentioned above. Intriguingly, the network’s behaviour is reminiscent of sampling-based probabilistic inference, suggesting that correlates of sampling-based inference can develop from the interaction of STDP and homeostasis in deterministic networks. We conclude that key observations on spontaneous brain activity and the variability of neural responses can be accounted for by a simple deterministic recurrent neural network which learns a predictive model of its sensory environment via a combination of generic neural plasticity mechanisms. PMID:26714277

Representational Distance Learning for Deep Neural Networks

PubMed Central

McClure, Patrick; Kriegeskorte, Nikolaus

2016-01-01

Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Representational spaces of the student and the teacher are characterized by representational distance matrices (RDMs). We propose representational distance learning (RDL), a stochastic gradient descent method that drives the RDMs of the student to approximate the RDMs of the teacher. We demonstrate that RDL is competitive with other transfer learning techniques for two publicly available benchmark computer vision datasets (MNIST and CIFAR-100), while allowing for architectural differences between student and teacher. By pulling the student's RDMs toward those of the teacher, RDL significantly improved visual classification performance when compared to baseline networks that did not use transfer learning. In the future, RDL may enable combined supervised training of deep neural networks using task constraints (e.g., images and category labels) and constraints from brain-activity measurements, so as to build models that replicate the internal representational spaces of biological brains. PMID:28082889

Representational Distance Learning for Deep Neural Networks.

PubMed

McClure, Patrick; Kriegeskorte, Nikolaus

2016-01-01

Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Representational spaces of the student and the teacher are characterized by representational distance matrices (RDMs). We propose representational distance learning (RDL), a stochastic gradient descent method that drives the RDMs of the student to approximate the RDMs of the teacher. We demonstrate that RDL is competitive with other transfer learning techniques for two publicly available benchmark computer vision datasets (MNIST and CIFAR-100), while allowing for architectural differences between student and teacher. By pulling the student's RDMs toward those of the teacher, RDL significantly improved visual classification performance when compared to baseline networks that did not use transfer learning. In the future, RDL may enable combined supervised training of deep neural networks using task constraints (e.g., images and category labels) and constraints from brain-activity measurements, so as to build models that replicate the internal representational spaces of biological brains.

A neural network controller for automated composite manufacturing

NASA Technical Reports Server (NTRS)

Lichtenwalner, Peter F.

1994-01-01

At McDonnell Douglas Aerospace (MDA), an artificial neural network based control system has been developed and implemented to control laser heating for the fiber placement composite manufacturing process. This neurocontroller learns an approximate inverse model of the process on-line to provide performance that improves with experience and exceeds that of conventional feedback control techniques. When untrained, the control system behaves as a proportional plus integral (PI) controller. However after learning from experience, the neural network feedforward control module provides control signals that greatly improve temperature tracking performance. Faster convergence to new temperature set points and reduced temperature deviation due to changing feed rate have been demonstrated on the machine. A Cerebellar Model Articulation Controller (CMAC) network is used for inverse modeling because of its rapid learning performance. This control system is implemented in an IBM compatible 386 PC with an A/D board interface to the machine.

Perception Evolution Network Based on Cognition Deepening Model--Adapting to the Emergence of New Sensory Receptor.

PubMed

Xing, Youlu; Shen, Furao; Zhao, Jinxi

2016-03-01

The proposed perception evolution network (PEN) is a biologically inspired neural network model for unsupervised learning and online incremental learning. It is able to automatically learn suitable prototypes from learning data in an incremental way, and it does not require the predefined prototype number or the predefined similarity threshold. Meanwhile, being more advanced than the existing unsupervised neural network model, PEN permits the emergence of a new dimension of perception in the perception field of the network. When a new dimension of perception is introduced, PEN is able to integrate the new dimensional sensory inputs with the learned prototypes, i.e., the prototypes are mapped to a high-dimensional space, which consists of both the original dimension and the new dimension of the sensory inputs. In the experiment, artificial data and real-world data are used to test the proposed PEN, and the results show that PEN can work effectively.

Bidirectional extreme learning machine for regression problem and its learning effectiveness.

PubMed

Yang, Yimin; Wang, Yaonan; Yuan, Xiaofang

2012-09-01

It is clear that the learning effectiveness and learning speed of neural networks are in general far slower than required, which has been a major bottleneck for many applications. Recently, a simple and efficient learning method, referred to as extreme learning machine (ELM), was proposed by Huang , which has shown that, compared to some conventional methods, the training time of neural networks can be reduced by a thousand times. However, one of the open problems in ELM research is whether the number of hidden nodes can be further reduced without affecting learning effectiveness. This brief proposes a new learning algorithm, called bidirectional extreme learning machine (B-ELM), in which some hidden nodes are not randomly selected. In theory, this algorithm tends to reduce network output error to 0 at an extremely early learning stage. Furthermore, we find a relationship between the network output error and the network output weights in the proposed B-ELM. Simulation results demonstrate that the proposed method can be tens to hundreds of times faster than other incremental ELM algorithms.

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

NASA Astrophysics Data System (ADS)

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

2018-02-01

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

Artificial Neural Networks and Instructional Technology.

ERIC Educational Resources Information Center

Carlson, Patricia A.

1991-01-01

Artificial neural networks (ANN), part of artificial intelligence, are discussed. Such networks are fed sample cases (training sets), learn how to recognize patterns in the sample data, and use this experience in handling new cases. Two cognitive roles for ANNs (intelligent filters and spreading, associative memories) are examined. Prototypes…

Radar signal categorization using a neural network

NASA Technical Reports Server (NTRS)

Anderson, James A.; Gately, Michael T.; Penz, P. Andrew; Collins, Dean R.

1991-01-01

Neural networks were used to analyze a complex simulated radar environment which contains noisy radar pulses generated by many different emitters. The neural network used is an energy minimizing network (the BSB model) which forms energy minima - attractors in the network dynamical system - based on learned input data. The system first determines how many emitters are present (the deinterleaving problem). Pulses from individual simulated emitters give rise to separate stable attractors in the network. Once individual emitters are characterized, it is possible to make tentative identifications of them based on their observed parameters. As a test of this idea, a neural network was used to form a small data base that potentially could make emitter identifications.

Inversion of quasi-3D DC resistivity imaging data using artificial neural networks

NASA Astrophysics Data System (ADS)

Neyamadpour, Ahmad; Wan Abdullah, W. A. T.; Taib, Samsudin

2010-02-01

The objective of this paper is to investigate the applicability of artificial neural networks in inverting quasi-3D DC resistivity imaging data. An electrical resistivity imaging survey was carried out along seven parallel lines using a dipole-dipole array to confirm the validation of the results of an inversion using an artificial neural network technique. The model used to produce synthetic data to train the artificial neural network was a homogeneous medium of 100Ωm resistivity with an embedded anomalous body of 1000Ωm resistivity. The network was trained using 21 datasets (comprising 12159 data points) and tested on another 11 synthetic datasets (comprising 6369 data points) and on real field data. Another 24 test datasets (comprising 13896 data points) consisting of different resistivities for the background and the anomalous bodies were used in order to test the interpolation and extrapolation of network properties. Different learning paradigms were tried in the training process of the neural network, with the resilient propagation paradigm being the most efficient. The number of nodes, hidden layers, and efficient values for learning rate and momentum coefficient have been studied. Although a significant correlation between results of the neural network and the conventional robust inversion technique was found, the ANN results show more details of the subsurface structure, and the RMS misfits for the results of the neural network are less than seen with conventional methods. The interpreted results show that the trained network was able to invert quasi-3D electrical resistivity imaging data obtained by dipole-dipole configuration both rapidly and accurately.

Spatial-Temporal Reasoning Applications of Computational Intelligence in the Game of Go and Computer Networks

DTIC Science & Technology

2012-01-01

dimensionality, Tesauro used a backpropagation- based , three-layer neural network and implemented the outcome from a self-play game as the reinforcement signal...a school of fish, flock of birds, and colony of ants. Our literature review reveals that no one has used PSO to train the neural network ...trained with a variant of PSO called cellular PSO (CPSO). CSRN is a supervised learning neural network (SLNN). The proposed algorithm for the

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

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

2015-12-01

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

Deep learning in bioinformatics.

PubMed

Min, Seonwoo; Lee, Byunghan; Yoon, Sungroh

2017-09-01

In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics. Deep learning has advanced rapidly since the early 2000s and now demonstrates state-of-the-art performance in various fields. Accordingly, application of deep learning in bioinformatics to gain insight from data has been emphasized in both academia and industry. Here, we review deep learning in bioinformatics, presenting examples of current research. To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e. omics, biomedical imaging, biomedical signal processing) and deep learning architecture (i.e. deep neural networks, convolutional neural networks, recurrent neural networks, emergent architectures) and present brief descriptions of each study. Additionally, we discuss theoretical and practical issues of deep learning in bioinformatics and suggest future research directions. We believe that this review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Statistical Mechanical Analysis of Online Learning with Weight Normalization in Single Layer Perceptron

NASA Astrophysics Data System (ADS)

Yoshida, Yuki; Karakida, Ryo; Okada, Masato; Amari, Shun-ichi

2017-04-01

Weight normalization, a newly proposed optimization method for neural networks by Salimans and Kingma (2016), decomposes the weight vector of a neural network into a radial length and a direction vector, and the decomposed parameters follow their steepest descent update. They reported that learning with the weight normalization achieves better converging speed in several tasks including image recognition and reinforcement learning than learning with the conventional parameterization. However, it remains theoretically uncovered how the weight normalization improves the converging speed. In this study, we applied a statistical mechanical technique to analyze on-line learning in single layer linear and nonlinear perceptrons with weight normalization. By deriving order parameters of the learning dynamics, we confirmed quantitatively that weight normalization realizes fast converging speed by automatically tuning the effective learning rate, regardless of the nonlinearity of the neural network. This property is realized when the initial value of the radial length is near the global minimum; therefore, our theory suggests that it is important to choose the initial value of the radial length appropriately when using weight normalization.

A New Local Bipolar Autoassociative Memory Based on External Inputs of Discrete Recurrent Neural Networks With Time Delay.

PubMed

Zhou, Caigen; Zeng, Xiaoqin; Luo, Chaomin; Zhang, Huaguang

In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.

The graph neural network model.

PubMed

Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele

2009-01-01

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

Deep learning classification in asteroseismology using an improved neural network: results on 15 000 Kepler red giants and applications to K2 and TESS data

NASA Astrophysics Data System (ADS)

Hon, Marc; Stello, Dennis; Yu, Jie

2018-05-01

Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS, and PLATO, we train classifiers that are able to classify the evolutionary states of lower frequency resolution spectra expected from these missions. Additionally, we provide new classifications for 8633 Kepler red giants, out of which 426 have previously not been classified using asteroseismology. This brings the total to 14983 Kepler red giants classified with our new neural network. We also verify that our classifiers are remarkably robust to suboptimal data, including low signal-to-noise and incorrect training truth labels.

Processing of chromatic information in a deep convolutional neural network.

PubMed

Flachot, Alban; Gegenfurtner, Karl R

2018-04-01

Deep convolutional neural networks are a class of machine-learning algorithms capable of solving non-trivial tasks, such as object recognition, with human-like performance. Little is known about the exact computations that deep neural networks learn, and to what extent these computations are similar to the ones performed by the primate brain. Here, we investigate how color information is processed in the different layers of the AlexNet deep neural network, originally trained on object classification of over 1.2M images of objects in their natural contexts. We found that the color-responsive units in the first layer of AlexNet learned linear features and were broadly tuned to two directions in color space, analogously to what is known of color responsive cells in the primate thalamus. Moreover, these directions are decorrelated and lead to statistically efficient representations, similar to the cardinal directions of the second-stage color mechanisms in primates. We also found, in analogy to the early stages of the primate visual system, that chromatic and achromatic information were segregated in the early layers of the network. Units in the higher layers of AlexNet exhibit on average a lower responsivity for color than units at earlier stages.

Adaptive Optimization of Aircraft Engine Performance Using Neural Networks

NASA Technical Reports Server (NTRS)

Simon, Donald L.; Long, Theresa W.

1995-01-01

Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.

Single image super-resolution based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Zou, Lamei; Luo, Ming; Yang, Weidong; Li, Peng; Jin, Liujia

2018-03-01

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

Learning in Neural Networks: VLSI Implementation Strategies

NASA Technical Reports Server (NTRS)

Duong, Tuan Anh

1995-01-01

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

The use of global image characteristics for neural network pattern recognitions

NASA Astrophysics Data System (ADS)

Kulyas, Maksim O.; Kulyas, Oleg L.; Loshkarev, Aleksey S.

2017-04-01

The recognition system is observed, where the information is transferred by images of symbols generated by a television camera. For descriptors of objects the coefficients of two-dimensional Fourier transformation generated in a special way. For solution of the task of classification the one-layer neural network trained on reference images is used. Fast learning of a neural network with a single neuron calculation of coefficients is applied.

Neural Network Classifier Architectures for Phoneme Recognition. CRC Technical Note No. CRC-TN-92-001.

ERIC Educational Resources Information Center

Treurniet, William

A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

PubMed

Li, Yongcheng; Sun, Rong; Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment

PubMed Central

Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot’s performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks. PMID:27806074

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

PubMed

Somers, M J

1999-04-01

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

Weighted-outer-product associative neural network

NASA Astrophysics Data System (ADS)

Ji, Han-Bing

1991-11-01

A weighted outer product learning (WOPL) scheme for associative memory neural network is presented in which learning orders are incorporated to the Hopfield model. WOPL can be guaranteed to achieve correct recall of some stored datums no matter whether or not they are stable in the Hopfield model, and whether the number of stored datums is small or large. A technically sufficient condition is also discussed for how to suitably choose learning orders to fully utilize WOPL for correct recall of as many stored datums as possible.

Models of Acetylcholine and Dopamine Signals Differentially Improve Neural Representations

PubMed Central

Holca-Lamarre, Raphaël; Lücke, Jörg; Obermayer, Klaus

2017-01-01

Biological and artificial neural networks (ANNs) represent input signals as patterns of neural activity. In biology, neuromodulators can trigger important reorganizations of these neural representations. For instance, pairing a stimulus with the release of either acetylcholine (ACh) or dopamine (DA) evokes long lasting increases in the responses of neurons to the paired stimulus. The functional roles of ACh and DA in rearranging representations remain largely unknown. Here, we address this question using a Hebbian-learning neural network model. Our aim is both to gain a functional understanding of ACh and DA transmission in shaping biological representations and to explore neuromodulator-inspired learning rules for ANNs. We model the effects of ACh and DA on synaptic plasticity and confirm that stimuli coinciding with greater neuromodulator activation are over represented in the network. We then simulate the physiological release schedules of ACh and DA. We measure the impact of neuromodulator release on the network's representation and on its performance on a classification task. We find that ACh and DA trigger distinct changes in neural representations that both improve performance. The putative ACh signal redistributes neural preferences so that more neurons encode stimulus classes that are challenging for the network. The putative DA signal adapts synaptic weights so that they better match the classes of the task at hand. Our model thus offers a functional explanation for the effects of ACh and DA on cortical representations. Additionally, our learning algorithm yields performances comparable to those of state-of-the-art optimisation methods in multi-layer perceptrons while requiring weaker supervision signals and interacting with synaptically-local weight updates. PMID:28690509

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

NASA Technical Reports Server (NTRS)

Williams, Peggy S.

2004-01-01

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

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hohman, Frederick M.; Hodas, Nathan O.; Chau, Duen Horng

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as “black-boxes” due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user’s data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

Learning vector quantization neural networks improve accuracy of transcranial color-coded duplex sonography in detection of middle cerebral artery spasm--preliminary report.

PubMed

Swiercz, Miroslaw; Kochanowicz, Jan; Weigele, John; Hurst, Robert; Liebeskind, David S; Mariak, Zenon; Melhem, Elias R; Krejza, Jaroslaw

2008-01-01

To determine the performance of an artificial neural network in transcranial color-coded duplex sonography (TCCS) diagnosis of middle cerebral artery (MCA) spasm. TCCS was prospectively acquired within 2 h prior to routine cerebral angiography in 100 consecutive patients (54M:46F, median age 50 years). Angiographic MCA vasospasm was classified as mild (<25% of vessel caliber reduction), moderate (25-50%), or severe (>50%). A Learning Vector Quantization neural network classified MCA spasm based on TCCS peak-systolic, mean, and end-diastolic velocity data. During a four-class discrimination task, accurate classification by the network ranged from 64.9% to 72.3%, depending on the number of neurons in the Kohonen layer. Accurate classification of vasospasm ranged from 79.6% to 87.6%, with an accuracy of 84.7% to 92.1% for the detection of moderate-to-severe vasospasm. An artificial neural network may increase the accuracy of TCCS in diagnosis of MCA spasm.

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

PubMed

Carpenter, Gail A.

1997-11-01

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

Unsupervised learning of contextual constraints in neural networks for simultaneous visual processing of multiple objects

NASA Astrophysics Data System (ADS)

Marshall, Jonathan A.

1992-12-01

A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner, is described. EXIN networks develop efficient representation structures for higher-level visual tasks such as segmentation, grouping, transparency, depth perception, and size perception. Exposure to a perceptual environment during a developmental period serves to configure the network to perform appropriate organization of sensory data. A new anti-Hebbian inhibitory learning rule permits superposition of multiple simultaneous neural activations (multiple winners), while maintaining contextual consistency constraints, instead of forcing winner-take-all pattern classifications. The activations can represent multiple patterns simultaneously and can represent uncertainty. The network performs parallel parsing, credit attribution, and simultaneous constraint satisfaction. EXIN networks can learn to represent multiple oriented edges even where they intersect and can learn to represent multiple transparently overlaid surfaces defined by stereo or motion cues. In the case of stereo transparency, the inhibitory learning implements both a uniqueness constraint and permits coactivation of cells representing multiple disparities at the same image location. Thus two or more disparities can be active simultaneously without interference. This behavior is analogous to that of Prazdny's stereo vision algorithm, with the bonus that each binocular point is assigned a unique disparity. In a large implementation, such a NN would also be able to represent effectively the disparities of a cloud of points at random depths, like human observers, and unlike Prazdny's method

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

PubMed

Kam, Hye Jin; Kim, Ha Young

2017-10-01

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

Patterns recognition of electric brain activity using artificial neural networks

NASA Astrophysics Data System (ADS)

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

2017-04-01

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

Beyond Fine Tuning: Adding capacity to leverage few labels

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hodas, Nathan O.; Shaffer, Kyle J.; Yankov, Artem

2017-12-09

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural networks or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning.more » Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.« less

Neural Network Model For Fast Learning And Retrieval

NASA Astrophysics Data System (ADS)

Arsenault, Henri H.; Macukow, Bohdan

1989-05-01

An approach to learning in a multilayer neural network is presented. The proposed network learns by creating interconnections between the input layer and the intermediate layer. In one of the new storage prescriptions proposed, interconnections are excitatory (positive) only and the weights depend on the stored patterns. In the intermediate layer each mother cell is responsible for one stored pattern. Mutually interconnected neurons in the intermediate layer perform a winner-take-all operation, taking into account correlations between stored vectors. The performance of networks using this interconnection prescription is compared with two previously proposed schemes, one using inhibitory connections at the output and one using all-or-nothing interconnections. The network can be used as a content-addressable memory or as a symbolic substitution system that yields an arbitrarily defined output for any input. The training of a model to perform Boolean logical operations is also described. Computer simulations using the network as an autoassociative content-addressable memory show the model to be efficient. Content-addressable associative memories and neural logic modules can be combined to perform logic operations on highly corrupted data.

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 1

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Houston, Clear Lake. The workshop was held April 11 to 13 at the Johnson Space Flight Center. Technical topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

Associative memory in an analog iterated-map neural network

NASA Astrophysics Data System (ADS)

Marcus, C. M.; Waugh, F. R.; Westervelt, R. M.

1990-03-01

The behavior of an analog neural network with parallel dynamics is studied analytically and numerically for two associative-memory learning algorithms, the Hebb rule and the pseudoinverse rule. Phase diagrams in the parameter space of analog gain β and storage ratio α are presented. For both learning rules, the networks have large ``recall'' phases in which retrieval states exist and convergence to a fixed point is guaranteed by a global stability criterion. We also demonstrate numerically that using a reduced analog gain increases the probability of recall starting from a random initial state. This phenomenon is comparable to thermal annealing used to escape local minima but has the advantage of being deterministic, and therefore easily implemented in electronic hardware. Similarities and differences between analog neural networks and networks with two-state neurons at finite temperature are also discussed.

Deep Constrained Siamese Hash Coding Network and Load-Balanced Locality-Sensitive Hashing for Near Duplicate Image Detection.

PubMed

Hu, Weiming; Fan, Yabo; Xing, Junliang; Sun, Liang; Cai, Zhaoquan; Maybank, Stephen

2018-09-01

We construct a new efficient near duplicate image detection method using a hierarchical hash code learning neural network and load-balanced locality-sensitive hashing (LSH) indexing. We propose a deep constrained siamese hash coding neural network combined with deep feature learning. Our neural network is able to extract effective features for near duplicate image detection. The extracted features are used to construct a LSH-based index. We propose a load-balanced LSH method to produce load-balanced buckets in the hashing process. The load-balanced LSH significantly reduces the query time. Based on the proposed load-balanced LSH, we design an effective and feasible algorithm for near duplicate image detection. Extensive experiments on three benchmark data sets demonstrate the effectiveness of our deep siamese hash encoding network and load-balanced LSH.

Bankruptcy prediction based on financial ratios using Jordan Recurrent Neural Networks: a case study in Polish companies

NASA Astrophysics Data System (ADS)

Hardinata, Lingga; Warsito, Budi; Suparti

2018-05-01

Complexity of bankruptcy causes the accurate models of bankruptcy prediction difficult to be achieved. Various prediction models have been developed to improve the accuracy of bankruptcy predictions. Machine learning has been widely used to predict because of its adaptive capabilities. Artificial Neural Networks (ANN) is one of machine learning which proved able to complete inference tasks such as prediction and classification especially in data mining. In this paper, we propose the implementation of Jordan Recurrent Neural Networks (JRNN) to classify and predict corporate bankruptcy based on financial ratios. Feedback interconnection in JRNN enable to make the network keep important information well allowing the network to work more effectively. The result analysis showed that JRNN works very well in bankruptcy prediction with average success rate of 81.3785%.

Drive Control Scheme of Electric Power Assisted Wheelchair Based on Neural Network Learning of Human Wheelchair Operation Characteristics

NASA Astrophysics Data System (ADS)

Tanohata, Naoki; Seki, Hirokazu

This paper describes a novel drive control scheme of electric power assisted wheelchairs based on neural network learning of human wheelchair operation characteristics. “Electric power assisted wheelchair” which enhances the drive force of the operator by employing electric motors is expected to be widely used as a mobility support system for elderly and disabled people. However, some handicapped people with paralysis of the muscles of one side of the body cannot maneuver the wheelchair as desired because of the difference in the right and left input force. Therefore, this study proposes a neural network learning system of such human wheelchair operation characteristics and a drive control scheme with variable distribution and assistance ratios. Some driving experiments will be performed to confirm the effectiveness of the proposed control system.

Smoothing of cost function leads to faster convergence of neural network learning

NASA Astrophysics Data System (ADS)

Xu, Li-Qun; Hall, Trevor J.

1994-03-01

One of the major problems in supervised learning of neural networks is the inevitable local minima inherent in the cost function f(W,D). This often makes classic gradient-descent-based learning algorithms that calculate the weight updates for each iteration according to (Delta) W(t) equals -(eta) (DOT)$DELwf(W,D) powerless. In this paper we describe a new strategy to solve this problem, which, adaptively, changes the learning rate and manipulates the gradient estimator simultaneously. The idea is to implicitly convert the local- minima-laden cost function f((DOT)) into a sequence of its smoothed versions {f(beta t)}Ttequals1, which, subject to the parameter (beta) t, bears less details at time t equals 1 and gradually more later on, the learning is actually performed on this sequence of functionals. The corresponding smoothed global minima obtained in this way, {Wt}Ttequals1, thus progressively approximate W-the desired global minimum. Experimental results on a nonconvex function minimization problem and a typical neural network learning task are given, analyses and discussions of some important issues are provided.

Hexacopter trajectory control using a neural network

NASA Astrophysics Data System (ADS)

Artale, V.; Collotta, M.; Pau, G.; Ricciardello, A.

2013-10-01

The modern flight control systems are complex due to their non-linear nature. In fact, modern aerospace vehicles are expected to have non-conventional flight envelopes and, then, they must guarantee a high level of robustness and adaptability in order to operate in uncertain environments. Neural Networks (NN), with real-time learning capability, for flight control can be used in applications with manned or unmanned aerial vehicles. Indeed, using proven lower level control algorithms with adaptive elements that exhibit long term learning could help in achieving better adaptation performance while performing aggressive maneuvers. In this paper we show a mathematical modeling and a Neural Network for a hexacopter dynamics in order to develop proper methods for stabilization and trajectory control.

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction

DOE Office of Scientific and Technical Information (OSTI.GOV)

Goh, Garrett B.; Siegel, Charles M.; Vishnu, Abhinav

With access to large datasets, deep neural networks through representation learning have been able to identify patterns from raw data, achieving human-level accuracy in image and speech recognition tasks. However, in chemistry, availability of large standardized and labelled datasets is scarce, and with a multitude of chemical properties of interest, chemical data is inherently small and fragmented. In this work, we explore transfer learning techniques in conjunction with the existing Chemception CNN model, to create a transferable and generalizable deep neural network for small-molecule property prediction. Our latest model, ChemNet learns in a semi-supervised manner from inexpensive labels computed frommore » the ChEMBL database. When fine-tuned to the Tox21, HIV and FreeSolv dataset, which are 3 separate chemical tasks that ChemNet was not originally trained on, we demonstrate that ChemNet exceeds the performance of existing Chemception models, contemporary MLP models that trains on molecular fingerprints, and it matches the performance of the ConvGraph algorithm, the current state-of-the-art. Furthermore, as ChemNet has been pre-trained on a large diverse chemical database, it can be used as a universal “plug-and-play” deep neural network, which accelerates the deployment of deep neural networks for the prediction of novel small-molecule chemical properties.« less

Forecasting influenza-like illness dynamics for military populations using neural networks and social media

DOE PAGES

Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; ...

2017-12-15

This work is the first to take advantage of recurrent neural networks to predict influenza-like-illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data [1, 2] and the state-of-the-art machine learning models [3, 4], we build and evaluate the predictive power of Long Short Term Memory (LSTMs) architectures capable of nowcasting (predicting in \\real-time") and forecasting (predicting the future) ILI dynamics in the 2011 { 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, stylistic and syntactic patterns,more » emotions and opinions, and communication behavior. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks. Finally, we combine ILI and social media signals to build joint neural network models for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance [1], specifically for military rather than general populations [3] in 26 U.S. and six international locations. Our approach demonstrates several advantages: (a) Neural network models learned from social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than syntactic and stylistic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns.« less

Forecasting influenza-like illness dynamics for military populations using neural networks and social media

DOE Office of Scientific and Technical Information (OSTI.GOV)

Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine

This work is the first to take advantage of recurrent neural networks to predict influenza-like-illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data [1, 2] and the state-of-the-art machine learning models [3, 4], we build and evaluate the predictive power of Long Short Term Memory (LSTMs) architectures capable of nowcasting (predicting in \\real-time") and forecasting (predicting the future) ILI dynamics in the 2011 { 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, stylistic and syntactic patterns,more » emotions and opinions, and communication behavior. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks. Finally, we combine ILI and social media signals to build joint neural network models for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance [1], specifically for military rather than general populations [3] in 26 U.S. and six international locations. Our approach demonstrates several advantages: (a) Neural network models learned from social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than syntactic and stylistic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns.« less

Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.

Reconstruction of three-dimensional porous media using generative adversarial neural networks

NASA Astrophysics Data System (ADS)

Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J.

2017-10-01

To evaluate the variability of multiphase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image data sets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics, and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that generative adversarial networks can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

PubMed

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p < 0.001). The results demonstrate that transfer learning with convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

Stable architectures for deep neural networks

NASA Astrophysics Data System (ADS)

Haber, Eldad; Ruthotto, Lars

2018-01-01

Deep neural networks have become invaluable tools for supervised machine learning, e.g. classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in data, deep architectures are known to be challenging to design and train such that they generalize well to new data. Critical issues with deep architectures are numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients. In this paper, we propose new forward propagation techniques inspired by systems of ordinary differential equations (ODE) that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks. The backbone of our approach is our interpretation of deep learning as a parameter estimation problem of nonlinear dynamical systems. Given this formulation, we analyze stability and well-posedness of deep learning and use this new understanding to develop new network architectures. We relate the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and present several strategies for stabilizing deep learning for very deep networks. While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.

Using neural networks in software repositories

NASA Technical Reports Server (NTRS)

Eichmann, David (Editor); Srinivas, Kankanahalli; Boetticher, G.

1992-01-01

The first topic is an exploration of the use of neural network techniques to improve the effectiveness of retrieval in software repositories. The second topic relates to a series of experiments conducted to evaluate the feasibility of using adaptive neural networks as a means of deriving (or more specifically, learning) measures on software. Taken together, these two efforts illuminate a very promising mechanism supporting software infrastructures - one based upon a flexible and responsive technology.

Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware

PubMed Central

Knight, James C.; Tully, Philip J.; Kaplan, Bernhard A.; Lansner, Anders; Furber, Steve B.

2016-01-01

SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 2.0 × 104 neurons and 5.1 × 107 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately 45× more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models. PMID:27092061

Overview of artificial neural networks.

PubMed

Zou, Jinming; Han, Yi; So, Sung-Sau

2008-01-01

The artificial neural network (ANN), or simply neural network, is a machine learning method evolved from the idea of simulating the human brain. The data explosion in modem drug discovery research requires sophisticated analysis methods to uncover the hidden causal relationships between single or multiple responses and a large set of properties. The ANN is one of many versatile tools to meet the demand in drug discovery modeling. Compared to a traditional regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN also has excellent fault tolerance and is fast and highly scalable with parallel processing. This chapter introduces the background of ANN development and outlines the basic concepts crucially important for understanding more sophisticated ANN. Several commonly used learning methods and network setups are discussed briefly at the end of the chapter.

Noise-Driven Manifestation of Learning in Mature Neural Networks

NASA Astrophysics Data System (ADS)

Monterola, Christopher; Saloma, Caesar

2002-10-01

We show that the generalization capability of a mature thresholding neural network to process above-threshold disturbances in a noise-free environment is extended to subthreshold disturbances by ambient noise without retraining. The ability to benefit from noise is intrinsic and does not have to be learned separately. Nonlinear dependence of sensitivity with noise strength is significantly narrower than in individual threshold systems. Noise has a minimal effect on network performance for above-threshold signals. We resolve two seemingly contradictory responses of trained networks to noise-their ability to benefit from its presence and their robustness against noisy strong disturbances.

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

PubMed

Schwaibold, M; Schöchlin, J; Bolz, A

2002-01-01

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

LVQ and backpropagation neural networks applied to NASA SSME data

NASA Technical Reports Server (NTRS)

Doniere, Timothy F.; Dhawan, Atam P.

1993-01-01

Feedfoward neural networks with backpropagation learning have been used as function approximators for modeling the space shuttle main engine (SSME) sensor signals. The modeling of these sensor signals is aimed at the development of a sensor fault detection system that can be used during ground test firings. The generalization capability of a neural network based function approximator depends on the training vectors which in this application may be derived from a number of SSME ground test-firings. This yields a large number of training vectors. Large training sets can cause the time required to train the network to be very large. Also, the network may not be able to generalize for large training sets. To reduce the size of the training sets, the SSME test-firing data is reduced using the learning vector quantization (LVQ) based technique. Different compression ratios were used to obtain compressed data in training the neural network model. The performance of the neural model trained using reduced sets of training patterns is presented and compared with the performance of the model trained using complete data. The LVQ can also be used as a function approximator. The performance of the LVQ as a function approximator using reduced training sets is presented and compared with the performance of the backpropagation network.

A network model of behavioural performance in a rule learning task.

PubMed

Hasselmo, Michael E; Stern, Chantal E

2018-04-19

Humans demonstrate differences in performance on cognitive rule learning tasks which could involve differences in properties of neural circuits. An example model is presented to show how gating of the spread of neural activity could underlie rule learning and the generalization of rules to previously unseen stimuli. This model uses the activity of gating units to regulate the pattern of connectivity between neurons responding to sensory input and subsequent gating units or output units. This model allows analysis of network parameters that could contribute to differences in cognitive rule learning. These network parameters include differences in the parameters of synaptic modification and presynaptic inhibition of synaptic transmission that could be regulated by neuromodulatory influences on neural circuits. Neuromodulatory receptors play an important role in cognitive function, as demonstrated by the fact that drugs that block cholinergic muscarinic receptors can cause cognitive impairments. In discussions of the links between neuromodulatory systems and biologically based traits, the issue of mechanisms through which these linkages are realized is often missing. This model demonstrates potential roles of neural circuit parameters regulated by acetylcholine in learning context-dependent rules, and demonstrates the potential contribution of variation in neural circuit properties and neuromodulatory function to individual differences in cognitive function.This article is part of the theme issue 'Diverse perspectives on diversity: multi-disciplinary approaches to taxonomies of individual differences'. © 2018 The Author(s).

Structural reliability calculation method based on the dual neural network and direct integration method.

PubMed

Li, Haibin; He, Yun; Nie, Xiaobo

2018-01-01

Structural reliability analysis under uncertainty is paid wide attention by engineers and scholars due to reflecting the structural characteristics and the bearing actual situation. The direct integration method, started from the definition of reliability theory, is easy to be understood, but there are still mathematics difficulties in the calculation of multiple integrals. Therefore, a dual neural network method is proposed for calculating multiple integrals in this paper. Dual neural network consists of two neural networks. The neural network A is used to learn the integrand function, and the neural network B is used to simulate the original function. According to the derivative relationships between the network output and the network input, the neural network B is derived from the neural network A. On this basis, the performance function of normalization is employed in the proposed method to overcome the difficulty of multiple integrations and to improve the accuracy for reliability calculations. The comparisons between the proposed method and Monte Carlo simulation method, Hasofer-Lind method, the mean value first-order second moment method have demonstrated that the proposed method is an efficient and accurate reliability method for structural reliability problems.

Learning and retrieval behavior in recurrent neural networks with pre-synaptic dependent homeostatic plasticity

NASA Astrophysics Data System (ADS)

Mizusaki, Beatriz E. P.; Agnes, Everton J.; Erichsen, Rubem; Brunnet, Leonardo G.

2017-08-01

The plastic character of brain synapses is considered to be one of the foundations for the formation of memories. There are numerous kinds of such phenomenon currently described in the literature, but their role in the development of information pathways in neural networks with recurrent architectures is still not completely clear. In this paper we study the role of an activity-based process, called pre-synaptic dependent homeostatic scaling, in the organization of networks that yield precise-timed spiking patterns. It encodes spatio-temporal information in the synaptic weights as it associates a learned input with a specific response. We introduce a correlation measure to evaluate the precision of the spiking patterns and explore the effects of different inhibitory interactions and learning parameters. We find that large learning periods are important in order to improve the network learning capacity and discuss this ability in the presence of distinct inhibitory currents.

Learning and optimization with cascaded VLSI neural network building-block chips

NASA Technical Reports Server (NTRS)

Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

1992-01-01

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

DOE PAGES

Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

2016-10-18

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

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

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

Supervised Learning Using Spike-Timing-Dependent Plasticity of Memristive Synapses.

PubMed

Nishitani, Yu; Kaneko, Yukihiro; Ueda, Michihito

2015-12-01

We propose a supervised learning model that enables error backpropagation for spiking neural network hardware. The method is modeled by modifying an existing model to suit the hardware implementation. An example of a network circuit for the model is also presented. In this circuit, a three-terminal ferroelectric memristor (3T-FeMEM), which is a field-effect transistor with a gate insulator composed of ferroelectric materials, is used as an electric synapse device to store the analog synaptic weight. Our model can be implemented by reflecting the network error to the write voltage of the 3T-FeMEMs and introducing a spike-timing-dependent learning function to the device. An XOR problem was successfully demonstrated as a benchmark learning by numerical simulations using the circuit properties to estimate the learning performance. In principle, the learning time per step of this supervised learning model and the circuit is independent of the number of neurons in each layer, promising a high-speed and low-power calculation in large-scale neural networks.

Comparative Studies of Prediction Strategies for Solar X-ray Time Series

NASA Astrophysics Data System (ADS)

Muranushi, T.; Hattori, T.; Jin, Q.; Hishinuma, T.; Tominaga, M.; Nakagawa, K.; Fujiwara, Y.; Nakamura, T.; Sakaue, T.; Takahashi, T.; Seki, D.; Namekata, K.; Tei, A.; Ban, M.; Kawamura, A. D.; Hada-Muranushi, Y.; Asai, A.; Nemoto, S.; Shibata, K.

2016-12-01

Crucial virtues for operational space weather forecast are real-timeforecast ability, forecast precision and customizability to userneeds. The recent development of deep-learning makes it veryattractive to space weather, because (1) it learns gradually incomingdata, (2) it exhibits superior accuracy over conventional algorithmsin many fields, and (3) it makes the customization of the forecasteasier because it accepts raw images.However, the best deep-learning applications are only attainable bycareful human designers that understands both the mechanism of deeplearning and the application field. Therefore, we need to foster youngresearchers to enter the field of machine-learning aided forecast. So,we have held a seminar every Monday with undergraduate and graduatestudents from May to August 2016.We will review the current status of space weather science and theautomated real-time space weather forecast engine UFCORIN. Then, weintroduce the deep-learning space weather forecast environments wehave set up using Python and Chainer on students' laptop computers.We have started from simple image classification neural network, thenimplemented space-weather neural network that predicts future X-rayflux of the Sun based on the past X-ray lightcurve and magnetic fieldline-of-sight images.In order to perform each forecast faster, we have focused on simplelightcurve-to-lightcurve forecast, and performed comparative surveysby changing following parameters: The size and topology of the neural network Batchsize Neural network hyperparameters such as learning rates to optimize the preduction accuracy, and time for prediction.We have found how to design compact, fast but accurate neural networkto perform forecast. Our forecasters can perform predictionexperiment for four-year timespan in a few minutes, and achieveslog-scale errors of the order of 1. Our studies is ongoing, and inour talk we will review our progress till December.

On the sample complexity of learning for networks of spiking neurons with nonlinear synaptic interactions.

PubMed

Schmitt, Michael

2004-09-01

We study networks of spiking neurons that use the timing of pulses to encode information. Nonlinear interactions model the spatial groupings of synapses on the neural dendrites and describe the computations performed at local branches. Within a theoretical framework of learning we analyze the question of how many training examples these networks must receive to be able to generalize well. Bounds for this sample complexity of learning can be obtained in terms of a combinatorial parameter known as the pseudodimension. This dimension characterizes the computational richness of a neural network and is given in terms of the number of network parameters. Two types of feedforward architectures are considered: constant-depth networks and networks of unconstrained depth. We derive asymptotically tight bounds for each of these network types. Constant depth networks are shown to have an almost linear pseudodimension, whereas the pseudodimension of general networks is quadratic. Networks of spiking neurons that use temporal coding are becoming increasingly more important in practical tasks such as computer vision, speech recognition, and motor control. The question of how well these networks generalize from a given set of training examples is a central issue for their successful application as adaptive systems. The results show that, although coding and computation in these networks is quite different and in many cases more powerful, their generalization capabilities are at least as good as those of traditional neural network models.

Fault-tolerant nonlinear adaptive flight control using sliding mode online learning.

PubMed

Krüger, Thomas; Schnetter, Philipp; Placzek, Robin; Vörsmann, Peter

2012-08-01

An expanded nonlinear model inversion flight control strategy using sliding mode online learning for neural networks is presented. The proposed control strategy is implemented for a small unmanned aircraft system (UAS). This class of aircraft is very susceptible towards nonlinearities like atmospheric turbulence, model uncertainties and of course system failures. Therefore, these systems mark a sensible testbed to evaluate fault-tolerant, adaptive flight control strategies. Within this work the concept of feedback linearization is combined with feed forward neural networks to compensate for inversion errors and other nonlinear effects. Backpropagation-based adaption laws of the network weights are used for online training. Within these adaption laws the standard gradient descent backpropagation algorithm is augmented with the concept of sliding mode control (SMC). Implemented as a learning algorithm, this nonlinear control strategy treats the neural network as a controlled system and allows a stable, dynamic calculation of the learning rates. While considering the system's stability, this robust online learning method therefore offers a higher speed of convergence, especially in the presence of external disturbances. The SMC-based flight controller is tested and compared with the standard gradient descent backpropagation algorithm in the presence of system failures. Copyright © 2012 Elsevier Ltd. All rights reserved.

Decoding of finger trajectory from ECoG using deep learning.

PubMed

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

Decoding of finger trajectory from ECoG using deep learning

NASA Astrophysics Data System (ADS)

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Objective. Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. Approach. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. Main results. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. Significance. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

Face recognition via Gabor and convolutional neural network

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wu, Menglu; Lu, Tao

2018-04-01

In recent years, the powerful feature learning and classification ability of convolutional neural network have attracted widely attention. Compared with the deep learning, the traditional machine learning algorithm has a good explanatory which deep learning does not have. Thus, In this paper, we propose a method to extract the feature of the traditional algorithm as the input of convolution neural network. In order to reduce the complexity of the network, the kernel function of Gabor wavelet is used to extract the feature from different position, frequency and direction of target image. It is sensitive to edge of image which can provide good direction and scale selection. The extraction of the image from eight directions on a scale are as the input of network that we proposed. The network have the advantage of weight sharing and local connection and texture feature of the input image can reduce the influence of facial expression, gesture and illumination. At the same time, we introduced a layer which combined the results of the pooling and convolution can extract deeper features. The training network used the open source caffe framework which is beneficial to feature extraction. The experiment results of the proposed method proved that the network structure effectively overcame the barrier of illumination and had a good robustness as well as more accurate and rapid than the traditional algorithm.

Artificial neural networks and approximate reasoning for intelligent control in space

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

A method is introduced for learning to refine the control rules of approximate reasoning-based controllers. A reinforcement-learning technique is used in conjunction with a multi-layer neural network model of an approximate reasoning-based controller. The model learns by updating its prediction of the physical system's behavior. The model can use the control knowledge of an experienced operator and fine-tune it through the process of learning. Some of the space domains suitable for applications of the model such as rendezvous and docking, camera tracking, and tethered systems control are discussed.

Comparison of artificial intelligence classifiers for SIP attack data

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2016-05-01

Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.

A model of human motor sequence learning explains facilitation and interference effects based on spike-timing dependent plasticity.

PubMed

Wang, Quan; Rothkopf, Constantin A; Triesch, Jochen

2017-08-01

The ability to learn sequential behaviors is a fundamental property of our brains. Yet a long stream of studies including recent experiments investigating motor sequence learning in adult human subjects have produced a number of puzzling and seemingly contradictory results. In particular, when subjects have to learn multiple action sequences, learning is sometimes impaired by proactive and retroactive interference effects. In other situations, however, learning is accelerated as reflected in facilitation and transfer effects. At present it is unclear what the underlying neural mechanism are that give rise to these diverse findings. Here we show that a recently developed recurrent neural network model readily reproduces this diverse set of findings. The self-organizing recurrent neural network (SORN) model is a network of recurrently connected threshold units that combines a simplified form of spike-timing dependent plasticity (STDP) with homeostatic plasticity mechanisms ensuring network stability, namely intrinsic plasticity (IP) and synaptic normalization (SN). When trained on sequence learning tasks modeled after recent experiments we find that it reproduces the full range of interference, facilitation, and transfer effects. We show how these effects are rooted in the network's changing internal representation of the different sequences across learning and how they depend on an interaction of training schedule and task similarity. Furthermore, since learning in the model is based on fundamental neuronal plasticity mechanisms, the model reveals how these plasticity mechanisms are ultimately responsible for the network's sequence learning abilities. In particular, we find that all three plasticity mechanisms are essential for the network to learn effective internal models of the different training sequences. This ability to form effective internal models is also the basis for the observed interference and facilitation effects. This suggests that STDP, IP, and SN may be the driving forces behind our ability to learn complex action sequences.

Pruning artificial neural networks using neural complexity measures.

PubMed

Jorgensen, Thomas D; Haynes, Barry P; Norlund, Charlotte C F

2008-10-01

This paper describes a new method for pruning artificial neural networks, using a measure of the neural complexity of the neural network. This measure is used to determine the connections that should be pruned. The measure computes the information-theoretic complexity of a neural network, which is similar to, yet different from previous research on pruning. The method proposed here shows how overly large and complex networks can be reduced in size, whilst retaining learnt behaviour and fitness. The technique proposed here helps to discover a network topology that matches the complexity of the problem it is meant to solve. This novel pruning technique is tested in a robot control domain, simulating a racecar. It is shown, that the proposed pruning method is a significant improvement over the most commonly used pruning method Magnitude Based Pruning. Furthermore, some of the pruned networks prove to be faster learners than the benchmark network that they originate from. This means that this pruning method can also help to unleash hidden potential in a network, because the learning time decreases substantially for a pruned a network, due to the reduction of dimensionality of the network.

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

PubMed

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

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

Artificial Neural Networks for Modeling Knowing and Learning in Science.

ERIC Educational Resources Information Center

Roth, Wolff-Michael

2000-01-01

Advocates artificial neural networks as models for cognition and development. Provides an example of how such models work in the context of a well-known Piagetian developmental task and school science activity: balance beam problems. (Contains 59 references.) (Author/WRM)

Auto-programmable impulse neural circuits

NASA Technical Reports Server (NTRS)

Watula, D.; Meador, J.

1990-01-01

Impulse neural networks use pulse trains to communicate neuron activation levels. Impulse neural circuits emulate natural neurons at a more detailed level than that typically employed by contemporary neural network implementation methods. An impulse neural circuit which realizes short term memory dynamics is presented. The operation of that circuit is then characterized in terms of pulse frequency modulated signals. Both fixed and programmable synapse circuits for realizing long term memory are also described. The implementation of a simple and useful unsupervised learning law is then presented. The implementation of a differential Hebbian learning rule for a specific mean-frequency signal interpretation is shown to have a straightforward implementation using digital combinational logic with a variation of a previously developed programmable synapse circuit. This circuit is expected to be exploited for simple and straightforward implementation of future auto-adaptive neural circuits.

Synthesizing animal and human behavior research via neural network learning theory.

PubMed

Tryon, W W

1995-12-01

Animal and human research have been "divorced" since approximately 1968. Several recent articles have tried to persuade behavior therapists of the merits of animal research. Three reasons are given concerning why disinterest in animal research is so widespread: (1) functional explanations are given for animals, and cognitive explanations are given for humans; (2) serial symbol manipulating models are used to explain human behavior; and (3) human learning was assumed, thereby removing it as something to be explained. Brain-inspired connectionist neural networks, collectively referred to as neural network learning theory (NNLT), are briefly described, and a spectrum of their accomplishments from simple conditioning through speech is outlined. Five benefits that behavior therapists can derive from NNLT are described. They include (a) enhanced professional identity derived from a comprehensive learning theory, (b) improved interdisciplinary collaboration both clinically and scientifically, (c) renewed perceived relevance of animal research, (d) access to plausible proximal causal mechanisms capable of explaining operant conditioning, and (e) an inherently developmental perspective.

A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

PubMed Central

Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.

2016-01-01

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566

Neural Models of Spatial Orientation in Novel Environments

DTIC Science & Technology

1994-01-01

tool use, the problem of self-organizing body -centered spatial representations for movement planning and spatial orientation, and the problem of...meeting of the American Association for the Advancement of Science, Boston, February, 1993. 23. Grossberg, S., annual Linnaeus Lecture, Uppsala...Congress on Neural Networks entitled --A self-organizing neural network for learning a body -centered invariant representa- tion of 3-D target

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

NASA Astrophysics Data System (ADS)

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

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

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

NASA Astrophysics Data System (ADS)

Lähivaara, Timo; Kärkkäinen, Leo; Huttunen, Janne M. J.; Hesthaven, Jan S.

2018-02-01

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelastic-acoustic media. As the forward model, we consider a high-order discontinuous Galerkin method while deep convolutional neural networks are used to solve the parameter estimation problem. In the numerical experiment, we estimate the material porosity and tortuosity while the remaining parameters which are of less interest are successfully marginalized in the neural networks-based inversion. Computational examples confirms the feasibility and accuracy of this approach.

Prediction of welding shrinkage deformation of bridge steel box girder based on wavelet neural network

NASA Astrophysics Data System (ADS)

Tao, Yulong; Miao, Yunshui; Han, Jiaqi; Yan, Feiyun

2018-05-01

Aiming at the low accuracy of traditional forecasting methods such as linear regression method, this paper presents a prediction method for predicting the relationship between bridge steel box girder and its displacement with wavelet neural network. Compared with traditional forecasting methods, this scheme has better local characteristics and learning ability, which greatly improves the prediction ability of deformation. Through analysis of the instance and found that after compared with the traditional prediction method based on wavelet neural network, the rigid beam deformation prediction accuracy is higher, and is superior to the BP neural network prediction results, conform to the actual demand of engineering design.

Application of artificial neural network for heat transfer in porous cone

NASA Astrophysics Data System (ADS)

Athani, Abdulgaphur; Ahamad, N. Ameer; Badruddin, Irfan Anjum

2018-05-01

Heat transfer in porous medium is one of the classical areas of research that has been active for many decades. The heat transfer in porous medium is generally studied by using numerical methods such as finite element method; finite difference method etc. that solves coupled partial differential equations by converting them into simpler forms. The current work utilizes an alternate method known as artificial neural network that mimics the learning characteristics of neurons. The heat transfer in porous medium fixed in a cone is predicted using backpropagation neural network. The artificial neural network is able to predict this behavior quite accurately.

Optimal mapping of neural-network learning on message-passing multicomputers

NASA Technical Reports Server (NTRS)

Chu, Lon-Chan; Wah, Benjamin W.

1992-01-01

A minimization of learning-algorithm completion time is sought in the present optimal-mapping study of the learning process in multilayer feed-forward artificial neural networks (ANNs) for message-passing multicomputers. A novel approximation algorithm for mappings of this kind is derived from observations of the dominance of a parallel ANN algorithm over its communication time. Attention is given to both static and dynamic mapping schemes for systems with static and dynamic background workloads, as well as to experimental results obtained for simulated mappings on multicomputers with dynamic background workloads.

Fault detection and diagnosis using neural network approaches

NASA Technical Reports Server (NTRS)

Kramer, Mark A.

1992-01-01

Neural networks can be used to detect and identify abnormalities in real-time process data. Two basic approaches can be used, the first based on training networks using data representing both normal and abnormal modes of process behavior, and the second based on statistical characterization of the normal mode only. Given data representative of process faults, radial basis function networks can effectively identify failures. This approach is often limited by the lack of fault data, but can be facilitated by process simulation. The second approach employs elliptical and radial basis function neural networks and other models to learn the statistical distributions of process observables under normal conditions. Analytical models of failure modes can then be applied in combination with the neural network models to identify faults. Special methods can be applied to compensate for sensor failures, to produce real-time estimation of missing or failed sensors based on the correlations codified in the neural network.

Brain-Inspired Constructive Learning Algorithms with Evolutionally Additive Nonlinear Neurons

NASA Astrophysics Data System (ADS)

Fang, Le-Heng; Lin, Wei; Luo, Qiang

In this article, inspired partially by the physiological evidence of brain’s growth and development, we developed a new type of constructive learning algorithm with evolutionally additive nonlinear neurons. The new algorithms have remarkable ability in effective regression and accurate classification. In particular, the algorithms are able to sustain a certain reduction of the loss function when the dynamics of the trained network are bogged down in the vicinity of the local minima. The algorithm augments the neural network by adding only a few connections as well as neurons whose activation functions are nonlinear, nonmonotonic, and self-adapted to the dynamics of the loss functions. Indeed, we analytically demonstrate the reduction dynamics of the algorithm for different problems, and further modify the algorithms so as to obtain an improved generalization capability for the augmented neural networks. Finally, through comparing with the classical algorithm and architecture for neural network construction, we show that our constructive learning algorithms as well as their modified versions have better performances, such as faster training speed and smaller network size, on several representative benchmark datasets including the MNIST dataset for handwriting digits.

Analog Delta-Back-Propagation Neural-Network Circuitry

NASA Technical Reports Server (NTRS)

Eberhart, Silvio

1990-01-01

Changes in synapse weights due to circuit drifts suppressed. Proposed fully parallel analog version of electronic neural-network processor based on delta-back-propagation algorithm. Processor able to "learn" when provided with suitable combinations of inputs and enforced outputs. Includes programmable resistive memory elements (corresponding to synapses), conductances (synapse weights) adjusted during learning. Buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in layers of electronic neurons in accordance with delta-back-propagation algorithm.

Two Stage Data Augmentation for Low Resourced Speech Recognition (Author’s Manuscript)

DTIC Science & Technology

2016-09-12

speech recognition, deep neural networks, data augmentation 1. Introduction When training data is limited—whether it be audio or text—the obvious...Schwartz, and S. Tsakalidis, “Enhancing low resource keyword spotting with au- tomatically retrieved web documents,” in Interspeech, 2015, pp. 839–843. [2...and F. Seide, “Feature learning in deep neural networks - a study on speech recognition tasks,” in International Conference on Learning Representations

Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

PubMed

Li, Siqi; Jiang, Huiyan; Pang, Wenbo

2017-05-01

Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

A new optimized GA-RBF neural network algorithm.

PubMed

Jia, Weikuan; Zhao, Dean; Shen, Tian; Su, Chunyang; Hu, Chanli; Zhao, Yuyan

2014-01-01

When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer's neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.

Genetic attack on neural cryptography.

PubMed

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka; Kanter, Ido

2006-03-01

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold for the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Oxytocin and vasopressin neural networks: implications for social behavioral diversity and translational neuroscience

PubMed Central

Johnson, Zachary V.; Young, Larry J.

2017-01-01

Oxytocin- and vasopressin-related systems are present in invertebrate and vertebrate bilaterian animals, including humans, and exhibit conserved neuroanatomical and functional properties. In vertebrates, these systems innervate conserved neural networks that regulate social learning and behavior, including conspecific recognition, social attachment, and parental behavior. Individual and species-level variation in central organization of oxytocin and vasopressin systems has been linked to individual and species variation in social learning and behavior. In humans, genetic polymorphisms in the genes encoding oxytocin and vasopressin peptides and/or their respective target receptors have been associated with individual variation in social recognition, social attachment phenotypes, parental behavior, and psychiatric phenotypes such as autism. Here we describe both conserved and variable features of central oxytocin and vasopressin systems in the context of social behavioral diversity, with a particular focus on neural networks that modulate social learning, behavior, and salience of sociosensory stimuli during species-typical social contexts. PMID:28434591

Segmented-memory recurrent neural networks.

PubMed

Chen, Jinmiao; Chaudhari, Narendra S

2009-08-01

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.

Perception as a Route for Motor Skill Learning: Perspectives from Neuroscience.

PubMed

Ossmy, Ori; Mukamel, Roy

2018-04-22

Learning a motor skill requires physical practice that engages neural networks involved in movement. These networks have also been found to be engaged during perception of sensory signals associated with actions. Nonetheless, despite extensive evidence for the existence of such sensory-evoked neural activity in motor pathways, much less is known about their contribution to learning and actual changes in behavior. Primate studies usually involve an overlearned task while studies in humans have largely focused on characterizing activity of the action observation network (AON) in the context of action understanding, theory of mind, and social interactions. Relatively few studies examined neural plasticity induced by perception and its role in transfer of motor knowledge. Here, we review this body of literature and point to future directions for the development of alternative, physiologically grounded ways in which sensory signals could be harnessed to improve motor skills. Copyright © 2018. Published by Elsevier Ltd.

Genetic attack on neural cryptography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka

2006-03-15

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold formore » the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.« less

Genetic attack on neural cryptography

NASA Astrophysics Data System (ADS)

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka; Kanter, Ido

2006-03-01

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold for the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.

Neural Detection of Malicious Network Activities Using a New Direct Parsing and Feature Extraction Technique

DTIC Science & Technology

2015-09-01

intrusion detection systems , neural networks 15. NUMBER OF PAGES 75 16. PRICE CODE 17. SECURITY CLASSIFICATION OF... detection system (IDS) software, which learns to detect and classify network attacks and intrusions through prior training data. With the added criteria of...BACKGROUND The growing threat of malicious network activities and intrusion attempts makes intrusion detection systems (IDS) a

Neural network simulation of the atmospheric point spread function for the adjacency effect research

NASA Astrophysics Data System (ADS)

Ma, Xiaoshan; Wang, Haidong; Li, Ligang; Yang, Zhen; Meng, Xin

2016-10-01

Adjacency effect could be regarded as the convolution of the atmospheric point spread function (PSF) and the surface leaving radiance. Monte Carlo is a common method to simulate the atmospheric PSF. But it can't obtain analytic expression and the meaningful results can be only acquired by statistical analysis of millions of data. A backward Monte Carlo algorithm was employed to simulate photon emitting and propagating in the atmosphere under different conditions. The PSF was determined by recording the photon-receiving numbers in fixed bin at different position. A multilayer feed-forward neural network with a single hidden layer was designed to learn the relationship between the PSF's and the input condition parameters. The neural network used the back-propagation learning rule for training. Its input parameters involved atmosphere condition, spectrum range, observing geometry. The outputs of the network were photon-receiving numbers in the corresponding bin. Because the output units were too many to be allowed by neural network, the large network was divided into a collection of smaller ones. These small networks could be ran simultaneously on many workstations and/or PCs to speed up the training. It is important to note that the simulated PSF's by Monte Carlo technique in non-nadir viewing angles are more complicated than that in nadir conditions which brings difficulties in the design of the neural network. The results obtained show that the neural network approach could be very useful to compute the atmospheric PSF based on the simulated data generated by Monte Carlo method.

Comment on 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study'.

PubMed

Valdes, Gilmer; Interian, Yannet

2018-03-15

The application of machine learning (ML) presents tremendous opportunities for the field of oncology, thus we read 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study' with great interest. In this article, the authors used state of the art techniques: a pre-trained convolutional neural network (VGG-16 CNN), transfer learning, data augmentation, drop out and early stopping, all of which are directly responsible for the success and the excitement that these algorithms have created in other fields. We believe that the use of these techniques can offer tremendous opportunities in the field of Medical Physics and as such we would like to praise the authors for their pioneering application to the field of Radiation Oncology. That being said, given that the field of Medical Physics has unique characteristics that differentiate us from those fields where these techniques have been applied successfully, we would like to raise some points for future discussion and follow up studies that could help the community understand the limitations and nuances of deep learning techniques.

Neural networks within multi-core optic fibers

PubMed Central

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-01-01

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks. PMID:27383911

Neural networks within multi-core optic fibers.

PubMed

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-07-07

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.

Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems

NASA Technical Reports Server (NTRS)

Innocenti, M.; Napolitano, M.

2003-01-01

Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.

On the Effectiveness of a Neural Network for Adaptive External Pacing.

ERIC Educational Resources Information Center

Montazemi, Ali R.; Wang, Feng

1995-01-01

Proposes a neural network model for an intelligent tutoring system featuring adaptive external control of student pacing. An experiment was conducted, and students using adaptive external pacing experienced improved mastery learning and increased motivation for time management. Contains 66 references. (JKP)

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines

PubMed Central

Neftci, Emre O.; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning. PMID:28680387

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines.

PubMed

Neftci, Emre O; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

Learning a trajectory using adjoint functions and teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad B.; Barhen, Jacob

1992-01-01

A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.

Human fatigue expression recognition through image-based dynamic multi-information and bimodal deep learning

NASA Astrophysics Data System (ADS)

Zhao, Lei; Wang, Zengcai; Wang, Xiaojin; Qi, Yazhou; Liu, Qing; Zhang, Guoxin

2016-09-01

Human fatigue is an important cause of traffic accidents. To improve the safety of transportation, we propose, in this paper, a framework for fatigue expression recognition using image-based facial dynamic multi-information and a bimodal deep neural network. First, the landmark of face region and the texture of eye region, which complement each other in fatigue expression recognition, are extracted from facial image sequences captured by a single camera. Then, two stacked autoencoder neural networks are trained for landmark and texture, respectively. Finally, the two trained neural networks are combined by learning a joint layer on top of them to construct a bimodal deep neural network. The model can be used to extract a unified representation that fuses landmark and texture modalities together and classify fatigue expressions accurately. The proposed system is tested on a human fatigue dataset obtained from an actual driving environment. The experimental results demonstrate that the proposed method performs stably and robustly, and that the average accuracy achieves 96.2%.

Functional model of biological neural networks.

PubMed

Lo, James Ting-Ho

2010-12-01

A functional model of biological neural networks, called temporal hierarchical probabilistic associative memory (THPAM), is proposed in this paper. THPAM comprises functional models of dendritic trees for encoding inputs to neurons, a first type of neuron for generating spike trains, a second type of neuron for generating graded signals to modulate neurons of the first type, supervised and unsupervised Hebbian learning mechanisms for easy learning and retrieving, an arrangement of dendritic trees for maximizing generalization, hardwiring for rotation-translation-scaling invariance, and feedback connections with different delay durations for neurons to make full use of present and past informations generated by neurons in the same and higher layers. These functional models and their processing operations have many functions of biological neural networks that have not been achieved by other models in the open literature and provide logically coherent answers to many long-standing neuroscientific questions. However, biological justifications of these functional models and their processing operations are required for THPAM to qualify as a macroscopic model (or low-order approximate) of biological neural networks.

Deterministic convergence of chaos injection-based gradient method for training feedforward neural networks.

PubMed

Zhang, Huisheng; Zhang, Ying; Xu, Dongpo; Liu, Xiaodong

2015-06-01

It has been shown that, by adding a chaotic sequence to the weight update during the training of neural networks, the chaos injection-based gradient method (CIBGM) is superior to the standard backpropagation algorithm. This paper presents the theoretical convergence analysis of CIBGM for training feedforward neural networks. We consider both the case of batch learning as well as the case of online learning. Under mild conditions, we prove the weak convergence, i.e., the training error tends to a constant and the gradient of the error function tends to zero. Moreover, the strong convergence of CIBGM is also obtained with the help of an extra condition. The theoretical results are substantiated by a simulation example.

Learning Data Set Influence on Identification Accuracy of Gas Turbine Neural Network Model

NASA Astrophysics Data System (ADS)

Kuznetsov, A. V.; Makaryants, G. M.

2018-01-01

There are many gas turbine engine identification researches via dynamic neural network models. It should minimize errors between model and real object during identification process. Questions about training data set processing of neural networks are usually missed. This article presents a study about influence of data set type on gas turbine neural network model accuracy. The identification object is thermodynamic model of micro gas turbine engine. The thermodynamic model input signal is the fuel consumption and output signal is the engine rotor rotation frequency. Four types input signals was used for creating training and testing data sets of dynamic neural network models - step, fast, slow and mixed. Four dynamic neural networks were created based on these types of training data sets. Each neural network was tested via four types test data sets. In the result 16 transition processes from four neural networks and four test data sets from analogous solving results of thermodynamic model were compared. The errors comparison was made between all neural network errors in each test data set. In the comparison result it was shown error value ranges of each test data set. It is shown that error values ranges is small therefore the influence of data set types on identification accuracy is low.

Neural networks for continuous online learning and control.

PubMed

Choy, Min Chee; Srinivasan, Dipti; Cheu, Ruey Long

2006-11-01

This paper proposes a new hybrid neural network (NN) model that employs a multistage online learning process to solve the distributed control problem with an infinite horizon. Various techniques such as reinforcement learning and evolutionary algorithm are used to design the multistage online learning process. For this paper, the infinite horizon distributed control problem is implemented in the form of real-time distributed traffic signal control for intersections in a large-scale traffic network. The hybrid neural network model is used to design each of the local traffic signal controllers at the respective intersections. As the state of the traffic network changes due to random fluctuation of traffic volumes, the NN-based local controllers will need to adapt to the changing dynamics in order to provide effective traffic signal control and to prevent the traffic network from becoming overcongested. Such a problem is especially challenging if the local controllers are used for an infinite horizon problem where online learning has to take place continuously once the controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District (CBD) of Singapore has been developed using PARAMICS microscopic simulation program. As the complexity of the simulation increases, results show that the hybrid NN model provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as a new, continuously updated simultaneous perturbation stochastic approximation-based neural network (SPSA-NN). Using the hybrid NN model, the total mean delay of each vehicle has been reduced by 78% and the total mean stoppage time of each vehicle has been reduced by 84% compared to the existing traffic signal control algorithm. This shows the efficacy of the hybrid NN model in solving large-scale traffic signal control problem in a distributed manner. Also, it indicates the possibility of using the hybrid NN model for other applications that are similar in nature as the infinite horizon distributed control problem.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-03-01

With the advancement of VLSI technology nodes, light diffraction caused lithographic hotspots have become a serious problem affecting manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with extreme scaling of transistor feature size and more and more complicated layout patterns, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. In this paper, we present a deep convolutional neural network (CNN) targeting representative feature learning in lithography hotspot detection. We carefully analyze impact and effectiveness of different CNN hyper-parameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always minorities in VLSI mask design, the training data set is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from high false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply minority upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves highly comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Overcoming catastrophic forgetting in neural networks

PubMed Central

Kirkpatrick, James; Pascanu, Razvan; Rabinowitz, Neil; Veness, Joel; Desjardins, Guillaume; Rusu, Andrei A.; Milan, Kieran; Quan, John; Ramalho, Tiago; Grabska-Barwinska, Agnieszka; Hassabis, Demis; Clopath, Claudia; Kumaran, Dharshan; Hadsell, Raia

2017-01-01

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks that they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on a hand-written digit dataset and by learning several Atari 2600 games sequentially. PMID:28292907

Indirect iterative learning control for a discrete visual servo without a camera-robot model.

PubMed

Jiang, Ping; Bamforth, Leon C A; Feng, Zuren; Baruch, John E F; Chen, YangQuan

2007-08-01

This paper presents a discrete learning controller for vision-guided robot trajectory imitation with no prior knowledge of the camera-robot model. A teacher demonstrates a desired movement in front of a camera, and then, the robot is tasked to replay it by repetitive tracking. The imitation procedure is considered as a discrete tracking control problem in the image plane, with an unknown and time-varying image Jacobian matrix. Instead of updating the control signal directly, as is usually done in iterative learning control (ILC), a series of neural networks are used to approximate the unknown Jacobian matrix around every sample point in the demonstrated trajectory, and the time-varying weights of local neural networks are identified through repetitive tracking, i.e., indirect ILC. This makes repetitive segmented training possible, and a segmented training strategy is presented to retain the training trajectories solely within the effective region for neural network approximation. However, a singularity problem may occur if an unmodified neural-network-based Jacobian estimation is used to calculate the robot end-effector velocity. A new weight modification algorithm is proposed which ensures invertibility of the estimation, thus circumventing the problem. Stability is further discussed, and the relationship between the approximation capability of the neural network and the tracking accuracy is obtained. Simulations and experiments are carried out to illustrate the validity of the proposed controller for trajectory imitation of robot manipulators with unknown time-varying Jacobian matrices.

Artificial intelligence: Neural network model as the multidisciplinary team member in clinical decision support to avoid medical mistakes.

PubMed

Buzaev, Igor Vyacheslavovich; Plechev, Vladimir Vyacheslavovich; Nikolaeva, Irina Evgenievna; Galimova, Rezida Maratovna

2016-09-01

The continuous uninterrupted feedback system is the essential part of any well-organized system. We propose aLYNX concept that is a possibility to use an artificial intelligence algorithm or a neural network model in decision-making system so as to avoid possible mistakes and to remind the doctors to review tactics once more in selected cases. aLYNX system includes: registry with significant factors, decisions and results; machine learning process based on this registry data; the use of the machine learning results as the adviser. We show a possibility to build a computer adviser with a neural network model for making a choice between coronary aortic bypass surgery (CABG) and percutaneous coronary intervention (PCI) in order to achieve a higher 5-year survival rate in patients with angina based on the experience of 5107 patients. The neural network was trained by 4679 patients who achieved 5-year survival. Among them, 2390 patients underwent PCI and 2289 CABG. After training, the correlation coefficient ( r ) of the network was 0.74 for training, 0.67 for validation, 0.71 for test and 0.73 for total. Simulation of the neural network function has been performed after training in the two groups of patients with known 5-year outcome. The disagreement rate was significantly higher in the dead patient group than that in the survivor group between neural network model and heart team [16.8% (787/4679) vs. 20.3% (87/428), P  = 0.065)]. The study shows the possibility to build a computer adviser with a neural network model for making a choice between CABG and PCI in order to achieve a higher 5-year survival rate in patients with angina.

Learning alters theta amplitude, theta-gamma coupling and neuronal synchronization in inferotemporal cortex.

PubMed

Kendrick, Keith M; Zhan, Yang; Fischer, Hanno; Nicol, Alister U; Zhang, Xuejuan; Feng, Jianfeng

2011-06-09

How oscillatory brain rhythms alone, or in combination, influence cortical information processing to support learning has yet to be fully established. Local field potential and multi-unit neuronal activity recordings were made from 64-electrode arrays in the inferotemporal cortex of conscious sheep during and after visual discrimination learning of face or object pairs. A neural network model has been developed to simulate and aid functional interpretation of learning-evoked changes. Following learning the amplitude of theta (4-8 Hz), but not gamma (30-70 Hz) oscillations was increased, as was the ratio of theta to gamma. Over 75% of electrodes showed significant coupling between theta phase and gamma amplitude (theta-nested gamma). The strength of this coupling was also increased following learning and this was not simply a consequence of increased theta amplitude. Actual discrimination performance was significantly correlated with theta and theta-gamma coupling changes. Neuronal activity was phase-locked with theta but learning had no effect on firing rates or the magnitude or latencies of visual evoked potentials during stimuli. The neural network model developed showed that a combination of fast and slow inhibitory interneurons could generate theta-nested gamma. By increasing N-methyl-D-aspartate receptor sensitivity in the model similar changes were produced as in inferotemporal cortex after learning. The model showed that these changes could potentiate the firing of downstream neurons by a temporal desynchronization of excitatory neuron output without increasing the firing frequencies of the latter. This desynchronization effect was confirmed in IT neuronal activity following learning and its magnitude was correlated with discrimination performance. Face discrimination learning produces significant increases in both theta amplitude and the strength of theta-gamma coupling in the inferotemporal cortex which are correlated with behavioral performance. A network model which can reproduce these changes suggests that a key function of such learning-evoked alterations in theta and theta-nested gamma activity may be increased temporal desynchronization in neuronal firing leading to optimal timing of inputs to downstream neural networks potentiating their responses. In this way learning can produce potentiation in neural networks simply through altering the temporal pattern of their inputs.

Learning alters theta amplitude, theta-gamma coupling and neuronal synchronization in inferotemporal cortex

PubMed Central

2011-01-01

Background How oscillatory brain rhythms alone, or in combination, influence cortical information processing to support learning has yet to be fully established. Local field potential and multi-unit neuronal activity recordings were made from 64-electrode arrays in the inferotemporal cortex of conscious sheep during and after visual discrimination learning of face or object pairs. A neural network model has been developed to simulate and aid functional interpretation of learning-evoked changes. Results Following learning the amplitude of theta (4-8 Hz), but not gamma (30-70 Hz) oscillations was increased, as was the ratio of theta to gamma. Over 75% of electrodes showed significant coupling between theta phase and gamma amplitude (theta-nested gamma). The strength of this coupling was also increased following learning and this was not simply a consequence of increased theta amplitude. Actual discrimination performance was significantly correlated with theta and theta-gamma coupling changes. Neuronal activity was phase-locked with theta but learning had no effect on firing rates or the magnitude or latencies of visual evoked potentials during stimuli. The neural network model developed showed that a combination of fast and slow inhibitory interneurons could generate theta-nested gamma. By increasing N-methyl-D-aspartate receptor sensitivity in the model similar changes were produced as in inferotemporal cortex after learning. The model showed that these changes could potentiate the firing of downstream neurons by a temporal desynchronization of excitatory neuron output without increasing the firing frequencies of the latter. This desynchronization effect was confirmed in IT neuronal activity following learning and its magnitude was correlated with discrimination performance. Conclusions Face discrimination learning produces significant increases in both theta amplitude and the strength of theta-gamma coupling in the inferotemporal cortex which are correlated with behavioral performance. A network model which can reproduce these changes suggests that a key function of such learning-evoked alterations in theta and theta-nested gamma activity may be increased temporal desynchronization in neuronal firing leading to optimal timing of inputs to downstream neural networks potentiating their responses. In this way learning can produce potentiation in neural networks simply through altering the temporal pattern of their inputs. PMID:21658251

Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland

NASA Astrophysics Data System (ADS)

Chattopadhyay, Surajit; Bandyopadhyay, Goutami

2007-01-01

Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.

Neurale Netwerken en Radarsystemen (Neural Networks and Radar Systems)

DTIC Science & Technology

1989-08-01

general issues in cognitive science", Parallel distributed processing, Vol 1: Foundations, Rumelhart et al. 1986 pp 110-146 THO rapport Pagina 151 36 D.E...34Neural networks (part 2)",Expert Focus, IEEE Expert, Spring 1988. 61 J.A. Anderson, " Cognitive and Psychological Computations with Neural Models", IEEE...Pagina 154 69 David H. Ackley, Geoffrey E. Hinton and Terrence J. Sejnowski, "A Learning Algorithm for Boltzmann machines", cognitive science 9, 147-169

Quantitative phase microscopy using deep neural networks

NASA Astrophysics Data System (ADS)

Li, Shuai; Sinha, Ayan; Lee, Justin; Barbastathis, George

2018-02-01

Deep learning has been proven to achieve ground-breaking accuracy in various tasks. In this paper, we implemented a deep neural network (DNN) to achieve phase retrieval in a wide-field microscope. Our DNN utilized the residual neural network (ResNet) architecture and was trained using the data generated by a phase SLM. The results showed that our DNN was able to reconstruct the profile of the phase target qualitatively. In the meantime, large error still existed, which indicated that our approach still need to be improved.

Artificial neural network in cosmic landscape

NASA Astrophysics Data System (ADS)

Liu, Junyu

2017-12-01

In this paper we propose that artificial neural network, the basis of machine learning, is useful to generate the inflationary landscape from a cosmological point of view. Traditional numerical simulations of a global cosmic landscape typically need an exponential complexity when the number of fields is large. However, a basic application of artificial neural network could solve the problem based on the universal approximation theorem of the multilayer perceptron. A toy model in inflation with multiple light fields is investigated numerically as an example of such an application.

AAAIC '88 - Aerospace Applications of Artificial Intelligence; Proceedings of the Fourth Annual Conference, Dayton, OH, Oct. 25-27, 1988. Volumes 1 2

DOE Office of Scientific and Technical Information (OSTI.GOV)

Johnson, J.R.; Netrologic, Inc., San Diego, CA)

1988-01-01

Topics presented include integrating neural networks and expert systems, neural networks and signal processing, machine learning, cognition and avionics applications, artificial intelligence and man-machine interface issues, real time expert systems, artificial intelligence, and engineering applications. Also considered are advanced problem solving techniques, combinational optimization for scheduling and resource control, data fusion/sensor fusion, back propagation with momentum, shared weights and recurrency, automatic target recognition, cybernetics, optical neural networks.

Modular neural networks: a survey.

PubMed

Auda, G; Kamel, M

1999-04-01

Modular Neural Networks (MNNs) is a rapidly growing field in artificial Neural Networks (NNs) research. This paper surveys the different motivations for creating MNNs: biological, psychological, hardware, and computational. Then, the general stages of MNN design are outlined and surveyed as well, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies. Advantages and disadvantages of the surveyed methods are pointed out, and an assessment with respect to practical potential is provided. Finally, some general recommendations for future designs are presented.

A Constructive Neural-Network Approach to Modeling Psychological Development

ERIC Educational Resources Information Center

Shultz, Thomas R.

2012-01-01

This article reviews a particular computational modeling approach to the study of psychological development--that of constructive neural networks. This approach is applied to a variety of developmental domains and issues, including Piagetian tasks, shift learning, language acquisition, number comparison, habituation of visual attention, concept…

Forecasting influenza-like illness dynamics for military populations using neural networks and social media

PubMed Central

Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D.

2017-01-01

This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in “real-time”) and forecasting (predicting the future) ILI dynamics in the 2011 – 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets. PMID:29244814

Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

PubMed

Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D

2017-01-01

This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in "real-time") and forecasting (predicting the future) ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets.

Application of artificial neural networks to chemostratigraphy

NASA Astrophysics Data System (ADS)

Malmgren, BjöRn A.; Nordlund, Ulf

1996-08-01

Artificial neural networks, a branch of artificial intelligence, are computer systems formed by a number of simple, highly interconnected processing units that have the ability to learn a set of target vectors from a set of associated input signals. Neural networks learn by self-adjusting a set of parameters, using some pertinent algorithm to minimize the error between the desired output and network output. We explore the potential of this approach in solving a problem involving classification of geochemical data. The data, taken from the literature, are derived from four late Quaternary zones of volcanic ash of basaltic and rhyolithic origin from the Norwegian Sea. These ash layers span the oxygen isotope zones 1, 5, 7, and 11, respectively (last 420,000 years). The data consist of nine geochemical variables (oxides) determined in each of 183 samples. We employed a three-layer back propagation neural network to assess its efficiency to optimally differentiate samples from the four ash zones on the basis of their geochemical composition. For comparison, three statistical pattern recognition techniques, linear discriminant analysis, the k-nearest neighbor (k-NN) technique, and SIMCA (soft independent modeling of class analogy), were applied to the same data. All of these showed considerably higher error rates than the artificial neural network, indicating that the back propagation network was indeed more powerful in correctly classifying the ash particles to the appropriate zone on the basis of their geochemical composition.

Concept Model on Topological Learning

NASA Astrophysics Data System (ADS)

Ae, Tadashi; Kioi, Kazumasa

2010-11-01

We discuss a new model for concept based on topological learning, where the learning process on the neural network is represented by mathematical topology. The topological learning of neural networks is summarized by a quotient of input space and the hierarchical step induces a tree where each node corresponds to a quotient. In general, the concept acquisition is a difficult problem, but the emotion for a subject is represented by providing the questions to a person. Therefore, a kind of concept is captured by such data and the answer sheet can be mapped into a topology consisting of trees. In this paper, we will discuss a way of mapping the emotional concept to a topological learning model.

Ensemble learning in fixed expansion layer networks for mitigating catastrophic forgetting.

PubMed

Coop, Robert; Mishtal, Aaron; Arel, Itamar

2013-10-01

Catastrophic forgetting is a well-studied attribute of most parameterized supervised learning systems. A variation of this phenomenon, in the context of feedforward neural networks, arises when nonstationary inputs lead to loss of previously learned mappings. The majority of the schemes proposed in the literature for mitigating catastrophic forgetting were not data driven and did not scale well. We introduce the fixed expansion layer (FEL) feedforward neural network, which embeds a sparsely encoding hidden layer to help mitigate forgetting of prior learned representations. In addition, we investigate a novel framework for training ensembles of FEL networks, based on exploiting an information-theoretic measure of diversity between FEL learners, to further control undesired plasticity. The proposed methodology is demonstrated on a basic classification task, clearly emphasizing its advantages over existing techniques. The architecture proposed can be enhanced to address a range of computational intelligence tasks, such as regression problems and system control.

Learning in Stochastic Bit Stream Neural Networks.

PubMed

van Daalen, Max; Shawe-Taylor, John; Zhao, Jieyu

1996-08-01

This paper presents learning techniques for a novel feedforward stochastic neural network. The model uses stochastic weights and the "bit stream" data representation. It has a clean analysable functionality and is very attractive with its great potential to be implemented in hardware using standard digital VLSI technology. The design allows simulation at three different levels and learning techniques are described for each level. The lowest level corresponds to on-chip learning. Simulation results on three benchmark MONK's problems and handwritten digit recognition with a clean set of 500 16 x 16 pixel digits demonstrate that the new model is powerful enough for the real world applications. Copyright 1996 Elsevier Science Ltd

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

On the fusion of tuning parameters of fuzzy rules and neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Learning fuzzy rule-based system with neural network can lead to a precise valuable empathy of several problems. Fuzzy logic offers a simple way to reach at a definite conclusion based upon its vague, ambiguous, imprecise, noisy or missing input information. Conventional learning algorithm for tuning parameters of fuzzy rules using training input-output data usually end in a weak firing state, this certainly powers the fuzzy rule and makes it insecure for a multiple-input fuzzy system. In this paper, we introduce a new learning algorithm for tuning the parameters of the fuzzy rules alongside with radial basis function neural network (RBFNN) in training input-output data based on the gradient descent method. By the new learning algorithm, the problem of weak firing using the conventional method was addressed. We illustrated the efficiency of our new learning algorithm by means of numerical examples. MATLAB R2014(a) software was used in simulating our result The result shows that the new learning method has the best advantage of training the fuzzy rules without tempering with the fuzzy rule table which allowed a membership function of the rule to be used more than one time in the fuzzy rule base.

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach.

PubMed

Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

2017-06-19

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification.

Addressing the Movement of a Freescale Robotic Car Using Neural Network

NASA Astrophysics Data System (ADS)

Horváth, Dušan; Cuninka, Peter

2016-12-01

This article deals with the management of a Freescale small robotic car along the predefined guide line. Controlling of the direction of movement of the robot is performed by neural networks, and scales (memory) of neurons are calculated by Hebbian learning from the truth tables as learning with a teacher. Reflexive infrared sensors serves as inputs. The results are experiments, which are used to compare two methods of mobile robot control - tracking lines.

Neural network representation and learning of mappings and their derivatives

NASA Technical Reports Server (NTRS)

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

1991-01-01

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

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

A spiking neural network based on the basal ganglia functional anatomy.

PubMed

Baladron, Javier; Hamker, Fred H

2015-07-01

We introduce a spiking neural network of the basal ganglia capable of learning stimulus-action associations. We model learning in the three major basal ganglia pathways, direct, indirect and hyperdirect, by spike time dependent learning and considering the amount of dopamine available (reward). Moreover, we allow to learn a cortico-thalamic pathway that bypasses the basal ganglia. As a result the system develops new functionalities for the different basal ganglia pathways: The direct pathway selects actions by disinhibiting the thalamus, the hyperdirect one suppresses alternatives and the indirect pathway learns to inhibit common mistakes. Numerical experiments show that the system is capable of learning sets of either deterministic or stochastic rules. Copyright © 2015 Elsevier Ltd. All rights reserved.

Differential theory of learning for efficient neural network pattern recognition

NASA Astrophysics Data System (ADS)

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

1993-09-01

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

Differential theory of learning for efficient neural network pattern recognition

NASA Astrophysics Data System (ADS)

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

1993-08-01

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

Redistribution of neural phase coherence reflects establishment of feedforward map in speech motor adaptation

PubMed Central

Sengupta, Ranit

2015-01-01

Despite recent progress in our understanding of sensorimotor integration in speech learning, a comprehensive framework to investigate its neural basis is lacking at behaviorally relevant timescales. Structural and functional imaging studies in humans have helped us identify brain networks that support speech but fail to capture the precise spatiotemporal coordination within the networks that takes place during speech learning. Here we use neuronal oscillations to investigate interactions within speech motor networks in a paradigm of speech motor adaptation under altered feedback with continuous recording of EEG in which subjects adapted to the real-time auditory perturbation of a target vowel sound. As subjects adapted to the task, concurrent changes were observed in the theta-gamma phase coherence during speech planning at several distinct scalp regions that is consistent with the establishment of a feedforward map. In particular, there was an increase in coherence over the central region and a decrease over the fronto-temporal regions, revealing a redistribution of coherence over an interacting network of brain regions that could be a general feature of error-based motor learning in general. Our findings have implications for understanding the neural basis of speech motor learning and could elucidate how transient breakdown of neuronal communication within speech networks relates to speech disorders. PMID:25632078

Using Neural Networks to Describe Tracer Correlations

NASA Technical Reports Server (NTRS)

Lary, D. J.; Mueller, M. D.; Mussa, H. Y.

2003-01-01

Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation co- efficient of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE) which has continuously observed CH4, (but not N2O) from 1991 till the present. The neural network Fortran code used is available for download.

Blur identification by multilayer neural network based on multivalued neurons.

PubMed

Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T

2008-05-01

A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones.

eLoom and Flatland: specification, simulation and visualization engines for the study of arbitrary hierarchical neural architectures.

PubMed

Caudell, Thomas P; Xiao, Yunhai; Healy, Michael J

2003-01-01

eLoom is an open source graph simulation software tool, developed at the University of New Mexico (UNM), that enables users to specify and simulate neural network models. Its specification language and libraries enables users to construct and simulate arbitrary, potentially hierarchical network structures on serial and parallel processing systems. In addition, eLoom is integrated with UNM's Flatland, an open source virtual environments development tool to provide real-time visualizations of the network structure and activity. Visualization is a useful method for understanding both learning and computation in artificial neural networks. Through 3D animated pictorially representations of the state and flow of information in the network, a better understanding of network functionality is achieved. ART-1, LAPART-II, MLP, and SOM neural networks are presented to illustrate eLoom and Flatland's capabilities.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

PubMed

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-04-17

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

PubMed Central

Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-01-01

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices. PMID:29673171

Decomposition of Rotor Hopfield Neural Networks Using Complex Numbers.

PubMed

Kobayashi, Masaki

2018-04-01

A complex-valued Hopfield neural network (CHNN) is a multistate model of a Hopfield neural network. It has the disadvantage of low noise tolerance. Meanwhile, a symmetric CHNN (SCHNN) is a modification of a CHNN that improves noise tolerance. Furthermore, a rotor Hopfield neural network (RHNN) is an extension of a CHNN. It has twice the storage capacity of CHNNs and SCHNNs, and much better noise tolerance than CHNNs, although it requires twice many connection parameters. In this brief, we investigate the relations between CHNN, SCHNN, and RHNN; an RHNN is uniquely decomposed into a CHNN and SCHNN. In addition, the Hebbian learning rule for RHNNs is decomposed into those for CHNNs and SCHNNs.

Automated selection of computed tomography display parameters using neural networks

NASA Astrophysics Data System (ADS)

Zhang, Di; Neu, Scott; Valentino, Daniel J.

2001-07-01

A collection of artificial neural networks (ANN's) was trained to identify simple anatomical structures in a set of x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point by using the image pixels located on the horizontal and vertical lines that ran through the point. The neural networks were integrated into a computer software tool whose function is to select an index into a list of CT window/level values from the location of the user's mouse cursor. Based upon the anatomical structure selected by the user, the software tool automatically adjusts the image display to optimally view the structure.

System Identification for Nonlinear Control Using Neural Networks

NASA Technical Reports Server (NTRS)

Stengel, Robert F.; Linse, Dennis J.

1990-01-01

An approach to incorporating artificial neural networks in nonlinear, adaptive control systems is described. The controller contains three principal elements: a nonlinear inverse dynamic control law whose coefficients depend on a comprehensive model of the plant, a neural network that models system dynamics, and a state estimator whose outputs drive the control law and train the neural network. Attention is focused on the system identification task, which combines an extended Kalman filter with generalized spline function approximation. Continual learning is possible during normal operation, without taking the system off line for specialized training. Nonlinear inverse dynamic control requires smooth derivatives as well as function estimates, imposing stringent goals on the approximating technique.

Deep multi-scale convolutional neural network for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Zhang, Feng-zhe; Yang, Xia

2018-04-01

In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

Discovery Learning in Autonomous Agents Using Genetic Algorithms

DTIC Science & Technology

1993-12-01

Meyer and Wilson (47). 65. Roitblat , H. L., et al. "Biomimetic Sonar Processing: Prom Dolphin Echoloc-Ation to Artificial Neural Networks." In Meyer and...34 In Meyer and Wilson (47). 65. Roitblat , H. L., et al. "Biomimetic Sonar Processing: From Dolphin Echolocation to Artificial Neural Networks." In

Does Artificial Neural Network Support Connectivism's Assumptions?

ERIC Educational Resources Information Center

AlDahdouh, Alaa A.

2017-01-01

Connectivism was presented as a learning theory for the digital age and connectivists claim that recent developments in Artificial Intelligence (AI) and, more specifically, Artificial Neural Network (ANN) support their assumptions of knowledge connectivity. Yet, very little has been done to investigate this brave allegation. Does the advancement…

Autoshaping and Automaintenance: A Neural-Network Approach

ERIC Educational Resources Information Center

Burgos, Jose E.

2007-01-01

This article presents an interpretation of autoshaping, and positive and negative automaintenance, based on a neural-network model. The model makes no distinction between operant and respondent learning mechanisms, and takes into account knowledge of hippocampal and dopaminergic systems. Four simulations were run, each one using an "A-B-A" design…

Density-based clustering: A 'landscape view' of multi-channel neural data for inference and dynamic complexity analysis.

PubMed

Baglietto, Gabriel; Gigante, Guido; Del Giudice, Paolo

2017-01-01

Two, partially interwoven, hot topics in the analysis and statistical modeling of neural data, are the development of efficient and informative representations of the time series derived from multiple neural recordings, and the extraction of information about the connectivity structure of the underlying neural network from the recorded neural activities. In the present paper we show that state-space clustering can provide an easy and effective option for reducing the dimensionality of multiple neural time series, that it can improve inference of synaptic couplings from neural activities, and that it can also allow the construction of a compact representation of the multi-dimensional dynamics, that easily lends itself to complexity measures. We apply a variant of the 'mean-shift' algorithm to perform state-space clustering, and validate it on an Hopfield network in the glassy phase, in which metastable states are largely uncorrelated from memories embedded in the synaptic matrix. In this context, we show that the neural states identified as clusters' centroids offer a parsimonious parametrization of the synaptic matrix, which allows a significant improvement in inferring the synaptic couplings from the neural activities. Moving to the more realistic case of a multi-modular spiking network, with spike-frequency adaptation inducing history-dependent effects, we propose a procedure inspired by Boltzmann learning, but extending its domain of application, to learn inter-module synaptic couplings so that the spiking network reproduces a prescribed pattern of spatial correlations; we then illustrate, in the spiking network, how clustering is effective in extracting relevant features of the network's state-space landscape. Finally, we show that the knowledge of the cluster structure allows casting the multi-dimensional neural dynamics in the form of a symbolic dynamics of transitions between clusters; as an illustration of the potential of such reduction, we define and analyze a measure of complexity of the neural time series.

Adaptive nodes enrich nonlinear cooperative learning beyond traditional adaptation by links.

PubMed

Sardi, Shira; Vardi, Roni; Goldental, Amir; Sheinin, Anton; Uzan, Herut; Kanter, Ido

2018-03-23

Physical models typically assume time-independent interactions, whereas neural networks and machine learning incorporate interactions that function as adjustable parameters. Here we demonstrate a new type of abundant cooperative nonlinear dynamics where learning is attributed solely to the nodes, instead of the network links which their number is significantly larger. The nodal, neuronal, fast adaptation follows its relative anisotropic (dendritic) input timings, as indicated experimentally, similarly to the slow learning mechanism currently attributed to the links, synapses. It represents a non-local learning rule, where effectively many incoming links to a node concurrently undergo the same adaptation. The network dynamics is now counterintuitively governed by the weak links, which previously were assumed to be insignificant. This cooperative nonlinear dynamic adaptation presents a self-controlled mechanism to prevent divergence or vanishing of the learning parameters, as opposed to learning by links, and also supports self-oscillations of the effective learning parameters. It hints on a hierarchical computational complexity of nodes, following their number of anisotropic inputs and opens new horizons for advanced deep learning algorithms and artificial intelligence based applications, as well as a new mechanism for enhanced and fast learning by neural networks.

Gross domestic product estimation based on electricity utilization by artificial neural network

NASA Astrophysics Data System (ADS)

Stevanović, Mirjana; Vujičić, Slađana; Gajić, Aleksandar M.

2018-01-01

The main goal of the paper was to estimate gross domestic product (GDP) based on electricity estimation by artificial neural network (ANN). The electricity utilization was analyzed based on different sources like renewable, coal and nuclear sources. The ANN network was trained with two training algorithms namely extreme learning method and back-propagation algorithm in order to produce the best prediction results of the GDP. According to the results it can be concluded that the ANN model with extreme learning method could produce the acceptable prediction of the GDP based on the electricity utilization.

Neural network based load and price forecasting and confidence interval estimation in deregulated power markets

NASA Astrophysics Data System (ADS)

Zhang, Li

With the deregulation of the electric power market in New England, an independent system operator (ISO) has been separated from the New England Power Pool (NEPOOL). The ISO provides a regional spot market, with bids on various electricity-related products and services submitted by utilities and independent power producers. A utility can bid on the spot market and buy or sell electricity via bilateral transactions. Good estimation of market clearing prices (MCP) will help utilities and independent power producers determine bidding and transaction strategies with low risks, and this is crucial for utilities to compete in the deregulated environment. MCP prediction, however, is difficult since bidding strategies used by participants are complicated and MCP is a non-stationary process. The main objective of this research is to provide efficient short-term load and MCP forecasting and corresponding confidence interval estimation methodologies. In this research, the complexity of load and MCP with other factors is investigated, and neural networks are used to model the complex relationship between input and output. With improved learning algorithm and on-line update features for load forecasting, a neural network based load forecaster was developed, and has been in daily industry use since summer 1998 with good performance. MCP is volatile because of the complexity of market behaviors. In practice, neural network based MCP predictors usually have a cascaded structure, as several key input factors need to be estimated first. In this research, the uncertainties involved in a cascaded neural network structure for MCP prediction are analyzed, and prediction distribution under the Bayesian framework is developed. A fast algorithm to evaluate the confidence intervals by using the memoryless Quasi-Newton method is also developed. The traditional back-propagation algorithm for neural network learning needs to be improved since MCP is a non-stationary process. The extended Kalman filter (EKF) can be used as an integrated adaptive learning and confidence interval estimation algorithm for neural networks, with fast convergence and small confidence intervals. However, EKF learning is computationally expensive because it involves high dimensional matrix manipulations. A modified U-D factorization within the decoupled EKF (DEKF-UD) framework is developed in this research. The computational efficiency and numerical stability are significantly improved.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Learning and coding in biological neural networks

NASA Astrophysics Data System (ADS)

Fiete, Ila Rani

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

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity

PubMed Central

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns—both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity. PMID:25566045

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity.

PubMed

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns-both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity.

A Network Neuroscience of Human Learning: Potential To Inform Quantitative Theories of Brain and Behavior

PubMed Central

Bassett, Danielle S.; Mattar, Marcelo G.

2017-01-01

Humans adapt their behavior to their external environment in a process often facilitated by learning. Efforts to describe learning empirically can be complemented by quantitative theories that map changes in neurophysiology to changes in behavior. In this review we highlight recent advances in network science that offer a sets of tools and a general perspective that may be particularly useful in understanding types of learning that are supported by distributed neural circuits. We describe recent applications of these tools to neuroimaging data that provide unique insights into adaptive neural processes, the attainment of knowledge, and the acquisition of new skills, forming a network neuroscience of human learning. While promising, the tools have yet to be linked to the well-formulated models of behavior that are commonly utilized in cognitive psychology. We argue that continued progress will require the explicit marriage of network approaches to neuroimaging data and quantitative models of behavior. PMID:28259554

A Network Neuroscience of Human Learning: Potential to Inform Quantitative Theories of Brain and Behavior.

PubMed

Bassett, Danielle S; Mattar, Marcelo G

2017-04-01

Humans adapt their behavior to their external environment in a process often facilitated by learning. Efforts to describe learning empirically can be complemented by quantitative theories that map changes in neurophysiology to changes in behavior. In this review we highlight recent advances in network science that offer a sets of tools and a general perspective that may be particularly useful in understanding types of learning that are supported by distributed neural circuits. We describe recent applications of these tools to neuroimaging data that provide unique insights into adaptive neural processes, the attainment of knowledge, and the acquisition of new skills, forming a network neuroscience of human learning. While promising, the tools have yet to be linked to the well-formulated models of behavior that are commonly utilized in cognitive psychology. We argue that continued progress will require the explicit marriage of network approaches to neuroimaging data and quantitative models of behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

A Learning Framework for Winner-Take-All Networks with Stochastic Synapses.

PubMed

Mostafa, Hesham; Cauwenberghs, Gert

2018-06-01

Many recent generative models make use of neural networks to transform the probability distribution of a simple low-dimensional noise process into the complex distribution of the data. This raises the question of whether biological networks operate along similar principles to implement a probabilistic model of the environment through transformations of intrinsic noise processes. The intrinsic neural and synaptic noise processes in biological networks, however, are quite different from the noise processes used in current abstract generative networks. This, together with the discrete nature of spikes and local circuit interactions among the neurons, raises several difficulties when using recent generative modeling frameworks to train biologically motivated models. In this letter, we show that a biologically motivated model based on multilayer winner-take-all circuits and stochastic synapses admits an approximate analytical description. This allows us to use the proposed networks in a variational learning setting where stochastic backpropagation is used to optimize a lower bound on the data log likelihood, thereby learning a generative model of the data. We illustrate the generality of the proposed networks and learning technique by using them in a structured output prediction task and a semisupervised learning task. Our results extend the domain of application of modern stochastic network architectures to networks where synaptic transmission failure is the principal noise mechanism.

Self-learning Monte Carlo with deep neural networks

NASA Astrophysics Data System (ADS)

Shen, Huitao; Liu, Junwei; Fu, Liang

2018-05-01

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

Recognition of Telugu characters using neural networks.

PubMed

Sukhaswami, M B; Seetharamulu, P; Pujari, A K

1995-09-01

The aim of the present work is to recognize printed and handwritten Telugu characters using artificial neural networks (ANNs). Earlier work on recognition of Telugu characters has been done using conventional pattern recognition techniques. We make an initial attempt here of using neural networks for recognition with the aim of improving upon earlier methods which do not perform effectively in the presence of noise and distortion in the characters. The Hopfield model of neural network working as an associative memory is chosen for recognition purposes initially. Due to limitation in the capacity of the Hopfield neural network, we propose a new scheme named here as the Multiple Neural Network Associative Memory (MNNAM). The limitation in storage capacity has been overcome by combining multiple neural networks which work in parallel. It is also demonstrated that the Hopfield network is suitable for recognizing noisy printed characters as well as handwritten characters written by different "hands" in a variety of styles. Detailed experiments have been carried out using several learning strategies and results are reported. It is shown here that satisfactory recognition is possible using the proposed strategy. A detailed preprocessing scheme of the Telugu characters from digitized documents is also described.

Computational Modeling of Statistical Learning: Effects of Transitional Probability versus Frequency and Links to Word Learning

ERIC Educational Resources Information Center

Mirman, Daniel; Estes, Katharine Graf; Magnuson, James S.

2010-01-01

Statistical learning mechanisms play an important role in theories of language acquisition and processing. Recurrent neural network models have provided important insights into how these mechanisms might operate. We examined whether such networks capture two key findings in human statistical learning. In Simulation 1, a simple recurrent network…

Wishart Deep Stacking Network for Fast POLSAR Image Classification.

PubMed

Jiao, Licheng; Liu, Fang

2016-05-11

Inspired by the popular deep learning architecture - Deep Stacking Network (DSN), a specific deep model for polarimetric synthetic aperture radar (POLSAR) image classification is proposed in this paper, which is named as Wishart Deep Stacking Network (W-DSN). First of all, a fast implementation of Wishart distance is achieved by a special linear transformation, which speeds up the classification of POLSAR image and makes it possible to use this polarimetric information in the following Neural Network (NN). Then a single-hidden-layer neural network based on the fast Wishart distance is defined for POLSAR image classification, which is named as Wishart Network (WN) and improves the classification accuracy. Finally, a multi-layer neural network is formed by stacking WNs, which is in fact the proposed deep learning architecture W-DSN for POLSAR image classification and improves the classification accuracy further. In addition, the structure of WN can be expanded in a straightforward way by adding hidden units if necessary, as well as the structure of the W-DSN. As a preliminary exploration on formulating specific deep learning architecture for POLSAR image classification, the proposed methods may establish a simple but clever connection between POLSAR image interpretation and deep learning. The experiment results tested on real POLSAR image show that the fast implementation of Wishart distance is very efficient (a POLSAR image with 768000 pixels can be classified in 0.53s), and both the single-hidden-layer architecture WN and the deep learning architecture W-DSN for POLSAR image classification perform well and work efficiently.

A new neural net approach to robot 3D perception and visuo-motor coordination

NASA Technical Reports Server (NTRS)

Lee, Sukhan

1992-01-01

A novel neural network approach to robot hand-eye coordination is presented. The approach provides a true sense of visual error servoing, redundant arm configuration control for collision avoidance, and invariant visuo-motor learning under gazing control. A 3-D perception network is introduced to represent the robot internal 3-D metric space in which visual error servoing and arm configuration control are performed. The arm kinematic network performs the bidirectional association between 3-D space arm configurations and joint angles, and enforces the legitimate arm configurations. The arm kinematic net is structured by a radial-based competitive and cooperative network with hierarchical self-organizing learning. The main goal of the present work is to demonstrate that the neural net representation of the robot 3-D perception net serves as an important intermediate functional block connecting robot eyes and arms.

The applications of deep neural networks to sdBV classification

NASA Astrophysics Data System (ADS)

Boudreaux, Thomas M.

2017-12-01

With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in industry for years now, allows for advanced feature detection in minimally prepared datasets at very high speeds; however, despite the advantages of this method, its application to astrophysics has not yet been extensively explored. This dearth may be due to a lack of training data available to researchers. Here we generate synthetic data loosely mimicking the properties of acoustic mode pulsating stars and we show that two separate paradigms of deep learning - the Artificial Neural Network And the Convolutional Neural Network - can both be used to classify this synthetic data effectively. And that additionally this classification can be performed at relatively high levels of accuracy with minimal time spent adjusting network hyperparameters.

Adaptive control of nonlinear system using online error minimum neural networks.

PubMed

Jia, Chao; Li, Xiaoli; Wang, Kang; Ding, Dawei

2016-11-01

In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

NASA Astrophysics Data System (ADS)

Zhu, Aichun; Wang, Tian; Snoussi, Hichem

2018-03-01

This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

Two distinct neural networks support the mapping of meaning to a novel word.

PubMed

Ye, Zheng; Mestres-Missé, Anna; Rodriguez-Fornells, Antoni; Münte, Thomas F

2011-07-01

Children can learn the meaning of a new word from context during normal reading or listening, without any explicit instruction. It is unclear how such meaning acquisition is supported and achieved in human brain. In this functional magnetic resonance imaging (fMRI) study we investigated neural networks supporting word learning with a functional connectivity approach. Participants were exposed to a new word presented in two successive sentences and needed to derive the meaning of the new word. We observed two neural networks involved in mapping the meaning to the new word. One network connected the left inferior frontal gyrus (LIFG) with the middle frontal gyrus (MFG), medial superior frontal gyrus, caudate nucleus, thalamus, and inferior parietal lobule. The other network connected the left middle temporal gyrus (LMTG) with the MFG, anterior and posterior cingulate cortex. The LIFG network showed stronger interregional interactions for new than real words, whereas the LMTG network showed similar connectivity patterns for new and real words. We proposed that these two networks support different functions during word learning. The LIFG network appears to select the most appropriate meaning from competing candidates and to map the selected meaning onto the new word. The LMTG network may be recruited to integrate the word into sentential context, regardless of whether the word is real or new. The LIFG and the LMTG networks share a common node, the MFG, suggesting that these two networks communicate in working memory. Copyright © 2010 Wiley-Liss, Inc.

Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Culbert, Christopher J. (Editor)

1993-01-01

Papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by the National Aeronautics and Space Administration and cosponsored by the University of Houston, Clear Lake, held 1-3 Jun. 1992 at the Lyndon B. Johnson Space Center in Houston, Texas are included. During the three days approximately 50 papers were presented. Technical topics addressed included adaptive systems; learning algorithms; network architectures; vision; robotics; neurobiological connections; speech recognition and synthesis; fuzzy set theory and application, control and dynamics processing; space applications; fuzzy logic and neural network computers; approximate reasoning; and multiobject decision making.

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

NASA Astrophysics Data System (ADS)

Saputra, Widodo; Tulus; Zarlis, Muhammad; Widia Sembiring, Rahmat; Hartama, Dedy

2017-12-01

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.

Semi-Supervised Recurrent Neural Network for Adverse Drug Reaction mention extraction.

PubMed

Gupta, Shashank; Pawar, Sachin; Ramrakhiyani, Nitin; Palshikar, Girish Keshav; Varma, Vasudeva

2018-06-13

Social media is a useful platform to share health-related information due to its vast reach. This makes it a good candidate for public-health monitoring tasks, specifically for pharmacovigilance. We study the problem of extraction of Adverse-Drug-Reaction (ADR) mentions from social media, particularly from Twitter. Medical information extraction from social media is challenging, mainly due to short and highly informal nature of text, as compared to more technical and formal medical reports. Current methods in ADR mention extraction rely on supervised learning methods, which suffer from labeled data scarcity problem. The state-of-the-art method uses deep neural networks, specifically a class of Recurrent Neural Network (RNN) which is Long-Short-Term-Memory network (LSTM). Deep neural networks, due to their large number of free parameters rely heavily on large annotated corpora for learning the end task. But in the real-world, it is hard to get large labeled data, mainly due to the heavy cost associated with the manual annotation. To this end, we propose a novel semi-supervised learning based RNN model, which can leverage unlabeled data also present in abundance on social media. Through experiments we demonstrate the effectiveness of our method, achieving state-of-the-art performance in ADR mention extraction. In this study, we tackle the problem of labeled data scarcity for Adverse Drug Reaction mention extraction from social media and propose a novel semi-supervised learning based method which can leverage large unlabeled corpus available in abundance on the web. Through empirical study, we demonstrate that our proposed method outperforms fully supervised learning based baseline which relies on large manually annotated corpus for a good performance.

Frame prediction using recurrent convolutional encoder with residual learning

NASA Astrophysics Data System (ADS)

Yue, Boxuan; Liang, Jun

2018-05-01

The prediction for the frame of a video is difficult but in urgent need in auto-driving. Conventional methods can only predict some abstract trends of the region of interest. The boom of deep learning makes the prediction for frames possible. In this paper, we propose a novel recurrent convolutional encoder and DE convolutional decoder structure to predict frames. We introduce the residual learning in the convolution encoder structure to solve the gradient issues. The residual learning can transform the gradient back propagation to an identity mapping. It can reserve the whole gradient information and overcome the gradient issues in Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). Besides, compared with the branches in CNNs and the gated structures in RNNs, the residual learning can save the training time significantly. In the experiments, we use UCF101 dataset to train our networks, the predictions are compared with some state-of-the-art methods. The results show that our networks can predict frames fast and efficiently. Furthermore, our networks are used for the driving video to verify the practicability.

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

NASA Astrophysics Data System (ADS)

Lin, Xin; Mori, Masahiko

2000-05-01

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

Assessing the Linguistic Productivity of Unsupervised Deep Neural Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Phillips, Lawrence A.; Hodas, Nathan O.

Increasingly, cognitive scientists have demonstrated interest in applying tools from deep learning. One use for deep learning is in language acquisition where it is useful to know if a linguistic phenomenon can be learned through domain-general means. To assess whether unsupervised deep learning is appropriate, we first pose a smaller question: Can unsupervised neural networks apply linguistic rules productively, using them in novel situations. We draw from the literature on determiner/noun productivity by training an unsupervised, autoencoder network measuring its ability to combine nouns with determiners. Our simple autoencoder creates combinations it has not previously encountered, displaying a degree ofmore » overlap similar to actual children. While this preliminary work does not provide conclusive evidence for productivity, it warrants further investigation with more complex models. Further, this work helps lay the foundations for future collaboration between the deep learning and cognitive science communities.« less

Reversible large–scale modification of cortical networks during neuroprosthetic control

PubMed Central

Ganguly, Karunesh; Wallis, Jonathan D.

2012-01-01

Brain-Machine Interfaces (BMI) provide a framework to study cortical dynamics and the neural correlates of learning. Neuroprosthetic control has been associated with tuning changes in specific neurons directly projecting to the BMI (hereafter ‘direct neurons’). However, little is known about the larger network dynamics. By monitoring ensembles of neurons that were either causally linked to BMI control or indirectly involved, here we show that proficient neuroprosthetic control is associated with large-scale modifications to the cortical network in macaque monkeys. Specifically, there were changes in the preferred direction of both direct and indirect neurons. Interestingly, with learning, there was a relative decrease in the net modulation of indirect neural activity in comparison to the direct activity. These widespread differential changes in the direct and indirect population activity were remarkably stable from one day to the next and readily coexisted with the long-standing cortical network for upper limb control. Thus, the process of learning BMI control is associated with differential modification of neural populations based on their specific relation to movement control. PMID:21499255

Reversible large-scale modification of cortical networks during neuroprosthetic control.

PubMed

Ganguly, Karunesh; Dimitrov, Dragan F; Wallis, Jonathan D; Carmena, Jose M

2011-05-01

Brain-machine interfaces (BMIs) provide a framework for studying cortical dynamics and the neural correlates of learning. Neuroprosthetic control has been associated with tuning changes in specific neurons directly projecting to the BMI (hereafter referred to as direct neurons). However, little is known about the larger network dynamics. By monitoring ensembles of neurons that were either causally linked to BMI control or indirectly involved, we found that proficient neuroprosthetic control is associated with large-scale modifications to the cortical network in macaque monkeys. Specifically, there were changes in the preferred direction of both direct and indirect neurons. Notably, with learning, there was a relative decrease in the net modulation of indirect neural activity in comparison with direct activity. These widespread differential changes in the direct and indirect population activity were markedly stable from one day to the next and readily coexisted with the long-standing cortical network for upper limb control. Thus, the process of learning BMI control is associated with differential modification of neural populations based on their specific relation to movement control.

Synchronization and Inter-Layer Interactions of Noise-Driven Neural Networks

PubMed Central

Yuniati, Anis; Mai, Te-Lun; Chen, Chi-Ming

2017-01-01

In this study, we used the Hodgkin-Huxley (HH) model of neurons to investigate the phase diagram of a developing single-layer neural network and that of a network consisting of two weakly coupled neural layers. These networks are noise driven and learn through the spike-timing-dependent plasticity (STDP) or the inverse STDP rules. We described how these networks transited from a non-synchronous background activity state (BAS) to a synchronous firing state (SFS) by varying the network connectivity and the learning efficacy. In particular, we studied the interaction between a SFS layer and a BAS layer, and investigated how synchronous firing dynamics was induced in the BAS layer. We further investigated the effect of the inter-layer interaction on a BAS to SFS repair mechanism by considering three types of neuron positioning (random, grid, and lognormal distributions) and two types of inter-layer connections (random and preferential connections). Among these scenarios, we concluded that the repair mechanism has the largest effect for a network with the lognormal neuron positioning and the preferential inter-layer connections. PMID:28197088

Synchronization and Inter-Layer Interactions of Noise-Driven Neural Networks.

PubMed

Yuniati, Anis; Mai, Te-Lun; Chen, Chi-Ming

2017-01-01

In this study, we used the Hodgkin-Huxley (HH) model of neurons to investigate the phase diagram of a developing single-layer neural network and that of a network consisting of two weakly coupled neural layers. These networks are noise driven and learn through the spike-timing-dependent plasticity (STDP) or the inverse STDP rules. We described how these networks transited from a non-synchronous background activity state (BAS) to a synchronous firing state (SFS) by varying the network connectivity and the learning efficacy. In particular, we studied the interaction between a SFS layer and a BAS layer, and investigated how synchronous firing dynamics was induced in the BAS layer. We further investigated the effect of the inter-layer interaction on a BAS to SFS repair mechanism by considering three types of neuron positioning (random, grid, and lognormal distributions) and two types of inter-layer connections (random and preferential connections). Among these scenarios, we concluded that the repair mechanism has the largest effect for a network with the lognormal neuron positioning and the preferential inter-layer connections.

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

PubMed

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

2018-01-01

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

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

PubMed Central

Habenschuss, Stefan; Hsieh, Michael

2018-01-01

Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown that the spontaneous synapse-autonomous component of spine dynamics is at least as large as the component that depends on the history of pre- and postsynaptic neural activity. These data are inconsistent with common models for network plasticity and raise the following questions: how can neural circuits maintain a stable computational function in spite of these continuously ongoing processes, and what could be functional uses of these ongoing processes? Here, we present a rigorous theoretical framework for these seemingly stochastic spine dynamics and rewiring processes in the context of reward-based learning tasks. We show that spontaneous synapse-autonomous processes, in combination with reward signals such as dopamine, can explain the capability of networks of neurons in the brain to configure themselves for specific computational tasks, and to compensate automatically for later changes in the network or task. Furthermore, we show theoretically and through computer simulations that stable computational performance is compatible with continuously ongoing synapse-autonomous changes. After reaching good computational performance it causes primarily a slow drift of network architecture and dynamics in task-irrelevant dimensions, as observed for neural activity in motor cortex and other areas. On the more abstract level of reinforcement learning the resulting model gives rise to an understanding of reward-driven network plasticity as continuous sampling of network configurations. PMID:29696150

Biologically inspired intelligent decision making

PubMed Central

Manning, Timmy; Sleator, Roy D; Walsh, Paul

2014-01-01

Artificial neural networks (ANNs) are a class of powerful machine learning models for classification and function approximation which have analogs in nature. An ANN learns to map stimuli to responses through repeated evaluation of exemplars of the mapping. This learning approach results in networks which are recognized for their noise tolerance and ability to generalize meaningful responses for novel stimuli. It is these properties of ANNs which make them appealing for applications to bioinformatics problems where interpretation of data may not always be obvious, and where the domain knowledge required for deductive techniques is incomplete or can cause a combinatorial explosion of rules. In this paper, we provide an introduction to artificial neural network theory and review some interesting recent applications to bioinformatics problems. PMID:24335433

Emergent latent symbol systems in recurrent neural networks

NASA Astrophysics Data System (ADS)

Monner, Derek; Reggia, James A.

2012-12-01

Fodor and Pylyshyn [(1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28(1-2), 3-71] famously argued that neural networks cannot behave systematically short of implementing a combinatorial symbol system. A recent response from Frank et al. [(2009). Connectionist semantic systematicity. Cognition, 110(3), 358-379] claimed to have trained a neural network to behave systematically without implementing a symbol system and without any in-built predisposition towards combinatorial representations. We believe systems like theirs may in fact implement a symbol system on a deeper and more interesting level: one where the symbols are latent - not visible at the level of network structure. In order to illustrate this possibility, we demonstrate our own recurrent neural network that learns to understand sentence-level language in terms of a scene. We demonstrate our model's learned understanding by testing it on novel sentences and scenes. By paring down our model into an architecturally minimal version, we demonstrate how it supports combinatorial computation over distributed representations by using the associative memory operations of Vector Symbolic Architectures. Knowledge of the model's memory scheme gives us tools to explain its errors and construct superior future models. We show how the model designs and manipulates a latent symbol system in which the combinatorial symbols are patterns of activation distributed across the layers of a neural network, instantiating a hybrid of classical symbolic and connectionist representations that combines advantages of both.

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods.

PubMed

Arcos-García, Álvaro; Álvarez-García, Juan A; Soria-Morillo, Luis M

2018-03-01

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements. Copyright © 2018 Elsevier Ltd. All rights reserved.

An Indoor Positioning Technique Based on a Feed-Forward Artificial Neural Network Using Levenberg-Marquardt Learning Method

NASA Astrophysics Data System (ADS)

Pahlavani, P.; Gholami, A.; Azimi, S.

2017-09-01

This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF) artificial neural networks (ANN). Most of the indoor received signal strength (RSS)-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration) phase and the online (estimation) phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening). Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg-Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks

PubMed Central

Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo

2015-01-01

Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns. PMID:26291608

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

PubMed

Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo

2015-08-01

Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns.

MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning

PubMed Central

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

2015-01-01

Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation. PMID:26681933

Electronic system with memristive synapses for pattern recognition

PubMed Central

Park, Sangsu; Chu, Myonglae; Kim, Jongin; Noh, Jinwoo; Jeon, Moongu; Hun Lee, Byoung; Hwang, Hyunsang; Lee, Boreom; Lee, Byung-geun

2015-01-01

Memristive synapses, the most promising passive devices for synaptic interconnections in artificial neural networks, are the driving force behind recent research on hardware neural networks. Despite significant efforts to utilize memristive synapses, progress to date has only shown the possibility of building a neural network system that can classify simple image patterns. In this article, we report a high-density cross-point memristive synapse array with improved synaptic characteristics. The proposed PCMO-based memristive synapse exhibits the necessary gradual and symmetrical conductance changes, and has been successfully adapted to a neural network system. The system learns, and later recognizes, the human thought pattern corresponding to three vowels, i.e. /a /, /i /, and /u/, using electroencephalography signals generated while a subject imagines speaking vowels. Our successful demonstration of a neural network system for EEG pattern recognition is likely to intrigue many researchers and stimulate a new research direction. PMID:25941950

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

PubMed

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

2015-01-01

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

Application of Artificial Neural Network to Predict the use of Runway at Juanda International Airport

NASA Astrophysics Data System (ADS)

Putra, J. C. P.; Safrilah

2017-06-01

Artificial neural network approaches are useful to solve many complicated problems. It solves a number of problems in various areas such as engineering, medicine, business, manufacturing, etc. This paper presents an application of artificial neural network to predict a runway capacity at Juanda International Airport. An artificial neural network model of backpropagation and multi-layer perceptron is adopted to this research to learning process of runway capacity at Juanda International Airport. The results indicate that the training data is successfully recognizing the certain pattern of runway use at Juanda International Airport. Whereas, testing data indicate vice versa. Finally, it can be concluded that the approach of uniformity data and network architecture is the critical part to determine the accuracy of prediction results.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-07-01

With the advancement of very large scale integrated circuits (VLSI) technology nodes, lithographic hotspots become a serious problem that affects manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with the extreme scaling of transistor feature size and layout patterns growing in complexity, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. We present a deep convolutional neural network (CNN) that targets representative feature learning in lithography hotspot detection. We carefully analyze the impact and effectiveness of different CNN hyperparameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always in the minority in VLSI mask design, the training dataset is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from a high number of false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply hotspot upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Artificial Neural Networks as an Architectural Design Tool-Generating New Detail Forms Based On the Roman Corinthian Order Capital

NASA Astrophysics Data System (ADS)

Radziszewski, Kacper

2017-10-01

The following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital. During the experiment, as an input training data set, five local geometry parameters combined has given the best results: Theta, Pi, Rho in spherical coordinate system based on the capital volume centroid, followed by Z value of the Cartesian coordinate system and a distance from vertical planes created based on the capital symmetry. Additionally during the experiment, artificial neural network hidden layers optimal count and structure was found, giving results of the error below 0.2% for the mentioned before input parameters. Once successfully trained artificial network, was able to mimic the details composition on any other geometry type given. Despite of calculating the transformed geometry locally and separately for each of the thousands of surface points, system could create visually attractive and diverse, complex patterns. Designed tool, based on the supervised learning method of machine learning, gives possibility of generating new architectural forms- free of the designer’s imagination bounds. Implementing the infinitely broad computational methods of machine learning, or Artificial Intelligence in general, not only could accelerate and simplify the design process, but give an opportunity to explore never seen before, unpredictable forms or everyday architectural practice solutions.

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

PubMed Central

Spencer, Matt; Eickholt, Jesse; Cheng, Jianlin

2014-01-01

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80% and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test data set of 198 proteins, achieving a Q3 accuracy of 80.7% and a Sov accuracy of 74.2%. PMID:25750595

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction.

PubMed

Spencer, Matt; Eickholt, Jesse; Jianlin Cheng

2015-01-01

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80 percent and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test dataset of 198 proteins, achieving a Q3 accuracy of 80.7 percent and a Sov accuracy of 74.2 percent.

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

PubMed

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

2018-05-10

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

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

PubMed

Shimansky, Yury P

2009-12-01

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

Neurocomputing

NASA Technical Reports Server (NTRS)

Hecht-Nielsen, Robert

1990-01-01

The present work is intended to give technologists, research scientists, and mathematicians a graduate-level overview of the field of neurocomputing. After exploring the relationship of this field to general neuroscience, attention is given to neural network building blocks, the self-adaptation equations of learning laws, the data-transformation structures of associative networks, and the multilayer data-transformation structures of mapping networks. Also treated are the neurocomputing frontiers of spatiotemporal, stochastic, and hierarchical networks, 'neurosoftware', the creation of neural network-based computers, and neurocomputing applications in sensor processing, control, and data analysis.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Comment on ‘Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study’

NASA Astrophysics Data System (ADS)

Valdes, Gilmer; Interian, Yannet

2018-03-01

The application of machine learning (ML) presents tremendous opportunities for the field of oncology, thus we read ‘Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study’ with great interest. In this article, the authors used state of the art techniques: a pre-trained convolutional neural network (VGG-16 CNN), transfer learning, data augmentation, drop out and early stopping, all of which are directly responsible for the success and the excitement that these algorithms have created in other fields. We believe that the use of these techniques can offer tremendous opportunities in the field of Medical Physics and as such we would like to praise the authors for their pioneering application to the field of Radiation Oncology. That being said, given that the field of Medical Physics has unique characteristics that differentiate us from those fields where these techniques have been applied successfully, we would like to raise some points for future discussion and follow up studies that could help the community understand the limitations and nuances of deep learning techniques.

The Brain as an Efficient and Robust Adaptive Learner.

PubMed

Denève, Sophie; Alemi, Alireza; Bourdoukan, Ralph

2017-06-07

Understanding how the brain learns to compute functions reliably, efficiently, and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological neural network. However, this is greatly complicated by the credit assignment problem for learning in recurrent networks, e.g., the contribution of each connection to the global output error cannot be determined based only on locally accessible quantities to the synapse. Combining tools from adaptive control theory and efficient coding theories, we propose that neural circuits can indeed learn complex dynamic tasks with local synaptic plasticity rules as long as they associate two experimentally established neural mechanisms. First, they should receive top-down feedbacks driving both their activity and their synaptic plasticity. Second, inhibitory interneurons should maintain a tight balance between excitation and inhibition in the circuit. The resulting networks could learn arbitrary dynamical systems and produce irregular spike trains as variable as those observed experimentally. Yet, this variability in single neurons may hide an extremely efficient and robust computation at the population level. Copyright © 2017 Elsevier Inc. All rights reserved.

Recruitment and Consolidation of Cell Assemblies for Words by Way of Hebbian Learning and Competition in a Multi-Layer Neural Network

PubMed Central

Garagnani, Max; Wennekers, Thomas; Pulvermüller, Friedemann

2009-01-01

Current cognitive theories postulate either localist representations of knowledge or fully overlapping, distributed ones. We use a connectionist model that closely replicates known anatomical properties of the cerebral cortex and neurophysiological principles to show that Hebbian learning in a multi-layer neural network leads to memory traces (cell assemblies) that are both distributed and anatomically distinct. Taking the example of word learning based on action-perception correlation, we document mechanisms underlying the emergence of these assemblies, especially (i) the recruitment of neurons and consolidation of connections defining the kernel of the assembly along with (ii) the pruning of the cell assembly’s halo (consisting of very weakly connected cells). We found that, whereas a learning rule mapping covariance led to significant overlap and merging of assemblies, a neurobiologically grounded synaptic plasticity rule with fixed LTP/LTD thresholds produced minimal overlap and prevented merging, exhibiting competitive learning behaviour. Our results are discussed in light of current theories of language and memory. As simulations with neurobiologically realistic neural networks demonstrate here spontaneous emergence of lexical representations that are both cortically dispersed and anatomically distinct, both localist and distributed cognitive accounts receive partial support. PMID:20396612

Recruitment and Consolidation of Cell Assemblies for Words by Way of Hebbian Learning and Competition in a Multi-Layer Neural Network.

PubMed

Garagnani, Max; Wennekers, Thomas; Pulvermüller, Friedemann

2009-06-01

Current cognitive theories postulate either localist representations of knowledge or fully overlapping, distributed ones. We use a connectionist model that closely replicates known anatomical properties of the cerebral cortex and neurophysiological principles to show that Hebbian learning in a multi-layer neural network leads to memory traces (cell assemblies) that are both distributed and anatomically distinct. Taking the example of word learning based on action-perception correlation, we document mechanisms underlying the emergence of these assemblies, especially (i) the recruitment of neurons and consolidation of connections defining the kernel of the assembly along with (ii) the pruning of the cell assembly's halo (consisting of very weakly connected cells). We found that, whereas a learning rule mapping covariance led to significant overlap and merging of assemblies, a neurobiologically grounded synaptic plasticity rule with fixed LTP/LTD thresholds produced minimal overlap and prevented merging, exhibiting competitive learning behaviour. Our results are discussed in light of current theories of language and memory. As simulations with neurobiologically realistic neural networks demonstrate here spontaneous emergence of lexical representations that are both cortically dispersed and anatomically distinct, both localist and distributed cognitive accounts receive partial support.

Calculation of precise firing statistics in a neural network model

NASA Astrophysics Data System (ADS)

Cho, Myoung Won

2017-08-01

A precise prediction of neural firing dynamics is requisite to understand the function of and the learning process in a biological neural network which works depending on exact spike timings. Basically, the prediction of firing statistics is a delicate manybody problem because the firing probability of a neuron at a time is determined by the summation over all effects from past firing states. A neural network model with the Feynman path integral formulation is recently introduced. In this paper, we present several methods to calculate firing statistics in the model. We apply the methods to some cases and compare the theoretical predictions with simulation results.

Oscillation, Conduction Delays, and Learning Cooperate to Establish Neural Competition in Recurrent Networks

PubMed Central

Kato, Hideyuki; Ikeguchi, Tohru

2016-01-01

Specific memory might be stored in a subnetwork consisting of a small population of neurons. To select neurons involved in memory formation, neural competition might be essential. In this paper, we show that excitable neurons are competitive and organize into two assemblies in a recurrent network with spike timing-dependent synaptic plasticity (STDP) and axonal conduction delays. Neural competition is established by the cooperation of spontaneously induced neural oscillation, axonal conduction delays, and STDP. We also suggest that the competition mechanism in this paper is one of the basic functions required to organize memory-storing subnetworks into fine-scale cortical networks. PMID:26840529

A convolutional neural network-based screening tool for X-ray serial crystallography

PubMed Central

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K.

2018-01-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. PMID:29714177

Hybrid optoelectronic neural networks using a mutually pumped phase-conjugate mirror

NASA Astrophysics Data System (ADS)

Dunning, G. J.; Owechko, Y.; Soffer, B. H.

1991-06-01

A method is described for interconnecting hybrid optoelectronic neural networks by using a mutually pumped phase conjugate mirror (MP-PCM). In this method, cross talk due to Bragg degeneracies is greatly reduced by storing each weight among many spatially and angularly multiplexed gratings. The effective weight throughput is increased by the parallel updating of weights using outer-product learning. Experiments demonstrated a high degree of interconnectivity between adjacent pixels. A diagram is presented showing the architecture for the optoelectronic neural network using an MP-PCM.

A convolutional neural network-based screening tool for X-ray serial crystallography.

PubMed

Ke, Tsung Wei; Brewster, Aaron S; Yu, Stella X; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K

2018-05-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. open access.

A convolutional neural network-based screening tool for X-ray serial crystallography

DOE PAGES

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; ...

2018-04-24

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

A convolutional neural network-based screening tool for X-ray serial crystallography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

A recurrent self-organizing neural fuzzy inference network.

PubMed

Juang, C F; Lin, C T

1999-01-01

A recurrent self-organizing neural fuzzy inference network (RSONFIN) is proposed in this paper. The RSONFIN is inherently a recurrent multilayered connectionist network for realizing the basic elements and functions of dynamic fuzzy inference, and may be considered to be constructed from a series of dynamic fuzzy rules. The temporal relations embedded in the network are built by adding some feedback connections representing the memory elements to a feedforward neural fuzzy network. Each weight as well as node in the RSONFIN has its own meaning and represents a special element in a fuzzy rule. There are no hidden nodes (i.e., no membership functions and fuzzy rules) initially in the RSONFIN. They are created on-line via concurrent structure identification (the construction of dynamic fuzzy if-then rules) and parameter identification (the tuning of the free parameters of membership functions). The structure learning together with the parameter learning forms a fast learning algorithm for building a small, yet powerful, dynamic neural fuzzy network. Two major characteristics of the RSONFIN can thus be seen: 1) the recurrent property of the RSONFIN makes it suitable for dealing with temporal problems and 2) no predetermination, like the number of hidden nodes, must be given, since the RSONFIN can find its optimal structure and parameters automatically and quickly. Moreover, to reduce the number of fuzzy rules generated, a flexible input partition method, the aligned clustering-based algorithm, is proposed. Various simulations on temporal problems are done and performance comparisons with some existing recurrent networks are also made. Efficiency of the RSONFIN is verified from these results.

Application of Artificial Neural Network to Optical Fluid Analyzer

NASA Astrophysics Data System (ADS)

Kimura, Makoto; Nishida, Katsuhiko

1994-04-01

A three-layer artificial neural network has been applied to the presentation of optical fluid analyzer (OFA) raw data, and the accuracy of oil fraction determination has been significantly improved compared to previous approaches. To apply the artificial neural network approach to solving a problem, the first step is training to determine the appropriate weight set for calculating the target values. This involves using a series of data sets (each comprising a set of input values and an associated set of output values that the artificial neural network is required to determine) to tune artificial neural network weighting parameters so that the output of the neural network to the given set of input values is as close as possible to the required output. The physical model used to generate the series of learning data sets was the effective flow stream model, developed for OFA data presentation. The effectiveness of the training was verified by reprocessing the same input data as were used to determine the weighting parameters and then by comparing the results of the artificial neural network to the expected output values. The standard deviation of the expected and obtained values was approximately 10% (two sigma).

Bringing Interpretability and Visualization with Artificial Neural Networks

ERIC Educational Resources Information Center

Gritsenko, Andrey

2017-01-01

Extreme Learning Machine (ELM) is a training algorithm for Single-Layer Feed-forward Neural Network (SLFN). The difference in theory of ELM from other training algorithms is in the existence of explicitly-given solution due to the immutability of initialed weights. In practice, ELMs achieve performance similar to that of other state-of-the-art…

Visual NNet: An Educational ANN's Simulation Environment Reusing Matlab Neural Networks Toolbox

ERIC Educational Resources Information Center

Garcia-Roselló, Emilio; González-Dacosta, Jacinto; Lado, Maria J.; Méndez, Arturo J.; Garcia Pérez-Schofield, Baltasar; Ferrer, Fátima

2011-01-01

Artificial Neural Networks (ANN's) are nowadays a common subject in different curricula of graduate and postgraduate studies. Due to the complex algorithms involved and the dynamic nature of ANN's, simulation software has been commonly used to teach this subject. This software has usually been developed specifically for learning purposes, because…

Bilingual Lexical Interactions in an Unsupervised Neural Network Model

ERIC Educational Resources Information Center

Zhao, Xiaowei; Li, Ping

2010-01-01

In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…

Deep convolutional neural network based antenna selection in multiple-input multiple-output system

NASA Astrophysics Data System (ADS)

Cai, Jiaxin; Li, Yan; Hu, Ying

2018-03-01

Antenna selection of wireless communication system has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity in large-scale Multiple-Input MultipleOutput antenna systems. Recently, deep learning based methods have achieved promising performance for large-scale data processing and analysis in many application fields. This paper is the first attempt to introduce the deep learning technique into the field of Multiple-Input Multiple-Output antenna selection in wireless communications. First, the label of attenuation coefficients channel matrix is generated by minimizing the key performance indicator of training antenna systems. Then, a deep convolutional neural network that explicitly exploits the massive latent cues of attenuation coefficients is learned on the training antenna systems. Finally, we use the adopted deep convolutional neural network to classify the channel matrix labels of test antennas and select the optimal antenna subset. Simulation experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based wireless antenna selection.

An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction

PubMed Central

Li, Yiyang; Jin, Weiqi; Zhu, Jin; Zhang, Xu; Li, Shuo

2018-01-01

The problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two problems are the estimated desired image and the learning rate. In this paper, we propose a learning rate rule that combines adaptive threshold edge detection and a temporal gate. Through the noise estimation algorithm, the adaptive spatial threshold is related to the residual nonuniformity noise in the corrected image. The proposed learning rate is used to effectively and stably suppress ghosting artifacts without slowing down the convergence speed. The performance of the proposed technique was thoroughly studied with infrared image sequences with both simulated nonuniformity and real nonuniformity. The results show that the deghosting performance of the proposed method is superior to that of other neural network-based nonuniformity correction algorithms and that the convergence speed is equivalent to the tested deghosting methods. PMID:29342857

An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction.

PubMed

Li, Yiyang; Jin, Weiqi; Zhu, Jin; Zhang, Xu; Li, Shuo

2018-01-13

The problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two problems are the estimated desired image and the learning rate. In this paper, we propose a learning rate rule that combines adaptive threshold edge detection and a temporal gate. Through the noise estimation algorithm, the adaptive spatial threshold is related to the residual nonuniformity noise in the corrected image. The proposed learning rate is used to effectively and stably suppress ghosting artifacts without slowing down the convergence speed. The performance of the proposed technique was thoroughly studied with infrared image sequences with both simulated nonuniformity and real nonuniformity. The results show that the deghosting performance of the proposed method is superior to that of other neural network-based nonuniformity correction algorithms and that the convergence speed is equivalent to the tested deghosting methods.

Deep learning and the electronic structure problem

NASA Astrophysics Data System (ADS)

Mills, Kyle; Spanner, Michael; Tamblyn, Isaac

In the past decade, the fields of artificial intelligence and computer vision have progressed remarkably. Supported by the enthusiasm of large tech companies, as well as significant hardware advances and the utilization of graphical processing units to accelerate computations, deep neural networks (DNN) are gaining momentum as a robust choice for many diverse machine learning applications. We have demonstrated the ability of a DNN to solve a quantum mechanical eigenvalue equation directly, without the need to compute a wavefunction, and without knowledge of the underlying physics. We have trained a convolutional neural network to predict the total energy of an electron in a confining, 2-dimensional electrostatic potential. We numerically solved the one-electron Schrödinger equation for millions of electrostatic potentials, and used this as training data for our neural network. Four classes of potentials were assessed: the canonical cases of the harmonic oscillator and infinite well, and two types of randomly generated potentials for which no analytic solution is known. We compare the performance of the neural network and consider how these results could lead to future advances in electronic structure theory.

Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks.

PubMed

Savalia, Shalin; Emamian, Vahid

2018-05-04

The electrocardiogram (ECG) plays an imperative role in the medical field, as it records heart signal over time and is used to discover numerous cardiovascular diseases. If a documented ECG signal has a certain irregularity in its predefined features, this is called arrhythmia, the types of which include tachycardia, bradycardia, supraventricular arrhythmias, and ventricular, etc. This has encouraged us to do research that consists of distinguishing between several arrhythmias by using deep neural network algorithms such as multi-layer perceptron (MLP) and convolution neural network (CNN). The TensorFlow library that was established by Google for deep learning and machine learning is used in python to acquire the algorithms proposed here. The ECG databases accessible at PhysioBank.com and kaggle.com were used for training, testing, and validation of the MLP and CNN algorithms. The proposed algorithm consists of four hidden layers with weights, biases in MLP, and four-layer convolution neural networks which map ECG samples to the different classes of arrhythmia. The accuracy of the algorithm surpasses the performance of the current algorithms that have been developed by other cardiologists in both sensitivity and precision.

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

PubMed Central

2017-01-01

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ PMID:28749969

F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR

NASA Technical Reports Server (NTRS)

Mitchell, P. H.

1994-01-01

F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the user. The program has a memory requirement of about 900K. The standard distribution medium for this package is a .25 inch streaming magnetic tape cartridge in UNIX tar format. It is also available on a 3.5 inch diskette in UNIX tar format. F77NNS was developed in 1989.

Path optimisation of a mobile robot using an artificial neural network controller

NASA Astrophysics Data System (ADS)

Singh, M. K.; Parhi, D. R.

2011-01-01

This article proposed a novel approach for design of an intelligent controller for an autonomous mobile robot using a multilayer feed forward neural network, which enables the robot to navigate in a real world dynamic environment. The inputs to the proposed neural controller consist of left, right and front obstacle distance with respect to its position and target angle. The output of the neural network is steering angle. A four layer neural network has been designed to solve the path and time optimisation problem of mobile robots, which deals with the cognitive tasks such as learning, adaptation, generalisation and optimisation. A back propagation algorithm is used to train the network. This article also analyses the kinematic design of mobile robots for dynamic movements. The simulation results are compared with experimental results, which are satisfactory and show very good agreement. The training of the neural nets and the control performance analysis has been done in a real experimental setup.

Evolutionary fuzzy ARTMAP neural networks for classification of semiconductor defects.

PubMed

Tan, Shing Chiang; Watada, Junzo; Ibrahim, Zuwairie; Khalid, Marzuki

2015-05-01

Wafer defect detection using an intelligent system is an approach of quality improvement in semiconductor manufacturing that aims to enhance its process stability, increase production capacity, and improve yields. Occasionally, only few records that indicate defective units are available and they are classified as a minority group in a large database. Such a situation leads to an imbalanced data set problem, wherein it engenders a great challenge to deal with by applying machine-learning techniques for obtaining effective solution. In addition, the database may comprise overlapping samples of different classes. This paper introduces two models of evolutionary fuzzy ARTMAP (FAM) neural networks to deal with the imbalanced data set problems in a semiconductor manufacturing operations. In particular, both the FAM models and hybrid genetic algorithms are integrated in the proposed evolutionary artificial neural networks (EANNs) to classify an imbalanced data set. In addition, one of the proposed EANNs incorporates a facility to learn overlapping samples of different classes from the imbalanced data environment. The classification results of the proposed evolutionary FAM neural networks are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed networks in handling classification problems with imbalanced data sets.

Singularities of Three-Layered Complex-Valued Neural Networks With Split Activation Function.

PubMed

Kobayashi, Masaki

2018-05-01

There are three important concepts related to learning processes in neural networks: reducibility, nonminimality, and singularity. Although the definitions of these three concepts differ, they are equivalent in real-valued neural networks. This is also true of complex-valued neural networks (CVNNs) with hidden neurons not employing biases. The situation of CVNNs with hidden neurons employing biases, however, is very complicated. Exceptional reducibility was found, and it was shown that reducibility and nonminimality are not the same. Irreducibility consists of minimality and exceptional reducibility. The relationship between minimality and singularity has not yet been established. In this paper, we describe our surprising finding that minimality and singularity are independent. We also provide several examples based on exceptional reducibility.

Airplane detection in remote sensing images using convolutional neural networks

NASA Astrophysics Data System (ADS)

Ouyang, Chao; Chen, Zhong; Zhang, Feng; Zhang, Yifei

2018-03-01

Airplane detection in remote sensing images remains a challenging problem and has also been taking a great interest to researchers. In this paper we propose an effective method to detect airplanes in remote sensing images using convolutional neural networks. Deep learning methods show greater advantages than the traditional methods with the rise of deep neural networks in target detection, and we give an explanation why this happens. To improve the performance on detection of airplane, we combine a region proposal algorithm with convolutional neural networks. And in the training phase, we divide the background into multi classes rather than one class, which can reduce false alarms. Our experimental results show that the proposed method is effective and robust in detecting airplane.

fMRI Syntactic and Lexical Repetition Effects Reveal the Initial Stages of Learning a New Language.

PubMed

Weber, Kirsten; Christiansen, Morten H; Petersson, Karl Magnus; Indefrey, Peter; Hagoort, Peter

2016-06-29

When learning a new language, we build brain networks to process and represent the acquired words and syntax and integrate these with existing language representations. It is an open question whether the same or different neural mechanisms are involved in learning and processing a novel language compared with the native language(s). Here we investigated the neural repetition effects of repeating known and novel word orders while human subjects were in the early stages of learning a new language. Combining a miniature language with a syntactic priming paradigm, we examined the neural correlates of language learning on-line using functional magnetic resonance imaging. In left inferior frontal gyrus and posterior temporal cortex, the repetition of novel syntactic structures led to repetition enhancement, whereas repetition of known structures resulted in repetition suppression. Additional verb repetition led to an increase in the syntactic repetition enhancement effect in language-related brain regions. Similarly, the repetition of verbs led to repetition enhancement effects in areas related to lexical and semantic processing, an effect that continued to increase in a subset of these regions. Repetition enhancement might reflect a mechanism to build and strengthen a neural network to process novel syntactic structures and lexical items. By contrast, the observed repetition suppression points to overlapping neural mechanisms for native and new language constructions when these have sufficient structural similarities. Acquiring a second language entails learning how to interpret novel words and relations between words, and to integrate them with existing language knowledge. To investigate the brain mechanisms involved in this particularly human skill, we combined an artificial language learning task with a syntactic repetition paradigm. We show that the repetition of novel syntactic structures, as well as words in contexts, leads to repetition enhancement, whereas repetition of known structures results in repetition suppression. We thus propose that repetition enhancement might reflect a brain mechanism to build and strengthen a neural network to process novel syntactic regularities and novel words. Importantly, the results also indicate an overlap in neural mechanisms for native and new language constructions with sufficient structural similarities. Copyright © 2016 the authors 0270-6474/16/366872-09$15.00/0.

Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method.

PubMed

Xie, Xiurui; Qu, Hong; Yi, Zhang; Kurths, Jurgen

2017-06-01

The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.

Learning Orthographic Structure With Sequential Generative Neural Networks.

PubMed

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

2016-04-01

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

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach

PubMed Central

Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

2017-01-01

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification. PMID:28629202

Deep learning with convolutional neural network in radiology.

PubMed

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

2018-04-01

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

Neural networks involved in learning lexical-semantic and syntactic information in a second language.

PubMed

Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

2014-01-01

The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

Analyzing Distributional Learning of Phonemic Categories in Unsupervised Deep Neural Networks

PubMed Central

Räsänen, Okko; Nagamine, Tasha; Mesgarani, Nima

2017-01-01

Infants’ speech perception adapts to the phonemic categories of their native language, a process assumed to be driven by the distributional properties of speech. This study investigates whether deep neural networks (DNNs), the current state-of-the-art in distributional feature learning, are capable of learning phoneme-like representations of speech in an unsupervised manner. We trained DNNs with unlabeled and labeled speech and analyzed the activations of each layer with respect to the phones in the input segments. The analyses reveal that the emergence of phonemic invariance in DNNs is dependent on the availability of phonemic labeling of the input during the training. No increased phonemic selectivity of the hidden layers was observed in the purely unsupervised networks despite successful learning of low-dimensional representations for speech. This suggests that additional learning constraints or more sophisticated models are needed to account for the emergence of phone-like categories in distributional learning operating on natural speech. PMID:29359204

Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN).

PubMed

Iqbal, Sajid; Ghani, M Usman; Saba, Tanzila; Rehman, Amjad

2018-04-01

A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research. © 2018 Wiley Periodicals, Inc.

Indirect adaptive fuzzy wavelet neural network with self- recurrent consequent part for AC servo system.

PubMed

Hou, Runmin; Wang, Li; Gao, Qiang; Hou, Yuanglong; Wang, Chao

2017-09-01

This paper proposes a novel indirect adaptive fuzzy wavelet neural network (IAFWNN) to control the nonlinearity, wide variations in loads, time-variation and uncertain disturbance of the ac servo system. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of TSK fuzzy model. For the IAFWNN controller, the online learning algorithm is based on back propagation (BP) algorithm. Moreover, an improved particle swarm optimization (IPSO) is used to adapt the learning rate. The aid of an adaptive SRWNN identifier offers the real-time gradient information to the adaptive fuzzy wavelet neural controller to overcome the impact of parameter variations, load disturbances and other uncertainties effectively, and has a good dynamic. The asymptotical stability of the system is guaranteed by using the Lyapunov method. The result of the simulation and the prototype test prove that the proposed are effective and suitable. Copyright © 2017. Published by Elsevier Ltd.

Forecasting PM10 in metropolitan areas: Efficacy of neural networks.

PubMed

Fernando, H J S; Mammarella, M C; Grandoni, G; Fedele, P; Di Marco, R; Dimitrova, R; Hyde, P

2012-04-01

Deterministic photochemical air quality models are commonly used for regulatory management and planning of urban airsheds. These models are complex, computer intensive, and hence are prohibitively expensive for routine air quality predictions. Stochastic methods are becoming increasingly popular as an alternative, which relegate decision making to artificial intelligence based on Neural Networks that are made of artificial neurons or 'nodes' capable of 'learning through training' via historic data. A Neural Network was used to predict particulate matter concentration at a regulatory monitoring site in Phoenix, Arizona; its development, efficacy as a predictive tool and performance vis-à-vis a commonly used regulatory photochemical model are described in this paper. It is concluded that Neural Networks are much easier, quicker and economical to implement without compromising the accuracy of predictions. Neural Networks can be used to develop rapid air quality warning systems based on a network of automated monitoring stations. Copyright © 2011 Elsevier Ltd. All rights reserved.

Application of artificial neural network to search for gravitational-wave signals associated with short gamma-ray bursts

NASA Astrophysics Data System (ADS)

Kim, Kyungmin; Harry, Ian W.; Hodge, Kari A.; Kim, Young-Min; Lee, Chang-Hwan; Lee, Hyun Kyu; Oh, John J.; Oh, Sang Hoon; Son, Edwin J.

2015-12-01

We apply a machine learning algorithm, the artificial neural network, to the search for gravitational-wave signals associated with short gamma-ray bursts (GRBs). The multi-dimensional samples consisting of data corresponding to the statistical and physical quantities from the coherent search pipeline are fed into the artificial neural network to distinguish simulated gravitational-wave signals from background noise artifacts. Our result shows that the data classification efficiency at a fixed false alarm probability (FAP) is improved by the artificial neural network in comparison to the conventional detection statistic. Specifically, the distance at 50% detection probability at a fixed false positive rate is increased about 8%-14% for the considered waveform models. We also evaluate a few seconds of the gravitational-wave data segment using the trained networks and obtain the FAP. We suggest that the artificial neural network can be a complementary method to the conventional detection statistic for identifying gravitational-wave signals related to the short GRBs.

A Fast Variational Approach for Learning Markov Random Field Language Models

DTIC Science & Technology

2015-01-01

the same distribution as n- gram models, but utilize a non-linear neural network pa- rameterization. NLMs have been shown to produce com- petitive...to either resort to local optimiza- tion methods, such as those used in neural lan- guage models, or work with heavily constrained distributions. In...embeddings learned through neural language models. Central to the language modelling problem is the challenge Proceedings of the 32nd International

Deep learning classification in asteroseismology

NASA Astrophysics Data System (ADS)

Hon, Marc; Stello, Dennis; Yu, Jie

2017-08-01

In the power spectra of oscillating red giants, there are visually distinct features defining stars ascending the red giant branch from those that have commenced helium core burning. We train a 1D convolutional neural network by supervised learning to automatically learn these visual features from images of folded oscillation spectra. By training and testing on Kepler red giants, we achieve an accuracy of up to 99 per cent in separating helium-burning red giants from those ascending the red giant branch. The convolutional neural network additionally shows capability in accurately predicting the evolutionary states of 5379 previously unclassified Kepler red giants, by which we now have greatly increased the number of classified stars.