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

Science.gov (United States)

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

2013-09-01

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

Boltzmann learning of parameters in cellular neural networks

DEFF Research Database (Denmark)

Hansen, Lars Kai

1992-01-01

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

Finite time convergent learning law for continuous neural networks.

Science.gov (United States)

Chairez, Isaac

2014-02-01

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

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

Science.gov (United States)

Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi

2017-01-01

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

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

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

2012-01-01

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

Biologically-inspired Learning in Pulsed Neural Networks

DEFF Research Database (Denmark)

Lehmann, Torsten; Woodburn, Robin

1999-01-01

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

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

Science.gov (United States)

Ponulak, Filip; Kasinski, Andrzej

2011-01-01

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

Learning and forgetting on asymmetric, diluted neural networks

International Nuclear Information System (INIS)

Derrida, B.; Nadal, J.P.

1987-01-01

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

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

Science.gov (United States)

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

2018-02-01

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

Learning in neural networks based on a generalized fluctuation theorem

Science.gov (United States)

Hayakawa, Takashi; Aoyagi, Toshio

2015-11-01

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

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

International Nuclear Information System (INIS)

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

2008-01-01

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

Continuous Online Sequence Learning with an Unsupervised Neural Network Model.

Science.gov (United States)

Cui, Yuwei; Ahmad, Subutar; Hawkins, Jeff

2016-09-14

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

Neural Networks

International Nuclear Information System (INIS)

Smith, Patrick I.

2003-01-01

Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

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

DEFF Research Database (Denmark)

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

2010-01-01

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

Deep learning classification in asteroseismology using an improved neural network

DEFF Research Database (Denmark)

Hon, Marc; Stello, Dennis; Yu, Jie

2018-01-01

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

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

Science.gov (United States)

Peng, Yefei

2010-01-01

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

Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

Czech Academy of Sciences Publication Activity Database

Neruda, Roman; Vidnerová, Petra

2009-01-01

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

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

Science.gov (United States)

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

2016-12-01

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

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

Directory of Open Access Journals (Sweden)

Md. Abdullah-al-mamun

2015-08-01

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

Introduction to neural networks

International Nuclear Information System (INIS)

Pavlopoulos, P.

1996-01-01

This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix

Nuclear power plant monitoring using real-time learning neural network

International Nuclear Information System (INIS)

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

1994-01-01

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

Chaotic diagonal recurrent neural network

International Nuclear Information System (INIS)

Wang Xing-Yuan; Zhang Yi

2012-01-01

We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)

Neural networks for aircraft control

Science.gov (United States)

Linse, Dennis

1990-01-01

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

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

Science.gov (United States)

Mills, Kyle; Tamblyn, Isaac

2018-03-01

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

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

DEFF Research Database (Denmark)

Lüders, Benno; Schläger, Mikkel; Korach, Aleksandra

2017-01-01

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

Prototype-Incorporated Emotional Neural Network.

Science.gov (United States)

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

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

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

Science.gov (United States)

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

2017-04-10

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

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

Science.gov (United States)

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

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

A learning algorithm for oscillatory cellular neural networks.

Science.gov (United States)

Ho, C Y.; Kurokawa, H

1999-07-01

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

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

NARCIS (Netherlands)

van den Dries, Sjoerd; Wiering, Marco A.

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

A stochastic learning algorithm for layered neural networks

International Nuclear Information System (INIS)

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

1992-01-01

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

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

Science.gov (United States)

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

2017-12-01

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

Biologically-inspired On-chip Learning in Pulsed Neural Networks

DEFF Research Database (Denmark)

Lehmann, Torsten; Woodburn, Robin

1999-01-01

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

Breast Cancer Diagnosis using Artificial Neural Networks with Extreme Learning Techniques

OpenAIRE

Chandra Prasetyo Utomo; Aan Kardiana; Rika Yuliwulandari

2014-01-01

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

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

Directory of Open Access Journals (Sweden)

OMER MAHMOUD

2007-08-01

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

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

Directory of Open Access Journals (Sweden)

Paul Tonelli

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

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

Science.gov (United States)

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

1993-01-01

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

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

International Nuclear Information System (INIS)

Sauget, M.

2007-12-01

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

Learning in Neural Networks: VLSI Implementation Strategies

Science.gov (United States)

Duong, Tuan Anh

1995-01-01

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

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

Science.gov (United States)

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

2010-05-01

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

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

OpenAIRE

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

2017-01-01

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

Neural Network Machine Learning and Dimension Reduction for Data Visualization

Science.gov (United States)

Liles, Charles A.

2014-01-01

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

Single-Iteration Learning Algorithm for Feed-Forward Neural Networks

Energy Technology Data Exchange (ETDEWEB)

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

1999-07-31

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

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

International Nuclear Information System (INIS)

Haggag, S.S.M.Y

2008-01-01

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

Self-teaching neural network learns difficult reactor control problem

International Nuclear Information System (INIS)

Jouse, W.C.

1989-01-01

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

Stochastic sensitivity analysis and Langevin simulation for neural network learning

International Nuclear Information System (INIS)

Koda, Masato

1997-01-01

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

Learning Orthographic Structure With Sequential Generative Neural Networks.

Science.gov (United States)

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

2016-04-01

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

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

Science.gov (United States)

Williams-Hayes, Peggy S.

2004-01-01

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

Neural network regulation driven by autonomous neural firings

Science.gov (United States)

Cho, Myoung Won

2016-07-01

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

Using machine learning, neural networks and statistics to predict bankruptcy

NARCIS (Netherlands)

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

1997-01-01

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

Competitive Learning Neural Network Ensemble Weighted by Predicted Performance

Science.gov (United States)

Ye, Qiang

2010-01-01

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

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

Science.gov (United States)

Simon, Solomon H.

1992-08-01

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

Neural networks and applications tutorial

Science.gov (United States)

Guyon, I.

1991-09-01

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

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

Science.gov (United States)

Carpenter, Gail A.

1997-11-01

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

Learning from neural control.

Science.gov (United States)

Wang, Cong; Hill, David J

2006-01-01

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

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

Science.gov (United States)

Kam, Hye Jin; Kim, Ha Young

2017-10-01

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

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

Science.gov (United States)

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

2015-12-01

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

Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS

Directory of Open Access Journals (Sweden)

Christopher Bergmeir

2012-01-01

Full Text Available Neural networks are important standard machine learning procedures for classification and regression. We describe the R package RSNNS that provides a convenient interface to the popular Stuttgart Neural Network Simulator SNNS. The main features are (a encapsulation of the relevant SNNS parts in a C++ class, for sequential and parallel usage of different networks, (b accessibility of all of the SNNSalgorithmic functionality from R using a low-level interface, and (c a high-level interface for convenient, R-style usage of many standard neural network procedures. The package also includes functions for visualization and analysis of the models and the training procedures, as well as functions for data input/output from/to the original SNNSfile formats.

Learning behavior and temporary minima of two-layer neural networks

NARCIS (Netherlands)

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

1994-01-01

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

Learning and Generalisation in Neural Networks with Local Preprocessing

OpenAIRE

Kutsia, Merab

2007-01-01

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

Neural network to diagnose lining condition

Science.gov (United States)

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.

Using Deep Learning Neural Networks To Find Best Performing Audience Segments

Directory of Open Access Journals (Sweden)

Anup Badhe

2015-08-01

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

A neural network model for credit risk evaluation.

Science.gov (United States)

Khashman, Adnan

2009-08-01

Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.

Program Helps Simulate Neural Networks

Science.gov (United States)

Villarreal, James; Mcintire, Gary

1993-01-01

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

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

Science.gov (United States)

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

2017-01-01

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

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

Science.gov (United States)

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

2018-05-10

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

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

Science.gov (United States)

Shimansky, Yury P

2009-12-01

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

Self-learning Monte Carlo with deep neural networks

Science.gov (United States)

Shen, Huitao; Liu, Junwei; Fu, Liang

2018-05-01

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

Noise-driven manifestation of learning in mature neural networks

International Nuclear Information System (INIS)

Monterola, Christopher; Saloma, Caesar

2002-01-01

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

Deep learning with convolutional neural network in radiology.

Science.gov (United States)

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

2018-04-01

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

Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks

OpenAIRE

Shen, Li; Lin, Zhouchen; Huang, Qingming

2015-01-01

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

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

Directory of Open Access Journals (Sweden)

Ryan Henderson

2017-09-01

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

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

Directory of Open Access Journals (Sweden)

Chih-Hong Kao

2011-01-01

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

Learning in Artificial Neural Systems

Science.gov (United States)

Matheus, Christopher J.; Hohensee, William E.

1987-01-01

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

Introduction to Concepts in Artificial Neural Networks

Science.gov (United States)

Niebur, Dagmar

1995-01-01

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

Learning, memory, and the role of neural network architecture.

Directory of Open Access Journals (Sweden)

Ann M Hermundstad

2011-06-01

Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

Fuzzy neural network theory and application

CERN Document Server

Liu, Puyin

2004-01-01

This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he

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

International Nuclear Information System (INIS)

Reifman, J.; Vitela, J.E.

1994-01-01

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

Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding.

Science.gov (United States)

Gardner, Brian; Grüning, André

2016-01-01

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

Neural network-based model reference adaptive control system.

Science.gov (United States)

Patino, H D; Liu, D

2000-01-01

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

Relabeling exchange method (REM) for learning in neural networks

Science.gov (United States)

Wu, Wen; Mammone, Richard J.

1994-02-01

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

Neural network recognition of mammographic lesions

International Nuclear Information System (INIS)

Oldham, W.J.B.; Downes, P.T.; Hunter, V.

1987-01-01

A method for recognition of mammographic lesions through the use of neural networks is presented. Neural networks have exhibited the ability to learn the shape andinternal structure of patterns. Digitized mammograms containing circumscribed and stelate lesions were used to train a feedfoward synchronous neural network that self-organizes to stable attractor states. Encoding of data for submission to the network was accomplished by performing a fractal analysis of the digitized image. This results in scale invariant representation of the lesions. Results are discussed

Outsmarting neural networks: an alternative paradigm for machine learning

Energy Technology Data Exchange (ETDEWEB)

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

1996-10-01

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

The interchangeability of learning rate and gain in backpropagation neural networks

NARCIS (Netherlands)

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

1996-01-01

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

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

Science.gov (United States)

Chrol-Cannon, Joseph; Jin, Yaochu

2014-11-01

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

Local Dynamics in Trained Recurrent Neural Networks.

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-23

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

Local Dynamics in Trained Recurrent Neural Networks

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-01

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

Ideomotor feedback control in a recurrent neural network.

Science.gov (United States)

Galtier, Mathieu

2015-06-01

The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show a promising performance of the approach, which can be turned into a local and better "biologically plausible" algorithm.

Boolean Factor Analysis by Attractor Neural Network

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.

2007-01-01

Roč. 18, č. 3 (2007), s. 698-707 ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007

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

OpenAIRE

Airola, Rasmus; Hager, Kristoffer

2017-01-01

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

Differential theory of learning for efficient neural network pattern recognition

Science.gov (United States)

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

1993-09-01

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

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

Science.gov (United States)

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

2018-02-01

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

Neural network error correction for solving coupled ordinary differential equations

Science.gov (United States)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

A study of reactor monitoring method with neural network

Energy Technology Data Exchange (ETDEWEB)

Nabeshima, Kunihiko [Japan Atomic Energy Research Inst., Tokai, Ibaraki (Japan). Tokai Research Establishment

2001-03-01

The purpose of this study is to investigate the methodology of Nuclear Power Plant (NPP) monitoring with neural networks, which create the plant models by the learning of the past normal operation patterns. The concept of this method is to detect the symptom of small anomalies by monitoring the deviations between the process signals measured from an actual plant and corresponding output signals from the neural network model, which might not be equal if the abnormal operational patterns are presented to the input of the neural network. Auto-associative network, which has same output as inputs, can detect an kind of anomaly condition by using normal operation data only. The monitoring tests of the feedforward neural network with adaptive learning were performed using the PWR plant simulator by which many kinds of anomaly conditions can be easily simulated. The adaptively trained feedforward network could follow the actual plant dynamics and the changes of plant condition, and then find most of the anomalies much earlier than the conventional alarm system during steady state and transient operations. Then the off-line and on-line test results during one year operation at the actual NPP (PWR) showed that the neural network could detect several small anomalies which the operators or the conventional alarm system didn't noticed. Furthermore, the sensitivity analysis suggests that the plant models by neural networks are appropriate. Finally, the simulation results show that the recurrent neural network with feedback connections could successfully model the slow behavior of the reactor dynamics without adaptive learning. Therefore, the recurrent neural network with adaptive learning will be the best choice for the actual reactor monitoring system. (author)

Markov Chain Monte Carlo Bayesian Learning for Neural Networks

Science.gov (United States)

Goodrich, Michael S.

2011-01-01

Conventional training methods for neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g., normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available data and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in network weights and therefore network predictions by using a modified Jeffery's prior combined with a Metropolis Markov Chain Monte Carlo method.

DCS-Neural-Network Program for Aircraft Control and Testing

Science.gov (United States)

Jorgensen, Charles C.

2006-01-01

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

A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.

Science.gov (United States)

Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa

2007-05-01

We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.

Neural network classifier of attacks in IP telephony

Science.gov (United States)

Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin

2014-05-01

Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.

Deep learning for steganalysis via convolutional neural networks

Science.gov (United States)

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

2015-03-01

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

SORN: a self-organizing recurrent neural network

Directory of Open Access Journals (Sweden)

Andreea Lazar

2009-10-01

Full Text Available Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain processes information. In the neocortex, a range of different plasticity mechanisms are shaping recurrent networks into effective information processing circuits that learn appropriate representations for time-varying sensory stimuli. However, it has been difficult to mimic these abilities in artificial neural network models. Here we introduce SORN, a self-organizing recurrent network. It combines three distinct forms of local plasticity to learn spatio-temporal patterns in its input while maintaining its dynamics in a healthy regime suitable for learning. The SORN learns to encode information in the form of trajectories through its high-dimensional state space reminiscent of recent biological findings on cortical coding. All three forms of plasticity are shown to be essential for the network's success.

Feature to prototype transition in neural networks

Science.gov (United States)

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.

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

Science.gov (United States)

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

2017-01-01

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

Genetic algorithm for neural networks optimization

Science.gov (United States)

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«.

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

Science.gov (United States)

Lee, Jun-Ki; Kwon, Yongju

2012-01-01

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

Supervised learning of probability distributions by neural networks

Science.gov (United States)

Baum, Eric B.; Wilczek, Frank

1988-01-01

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

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

Science.gov (United States)

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

2018-02-01

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

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

Science.gov (United States)

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

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

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

Science.gov (United States)

Giebel, S; Rainer, M

2010-01-01

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

Memory in Neural Networks and Glasses

NARCIS (Netherlands)

Heerema, M.

2000-01-01

The thesis tries and models a neural network in a way which, at essential points, is biologically realistic. In a biological context, the changes of the synapses of the neural network are most often described by what is called `Hebb's learning rule'. On careful analysis it is, in fact, nothing but a

Supervised learning in spiking neural networks with FORCE training.

Science.gov (United States)

Nicola, Wilten; Clopath, Claudia

2017-12-20

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

Issues in the use of neural networks in information retrieval

CERN Document Server

Iatan, Iuliana F

2017-01-01

This book highlights the ability of neural networks (NNs) to be excellent pattern matchers and their importance in information retrieval (IR), which is based on index term matching. The book defines a new NN-based method for learning image similarity and describes how to use fuzzy Gaussian neural networks to predict personality. It introduces the fuzzy Clifford Gaussian network, and two concurrent neural models: (1) concurrent fuzzy nonlinear perceptron modules, and (2) concurrent fuzzy Gaussian neural network modules. Furthermore, it explains the design of a new model of fuzzy nonlinear perceptron based on alpha level sets and describes a recurrent fuzzy neural network model with a learning algorithm based on the improved particle swarm optimization method.

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

Science.gov (United States)

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

2018-03-01

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

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

Science.gov (United States)

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).

Mode Choice Modeling Using Artificial Neural Networks

OpenAIRE

Edara, Praveen Kumar

2003-01-01

Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data becom...

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

DEFF Research Database (Denmark)

Bingel, Joachim; Søgaard, Anders

2017-01-01

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

An Introduction to Neural Networks for Hearing Aid Noise Recognition.

Science.gov (United States)

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…

Tensor Basis Neural Network v. 1.0 (beta)

Energy Technology Data Exchange (ETDEWEB)

2017-03-28

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

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

Directory of Open Access Journals (Sweden)

Alireza Alemi

2015-08-01

Full Text Available Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

Directory of Open Access Journals (Sweden)

Yoonsik Shim

2016-10-01

Full Text Available We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP. The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

Science.gov (United States)

Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

2016-10-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Statistical learning problem of artificial neural network to control roofing process

Directory of Open Access Journals (Sweden)

Lapidus Azariy

2017-01-01

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

Neural networks, nativism, and the plausibility of constructivism.

Science.gov (United States)

Quartz, S R

1993-09-01

Recent interest in PDP (parallel distributed processing) models is due in part to the widely held belief that they challenge many of the assumptions of classical cognitive science. In the domain of language acquisition, for example, there has been much interest in the claim that PDP models might undermine nativism. Related arguments based on PDP learning have also been given against Fodor's anti-constructivist position--a position that has contributed to the widespread dismissal of constructivism. A limitation of many of the claims regarding PDP learning, however, is that the principles underlying this learning have not been rigorously characterized. In this paper, I examine PDP models from within the framework of Valiant's PAC (probably approximately correct) model of learning, now the dominant model in machine learning, and which applies naturally to neural network learning. From this perspective, I evaluate the implications of PDP models for nativism and Fodor's influential anti-constructivist position. In particular, I demonstrate that, contrary to a number of claims, PDP models are nativist in a robust sense. I also demonstrate that PDP models actually serve as a good illustration of Fodor's anti-constructivist position. While these results may at first suggest that neural network models in general are incapable of the sort of concept acquisition that is required to refute Fodor's anti-constructivist position, I suggest that there is an alternative form of neural network learning that demonstrates the plausibility of constructivism. This alternative form of learning is a natural interpretation of the constructivist position in terms of neural network learning, as it employs learning algorithms that incorporate the addition of structure in addition to weight modification schemes. By demonstrating that there is a natural and plausible interpretation of constructivism in terms of neural network learning, the position that nativism is the only plausible model of

Neutron spectrometry and dosimetry by means of evolutive neural networks

International Nuclear Information System (INIS)

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

2008-01-01

The artificial neural networks and the genetic algorithms are two relatively new areas of research, which have been subject to a growing interest during the last years. Both models are inspired by the nature, however, the neural networks are interested in the learning of a single individual, which is defined as fenotypic learning, while the evolutionary algorithms are interested in the adaptation of a population to a changing environment, that which is defined as genotypic learning. Recently, the use of the technology of neural networks has been applied with success in the area of the nuclear sciences, mainly in the areas of neutron spectrometry and dosimetry. The structure (network topology), as well as the learning parameters of a neural network, are factors that contribute in a significant way with the acting of the same one, however, it has been observed that the investigators in this area, carry out the selection of the network parameters through the essay and error technique, that which produces neural networks of poor performance and low generalization capacity. From the revised sources, it has been observed that the use of the evolutionary algorithms, seen as search techniques, it has allowed him to be possible to evolve and to optimize different properties of the neural networks, just as the initialization of the synaptic weights, the network architecture or the training algorithms without the human intervention. The objective of the present work is focused in analyzing the intersection of the neural networks and the evolutionary algorithms, analyzing like it is that the same ones can be used to help in the design processes and training of a neural network, this is, in the good selection of the structural parameters and of network learning, improving its generalization capacity, in such way that the same one is able to reconstruct in an efficient way neutron spectra and to calculate equivalent doses starting from the counting rates of a Bonner sphere

Dynamic training algorithm for dynamic neural networks

International Nuclear Information System (INIS)

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

1996-01-01

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

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

CERN Document Server

Sundararajan, N; Wei Lu Ying

1999-01-01

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

Neural network based multiscale image restoration approach

Science.gov (United States)

de Castro, Ana Paula A.; da Silva, José D. S.

2007-02-01

This paper describes a neural network based multiscale image restoration approach. Multilayer perceptrons are trained with artificial images of degraded gray level circles, in an attempt to make the neural network learn inherent space relations of the degraded pixels. The present approach simulates the degradation by a low pass Gaussian filter blurring operation and the addition of noise to the pixels at pre-established rates. The training process considers the degraded image as input and the non-degraded image as output for the supervised learning process. The neural network thus performs an inverse operation by recovering a quasi non-degraded image in terms of least squared. The main difference of the approach to existing ones relies on the fact that the space relations are taken from different scales, thus providing relational space data to the neural network. The approach is an attempt to come up with a simple method that leads to an optimum solution to the problem. Considering different window sizes around a pixel simulates the multiscale operation. In the generalization phase the neural network is exposed to indoor, outdoor, and satellite degraded images following the same steps use for the artificial circle image.

Learning free energy landscapes using artificial neural networks.

Science.gov (United States)

Sidky, Hythem; Whitmer, Jonathan K

2018-03-14

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

Learning free energy landscapes using artificial neural networks

Science.gov (United States)

Sidky, Hythem; Whitmer, Jonathan K.

2018-03-01

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

Hybrid computing using a neural network with dynamic external memory.

Science.gov (United States)

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

2016-10-27

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

Generation of artificial accelerograms using neural networks for data of Iran

International Nuclear Information System (INIS)

Bargi, Kh.; Loux, C.; Rohani, H.

2002-01-01

A new method for generation of artificial earthquake accelerograms from response spectra is proposed by Ghaboussi and Lin in 1997 using neural networks. In this paper the methodology has been extended and enhanced for data of Iran. For this purpose, first 40 records of Iran acceleration is chosen, then an RBF neural network which called generalized regression neural network learn the inverse mapping directly from the response spectrum to the Discrete Cosine Transform of accelerograms. Discrete Cosine Transform has been used as an assisting device to extract the content of frequency domain. Learning of network is reasonable and a generalized regression neural network learns it in a few second. Outputs are presented to demonstrate the performance of this method and show its capabilities

A Neural Network-Based Interval Pattern Matcher

Directory of Open Access Journals (Sweden)

Jing Lu

2015-07-01

Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.

vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design

OpenAIRE

Rhu, Minsoo; Gimelshein, Natalia; Clemons, Jason; Zulfiqar, Arslan; Keckler, Stephen W.

2016-01-01

The most widely used machine learning frameworks require users to carefully tune their memory usage so that the deep neural network (DNN) fits into the DRAM capacity of a GPU. This restriction hampers a researcher's flexibility to study different machine learning algorithms, forcing them to either use a less desirable network architecture or parallelize the processing across multiple GPUs. We propose a runtime memory manager that virtualizes the memory usage of DNNs such that both GPU and CPU...

Neural network representation and learning of mappings and their derivatives

Science.gov (United States)

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

1991-01-01

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

Higher-order neural network software for distortion invariant object recognition

Science.gov (United States)

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.

PREDIKSI FOREX MENGGUNAKAN MODEL NEURAL NETWORK

Directory of Open Access Journals (Sweden)

R. Hadapiningradja Kusumodestoni

2015-11-01

Full Text Available ABSTRAK Prediksi adalah salah satu teknik yang paling penting dalam menjalankan bisnis forex. Keputusan dalam memprediksi adalah sangatlah penting, karena dengan prediksi dapat membantu mengetahui nilai forex di waktu tertentu kedepan sehingga dapat mengurangi resiko kerugian. Tujuan dari penelitian ini dimaksudkan memprediksi bisnis fores menggunakan model neural network dengan data time series per 1 menit untuk mengetahui nilai akurasi prediksi sehingga dapat mengurangi resiko dalam menjalankan bisnis forex. Metode penelitian pada penelitian ini meliputi metode pengumpulan data kemudian dilanjutkan ke metode training, learning, testing menggunakan neural network. Setelah di evaluasi hasil penelitian ini menunjukan bahwa penerapan algoritma Neural Network mampu untuk memprediksi forex dengan tingkat akurasi prediksi 0.431 +/- 0.096 sehingga dengan prediksi ini dapat membantu mengurangi resiko dalam menjalankan bisnis forex. Kata kunci: prediksi, forex, neural network.

Development of neural network simulating power distribution of a BWR fuel bundle

International Nuclear Information System (INIS)

Tanabe, A.; Yamamoto, T.; Shinfuku, K.; Nakamae, T.

1992-01-01

A neural network model is developed to simulate the precise nuclear physics analysis program code for quick scoping survey calculations. The relation between enrichment and local power distribution of BWR fuel bundles was learned using two layers neural network (ENET). A new model is to introduce burnable neutron absorber (Gadolinia), added to several fuel rods to decrease initial reactivity of fresh bundle. The 2nd stages three layers neural network (GNET) is added on the 1st stage network ENET. GNET studies the local distribution difference caused by Gadolinia. Using this method, it becomes possible to survey of the gradients of sigmoid functions and back propagation constants with reasonable time. Using 99 learning patterns of zero burnup, good error convergence curve is obtained after many trials. This neural network model is able to simulate no learned cases fairly as well as the learned cases. Computer time of this neural network model is about 100 times faster than a precise analysis model. (author)

Gradient Learning in Spiking Neural Networks by Dynamic Perturbation of Conductances

International Nuclear Information System (INIS)

Fiete, Ila R.; Seung, H. Sebastian

2006-01-01

We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic perturbation of the membrane conductances of the neurons. It is compatible with recurrent networks of conductance-based model neurons with dynamic synapses. The method can be interpreted as a biologically plausible synaptic learning rule, if the dynamic perturbations are generated by a special class of 'empiric' synapses driven by random spike trains from an external source

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

Science.gov (United States)

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

2008-12-01

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

Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks.

Science.gov (United States)

Walter, Florian; Röhrbein, Florian; Knoll, Alois

2015-12-01

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

Complex-valued neural networks advances and applications

CERN Document Server

Hirose, Akira

2013-01-01

Presents the latest advances in complex-valued neural networks by demonstrating the theory in a wide range of applications Complex-valued neural networks is a rapidly developing neural network framework that utilizes complex arithmetic, exhibiting specific characteristics in its learning, self-organizing, and processing dynamics. They are highly suitable for processing complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems to deal with electromagnetic, light, sonic/ultrasonic waves as well as quantum waves, namely, electron and

Two-Stage Approach to Image Classification by Deep Neural Networks

Science.gov (United States)

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.

A Neural Network Model to Learn Multiple Tasks under Dynamic Environments

Science.gov (United States)

Tsumori, Kenji; Ozawa, Seiichi

When environments are dynamically changed for agents, the knowledge acquired in an environment might be useless in future. In such dynamic environments, agents should be able to not only acquire new knowledge but also modify old knowledge in learning. However, modifying all knowledge acquired before is not efficient because the knowledge once acquired may be useful again when similar environment reappears and some knowledge can be shared among different environments. To learn efficiently in such environments, we propose a neural network model that consists of the following modules: resource allocating network, long-term & short-term memory, and environment change detector. We evaluate the model under a class of dynamic environments where multiple function approximation tasks are sequentially given. The experimental results demonstrate that the proposed model possesses stable incremental learning, accurate environmental change detection, proper association and recall of old knowledge, and efficient knowledge transfer.

Artificial neural network based approach to transmission lines protection

International Nuclear Information System (INIS)

Joorabian, M.

1999-05-01

The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection

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

Directory of Open Access Journals (Sweden)

Christoph Hartmann

2015-12-01

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

Classification of behavior using unsupervised temporal neural networks

International Nuclear Information System (INIS)

Adair, K.L.

1998-03-01

Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem

Neural networks. A new analytical tool, applicable also in nuclear technology

International Nuclear Information System (INIS)

Stritar, A.

1992-01-01

The basic concept of neural networks and back propagation learning algorithm are described. The behaviour of typical neural network is demonstrated on a simple graphical case. A short literature survey about the application of neural networks in nuclear science and engineering is made. The application of the neural network to the probability density calculation is shown. (author) [sl

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

Directory of Open Access Journals (Sweden)

Vuković Najdan L.

2014-01-01

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

Neural Networks

Directory of Open Access Journals (Sweden)

Schwindling Jerome

2010-04-01

Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.

How synapses can enhance sensibility of a neural network

Science.gov (United States)

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.

Convolutional neural network with transfer learning for rice type classification

Science.gov (United States)

Patel, Vaibhav Amit; Joshi, Manjunath V.

2018-04-01

Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

Convolutional Neural Network for Image Recognition

CERN Document Server

Seifnashri, Sahand

2015-01-01

The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

TRIGA control rod position and reactivity transient Monitoring by Neural Networks

International Nuclear Information System (INIS)

Rosa, R.; Palomba, M.; Sepielli, M.

2008-01-01

Plant sensors drift or malfunction and operator actions in nuclear reactor control can be supported by sensor on-line monitoring, and data validation through soft-computing process. On-line recalibration can often avoid manual calibration or drifting component replacement. DSP requires prompt response to the modified conditions. Artificial Neural Network (ANN) and Fuzzy logic ensure: prompt response, link with field measurement and physical system behaviour, data incoming interpretation, and detection of discrepancy for mis-calibration or sensor faults. ANN (Artificial Neural Network) is a system based on the operation of biological neural networks. Although computing is day by day advancing, there are certain tasks that a program made for a common microprocessor is unable to perform. A software implementation of an ANN can be made with Pros and Cons. Pros: A neural network can perform tasks that a linear program can not; When an element of the neural network fails, it can continue without any problem by their parallel nature; A neural network learns and does not need to be reprogrammed; It can be implemented in any application; It can be implemented without any problem. Cons: The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated; it requires high processing time for large neural networks; and the neural network needs training to operate. Three possibilities of training exist: Supervised learning: the network is trained providing input and matching output patterns; Unsupervised learning: input patterns are not a priori classified and the system must develop its own representation of the input stimuli; Reinforcement Learning: intermediate form of the above two types of learning, the learning machine does some action on the environment and gets a feedback response from the environment. Two TRIGAN ANN applications are considered: control rod position and fuel temperature. The outcome obtained in this

A fuzzy Hopfield neural network for medical image segmentation

International Nuclear Information System (INIS)

Lin, J.S.; Cheng, K.S.; Mao, C.W.

1996-01-01

In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learning and parallel implementation for medical image segmentation are feasible. The idea is to cast a clustering problem as a minimization problem where the criteria for the optimum segmentation is chosen as the minimization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering strategy is included in the Hopfield neural network to eliminate the need of finding weighting factors in the energy function, which is formulated and based on a basic concept commonly used in pattern classification, called the within-class scatter matrix principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfield neural network. The fuzzy Hopfield neural network based on the within-class scatter matrix shows the promising results in comparison with the hard c-means method

Identification of generalized state transfer matrix using neural networks

International Nuclear Information System (INIS)

Zhu Changchun

2001-01-01

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

Learning text representation using recurrent convolutional neural network with highway layers

OpenAIRE

Wen, Ying; Zhang, Weinan; Luo, Rui; Wang, Jun

2016-01-01

Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers. The highway network module is incorporated in the middle takes the output of the bi-directional Recurrent Neural Network (Bi-RNN) module in the first stage and provides the Convolutional Neural Network (CNN) module in the last stage with the i...

A Quantum Implementation Model for Artificial Neural Networks

OpenAIRE

Ammar Daskin

2018-01-01

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

Shaping the learning curve: epigenetic dynamics in neural plasticity

Directory of Open Access Journals (Sweden)

Zohar Ziv Bronfman

2014-07-01

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

Growing adaptive machines combining development and learning in artificial neural networks

CERN Document Server

Bredeche, Nicolas; Doursat, René

2014-01-01

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

Neural networks within multi-core optic fibers.

Science.gov (United States)

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.

International Conference on Artificial Neural Networks (ICANN)

CERN Document Server

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

2015-01-01

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

Do Convolutional Neural Networks Learn Class Hierarchy?

Science.gov (United States)

Bilal, Alsallakh; Jourabloo, Amin; Ye, Mao; Liu, Xiaoming; Ren, Liu

2018-01-01

Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.

Reinforcement Learning of Linking and Tracing Contours in Recurrent Neural Networks

Science.gov (United States)

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

2015-01-01

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

Identification of chaotic systems by neural network with hybrid learning algorithm

International Nuclear Information System (INIS)

Pan, S.-T.; Lai, C.-C.

2008-01-01

Based on the genetic algorithm (GA) and steepest descent method (SDM), this paper proposes a hybrid algorithm for the learning of neural networks to identify chaotic systems. The systems in question are the logistic map and the Duffing equation. Different identification schemes are used to identify both the logistic map and the Duffing equation, respectively. Simulation results show that our hybrid algorithm is more efficient than that of other methods

q-state Potts-glass neural network based on pseudoinverse rule

International Nuclear Information System (INIS)

Xiong Daxing; Zhao Hong

2010-01-01

We study the q-state Potts-glass neural network with the pseudoinverse (PI) rule. Its performance is investigated and compared with that of the counterpart network with the Hebbian rule instead. We find that there exists a critical point of q, i.e., q cr =14, below which the storage capacity and the retrieval quality can be greatly improved by introducing the PI rule. We show that the dynamics of the neural networks constructed with the two learning rules respectively are quite different; but however, regardless of the learning rules, in the q-state Potts-glass neural networks with q≥3 there is a common novel dynamical phase in which the spurious memories are completely suppressed. This property has never been noticed in the symmetric feedback neural networks. Free from the spurious memories implies that the multistate Potts-glass neural networks would not be trapped in the metastable states, which is a favorable property for their applications.

Neural Behavior Chain Learning of Mobile Robot Actions

Directory of Open Access Journals (Sweden)

Lejla Banjanovic-Mehmedovic

2012-01-01

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

Potential usefulness of an artificial neural network for assessing ventricular size

International Nuclear Information System (INIS)

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

1995-01-01

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

Two-Stage Approach to Image Classification by Deep Neural Networks

Directory of Open Access Journals (Sweden)

Ososkov Gennady

2018-01-01

Full Text Available 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 modularity helps organisms evolve to learn new skills without forgetting old skills.

Science.gov (United States)

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

2015-04-01

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

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

Directory of Open Access Journals (Sweden)

Kai Olav Ellefsen

2015-04-01

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

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

Science.gov (United States)

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

2015-01-01

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

A Quantum Implementation Model for Artificial Neural Networks

OpenAIRE

Daskin, Ammar

2016-01-01

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

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

Science.gov (United States)

Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro

1995-02-01

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

A Quantum Implementation Model for Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Ammar Daskin

2018-02-01

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

Using neural networks in software repositories

Science.gov (United States)

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.

Bio-inspired spiking neural network for nonlinear systems control.

Science.gov (United States)

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.

Intelligent neural network diagnostic system

International Nuclear Information System (INIS)

Mohamed, A.H.

2010-01-01

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

Improved Extension Neural Network and Its Applications

Directory of Open Access Journals (Sweden)

Yu Zhou

2014-01-01

Full Text Available Extension neural network (ENN is a new neural network that is a combination of extension theory and artificial neural network (ANN. The learning algorithm of ENN is based on supervised learning algorithm. One of important issues in the field of classification and recognition of ENN is how to achieve the best possible classifier with a small number of labeled training data. Training data selection is an effective approach to solve this issue. In this work, in order to improve the supervised learning performance and expand the engineering application range of ENN, we use a novel data selection method based on shadowed sets to refine the training data set of ENN. Firstly, we use clustering algorithm to label the data and induce shadowed sets. Then, in the framework of shadowed sets, the samples located around each cluster centers (core data and the borders between clusters (boundary data are selected as training data. Lastly, we use selected data to train ENN. Compared with traditional ENN, the proposed improved ENN (IENN has a better performance. Moreover, IENN is independent of the supervised learning algorithms and initial labeled data. Experimental results verify the effectiveness and applicability of our proposed work.

A fuzzy neural network for sensor signal estimation

International Nuclear Information System (INIS)

Na, Man Gyun

2000-01-01

In this work, a fuzzy neural network is used to estimate the relevant sensor signal using other sensor signals. Noise components in input signals into the fuzzy neural network are removed through the wavelet denoising technique. Principal component analysis (PCA) is used to reduce the dimension of an input space without losing a significant amount of information. A lower dimensional input space will also usually reduce the time necessary to train a fuzzy-neural network. Also, the principal component analysis makes easy the selection of the input signals into the fuzzy neural network. The fuzzy neural network parameters are optimized by two learning methods. A genetic algorithm is used to optimize the antecedent parameters of the fuzzy neural network and a least-squares algorithm is used to solve the consequent parameters. The proposed algorithm was verified through the application to the pressurizer water level and the hot-leg flowrate measurements in pressurized water reactors

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

Science.gov (United States)

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

2017-08-01

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

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

Directory of Open Access Journals (Sweden)

M. Njah

2017-06-01

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

Introduction to neural networks with electric power applications

International Nuclear Information System (INIS)

Wildberger, A.M.; Hickok, K.A.

1990-01-01

This is an introduction to the general field of neural networks with emphasis on prospects for their application in the power industry. It is intended to provide enough background information for its audience to begin to follow technical developments in neural networks and to recognize those which might impact on electric power engineering. Beginning with a brief discussion of natural and artificial neurons, the characteristics of neural networks in general and how they learn, neural networks are compared with other modeling tools such as simulation and expert systems in order to provide guidance in selecting appropriate applications. In the power industry, possible applications include plant control, dispatching, and maintenance scheduling. In particular, neural networks are currently being investigated for enhancements to the Thermal Performance Advisor (TPA) which General Physics Corporation (GP) has developed to improve the efficiency of electric power generation

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

Science.gov (United States)

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Development and application of deep convolutional neural network in target detection

Science.gov (United States)

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.

Genetic learning in rule-based and neural systems

Science.gov (United States)

Smith, Robert E.

1993-01-01

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

Applying neural networks to control the TFTR neutral beam ion sources

International Nuclear Information System (INIS)

Lagin, L.

1992-01-01

This paper describes the application of neural networks to the control of the neutral beam long-pulse positive ion source accelerators on the Tokamak Fusion Test Reactor (TFTR) at Princeton University. Neural networks were used to learn how the operators adjust the control setpoints when running these sources. The data sets used to train these networks were derived from a large database containing actual setpoints and power supply waveform calculations for the 1990 run period. The networks learned what the optimum control setpoints should initially be set based uon desired accel voltage and perveance levels. Neural networks were also used to predict the divergence of the ion beam

Diagnostic Classifiers: Revealing how Neural Networks Process Hierarchical Structure

NARCIS (Netherlands)

Veldhoen, S.; Hupkes, D.; Zuidema, W.

2016-01-01

We investigate how neural networks can be used for hierarchical, compositional semantics. To this end, we define the simple but nontrivial artificial task of processing nested arithmetic expressions and study whether different types of neural networks can learn to add and subtract. We find that

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

International Nuclear Information System (INIS)

Proriol, J.

1994-01-01

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

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

Science.gov (United States)

Li, Siqi; Jiang, Huiyan; Pang, Wenbo

2017-05-01

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

Modeling and control of magnetorheological fluid dampers using neural networks

Science.gov (United States)

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

2005-02-01

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

Functional model of biological neural networks.

Science.gov (United States)

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.

Quantum neural networks: Current status and prospects for development

Science.gov (United States)

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

2014-11-01

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

Nuclear power plant monitoring method by neural network and its application to actual nuclear reactor

International Nuclear Information System (INIS)

Nabeshima, Kunihiko; Suzuki, Katsuo; Shinohara, Yoshikuni; Tuerkcan, E.

1995-11-01

In this paper, the anomaly detection method for nuclear power plant monitoring and its program are described by using a neural network approach, which is based on the deviation between measured signals and output signals of neural network model. The neural network used in this study has three layered auto-associative network with 12 input/output, and backpropagation algorithm is adopted for learning. Furthermore, to obtain better dynamical model of the reactor plant, a new learning technique was developed in which the learning process of the present neural network is divided into initial and adaptive learning modes. The test results at the actual nuclear reactor shows that the neural network plant monitoring system is successfull in detecting in real-time the symptom of small anomaly over a wide power range including reactor start-up, shut-down and stationary operation. (author)

Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition

OpenAIRE

Zhang, Zewang; Sun, Zheng; Liu, Jiaqi; Chen, Jingwen; Huo, Zhao; Zhang, Xiao

2016-01-01

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, we build a novel deep recurrent convolutional network for acoustic modeling and then apply deep resid...

Morphological neural networks

Energy Technology Data Exchange (ETDEWEB)

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

1996-12-31

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

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

Science.gov (United States)

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

2017-01-01

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

Representation of neutron noise data using neural networks

International Nuclear Information System (INIS)

Korsah, K.; Damiano, B.; Wood, R.T.

1992-01-01

This paper describes a neural network-based method of representing neutron noise spectra using a model developed at the Oak Ridge National Laboratory (ORNL). The backpropagation neural network learned to represent neutron noise data in terms of four descriptors, and the network response matched calculated values to within 3.5 percent. These preliminary results are encouraging, and further research is directed towards the application of neural networks in a diagnostics system for the identification of the causes of changes in structural spectral resonances. This work is part of our current investigation of advanced technologies such as expert systems and neural networks for neutron noise data reduction, analysis, and interpretation. The objective is to improve the state-of-the-art of noise analysis as a diagnostic tool for nuclear power plants and other mechanical systems

Identification-based chaos control via backstepping design using self-organizing fuzzy neural networks

International Nuclear Information System (INIS)

Peng Yafu; Hsu, C.-F.

2009-01-01

This paper proposes an identification-based adaptive backstepping control (IABC) for the chaotic systems. The IABC system is comprised of a neural backstepping controller and a robust compensation controller. The neural backstepping controller containing a self-organizing fuzzy neural network (SOFNN) identifier is the principal controller, and the robust compensation controller is designed to dispel the effect of minimum approximation error introduced by the SOFNN identifier. The SOFNN identifier is used to online estimate the chaotic dynamic function with structure and parameter learning phases of fuzzy neural network. The structure learning phase consists of the growing and pruning of fuzzy rules; thus the SOFNN identifier can avoid the time-consuming trial-and-error tuning procedure for determining the neural structure of fuzzy neural network. The parameter learning phase adjusts the interconnection weights of neural network to achieve favorable approximation performance. Finally, simulation results verify that the proposed IABC can achieve favorable tracking performance.

Neural Networks for Modeling and Control of Particle Accelerators

Science.gov (United States)

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.

Application of neural network to CT

International Nuclear Information System (INIS)

Ma, Xiao-Feng; Takeda, Tatsuoki

1999-01-01

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

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

Science.gov (United States)

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Using neural networks to describe tracer correlations

Directory of Open Access Journals (Sweden)

D. J. Lary

2004-01-01

Full Text Available 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 methane 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 coefficient between simulated and training values 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.

A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

DEFF Research Database (Denmark)

Sturm, Bob L.; Kereliuk, Corey; Pikrakis, Aggelos

2014-01-01

Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look...

Artificial Neural Networks and Instructional Technology.

Science.gov (United States)

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…

Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise.

Science.gov (United States)

Vuković, Najdan; Miljković, Zoran

2015-03-01

Feedforward neural networks (FFNN) are among the most used neural networks for modeling of various nonlinear problems in engineering. In sequential and especially real time processing all neural networks models fail when faced with outliers. Outliers are found across a wide range of engineering problems. Recent research results in the field have shown that to avoid overfitting or divergence of the model, new approach is needed especially if FFNN is to run sequentially or in real time. To accommodate limitations of FFNN when training data contains a certain number of outliers, this paper presents new learning algorithm based on improvement of conventional extended Kalman filter (EKF). Extended Kalman filter robust to outliers (EKF-OR) is probabilistic generative model in which measurement noise covariance is not constant; the sequence of noise measurement covariance is modeled as stochastic process over the set of symmetric positive-definite matrices in which prior is modeled as inverse Wishart distribution. In each iteration EKF-OR simultaneously estimates noise estimates and current best estimate of FFNN parameters. Bayesian framework enables one to mathematically derive expressions, while analytical intractability of the Bayes' update step is solved by using structured variational approximation. All mathematical expressions in the paper are derived using the first principles. Extensive experimental study shows that FFNN trained with developed learning algorithm, achieves low prediction error and good generalization quality regardless of outliers' presence in training data. Copyright © 2014 Elsevier Ltd. All rights reserved.

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

Science.gov (United States)

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.

Optoelectronic Implementation of Neural Networks

Indian Academy of Sciences (India)

neural networks, such as learning, adapting and copying by means of parallel ... to provide robust recognition of hand-printed English text. Engine idle and misfiring .... and s represents the bounded activation function of a neuron. It is typically ...

Improved transformer protection using probabilistic neural network ...

African Journals Online (AJOL)

user

secure and dependable protection for power transformers. Owing to its superior learning and generalization capabilities Artificial. Neural Network (ANN) can considerably enhance the scope of WI method. ANN approach is faster, robust and easier to implement than the conventional waveform approach. The use of neural ...

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

Science.gov (United States)

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

NEURAL NETWORKS FOR STOCK MARKET OPTION PRICING

Directory of Open Access Journals (Sweden)

Sergey A. Sannikov

2017-03-01

Full Text Available Introduction: The use of neural networks for non-linear models helps to understand where linear model drawbacks, coused by their specification, reveal themselves. This paper attempts to find this out. The objective of research is to determine the meaning of “option prices calculation using neural networks”. Materials and Methods: We use two kinds of variables: endogenous (variables included in the model of neural network and variables affecting on the model (permanent disturbance. Results: All data are divided into 3 sets: learning, affirming and testing. All selected variables are normalised from 0 to 1. Extreme values of income were shortcut. Discussion and Conclusions: Using the 33-14-1 neural network with direct links we obtained two sets of forecasts. Optimal criteria of strategies in stock markets’ option pricing were developed.

A TLD dose algorithm using artificial neural networks

International Nuclear Information System (INIS)

Moscovitch, M.; Rotunda, J.E.; Tawil, R.A.; Rathbone, B.A.

1995-01-01

An artificial neural network was designed and used to develop a dose algorithm for a multi-element thermoluminescence dosimeter (TLD). The neural network architecture is based on the concept of functional links network (FLN). Neural network is an information processing method inspired by the biological nervous system. A dose algorithm based on neural networks is fundamentally different as compared to conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with given responses of a multi-element dosimeter (input) many times. The algorithm, being trained that way, eventually is capable to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personal dosimetry, the output consists of the desired dose components: deep dose, shallow dose and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. The neural network approach was applied to the Harshaw Type 8825 TLD, and was shown to significantly improve the performance of this dosimeter, well within the U.S. accreditation requirements for personnel dosimeters

Deformable image registration using convolutional neural networks

NARCIS (Netherlands)

Eppenhof, Koen A.J.; Lafarge, Maxime W.; Moeskops, Pim; Veta, Mitko; Pluim, Josien P.W.

2018-01-01

Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between

Nonequilibrium landscape theory of neural networks

Science.gov (United States)

Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

2013-01-01

The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape–flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments. PMID:24145451

Nonequilibrium landscape theory of neural networks.

Science.gov (United States)

Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

2013-11-05

The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.

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

Science.gov (United States)

Orhan, A Emin; Ma, Wei Ji

2017-07-26

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

Chaotic Hopfield Neural Network Swarm Optimization and Its Application

Directory of Open Access Journals (Sweden)

Yanxia Sun

2013-01-01

Full Text Available A new neural network based optimization algorithm is proposed. The presented model is a discrete-time, continuous-state Hopfield neural network and the states of the model are updated synchronously. The proposed algorithm combines the advantages of traditional PSO, chaos and Hopfield neural networks: particles learn from their own experience and the experiences of surrounding particles, their search behavior is ergodic, and convergence of the swarm is guaranteed. The effectiveness of the proposed approach is demonstrated using simulations and typical optimization problems.

Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control.

Science.gov (United States)

Pan, Yongping; Yu, Haoyong

2017-06-01

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

Foreign currency rate forecasting using neural networks

Science.gov (United States)

Pandya, Abhijit S.; Kondo, Tadashi; Talati, Amit; Jayadevappa, Suryaprasad

2000-03-01

Neural networks are increasingly being used as a forecasting tool in many forecasting problems. This paper discusses the application of neural networks in predicting daily foreign exchange rates between the USD, GBP as well as DEM. We approach the problem from a time-series analysis framework - where future exchange rates are forecasted solely using past exchange rates. This relies on the belief that the past prices and future prices are very close related, and interdependent. We present the result of training a neural network with historical USD-GBP data. The methodology used in explained, as well as the training process. We discuss the selection of inputs to the network, and present a comparison of using the actual exchange rates and the exchange rate differences as inputs. Price and rate differences are the preferred way of training neural network in financial applications. Results of both approaches are present together for comparison. We show that the network is able to learn the trends in the exchange rate movements correctly, and present the results of the prediction over several periods of time.

Neural networks in signal processing

International Nuclear Information System (INIS)

Govil, R.

2000-01-01

Nuclear Engineering has matured during the last decade. In research and design, control, supervision, maintenance and production, mathematical models and theories are used extensively. In all such applications signal processing is embedded in the process. Artificial Neural Networks (ANN), because of their nonlinear, adaptive nature are well suited to such applications where the classical assumptions of linearity and second order Gaussian noise statistics cannot be made. ANN's can be treated as nonparametric techniques, which can model an underlying process from example data. They can also adopt their model parameters to statistical change with time. Algorithms in the framework of Neural Networks in Signal processing have found new applications potentials in the field of Nuclear Engineering. This paper reviews the fundamentals of Neural Networks in signal processing and their applications in tasks such as recognition/identification and control. The topics covered include dynamic modeling, model based ANN's, statistical learning, eigen structure based processing and generalization structures. (orig.)

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

Science.gov (United States)

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

2017-01-13

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

White blood cells identification system based on convolutional deep neural learning networks.

Science.gov (United States)

Shahin, A I; Guo, Yanhui; Amin, K M; Sharawi, Amr A

2017-11-16

White blood cells (WBCs) differential counting yields valued information about human health and disease. The current developed automated cell morphology equipments perform differential count which is based on blood smear image analysis. Previous identification systems for WBCs consist of successive dependent stages; pre-processing, segmentation, feature extraction, feature selection, and classification. There is a real need to employ deep learning methodologies so that the performance of previous WBCs identification systems can be increased. Classifying small limited datasets through deep learning systems is a major challenge and should be investigated. In this paper, we propose a novel identification system for WBCs based on deep convolutional neural networks. Two methodologies based on transfer learning are followed: transfer learning based on deep activation features and fine-tuning of existed deep networks. Deep acrivation featues are extracted from several pre-trained networks and employed in a traditional identification system. Moreover, a novel end-to-end convolutional deep architecture called "WBCsNet" is proposed and built from scratch. Finally, a limited balanced WBCs dataset classification is performed through the WBCsNet as a pre-trained network. During our experiments, three different public WBCs datasets (2551 images) have been used which contain 5 healthy WBCs types. The overall system accuracy achieved by the proposed WBCsNet is (96.1%) which is more than different transfer learning approaches or even the previous traditional identification system. We also present features visualization for the WBCsNet activation which reflects higher response than the pre-trained activated one. a novel WBCs identification system based on deep learning theory is proposed and a high performance WBCsNet can be employed as a pre-trained network. Copyright © 2017. Published by Elsevier B.V.

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

Science.gov (United States)

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

2015-01-01

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

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

OpenAIRE

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

2017-01-01

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

Rotation Invariance Neural Network

OpenAIRE

Li, Shiyuan

2017-01-01

Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in 2-D symbol recognition. We can also get the position and orientation of the 2-D symbol by the network to achieve detection purpose for multiple non-overlap target. Last but not least, this architecture can achieve one-shot learning in some cases using thos...

Different propagation speeds of recalled sequences in plastic spiking neural networks

Science.gov (United States)

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

Predicting carbonate permeabilities from wireline logs using a back-propagation neural network

International Nuclear Information System (INIS)

Wiener, J.M.; Moll, R.F.; Rogers, J.A.

1991-01-01

This paper explores the applicability of using Neural Networks to aid in the determination of carbonate permeability from wireline logs. Resistivity, interval transit time, neutron porosity, and bulk density logs form Texaco's Stockyard Creek Oil field were used as input to a specially designed neural network to predict core permeabilities in this carbonate reservoir. Also of interest was the comparison of the neural network's results to those of standard statistical techniques. The process of developing the neural network for this problem has shown that a good understanding of the data is required when creating the training set from which the network learns. This network was trained to learn core permeabilities from raw and transformed log data using a hyperbolic tangent transfer function and a sum of squares global error function. Also, it required two hidden layers to solve this particular problem

Neural networks involved in learning lexical-semantic and syntactic information in a second language.

Science.gov (United States)

Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

2014-01-01

The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

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

Directory of Open Access Journals (Sweden)

Arie Rachmad Syulistyo

2016-02-01

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

Beneficial role of noise in artificial neural networks

International Nuclear Information System (INIS)

Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin

2008-01-01

We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated

Evolving Neural Turing Machines for Reward-based Learning

DEFF Research Database (Denmark)

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

2016-01-01

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

Construction of Neural Networks for Realization of Localized Deep Learning

Directory of Open Access Journals (Sweden)

Charles K. Chui

2018-05-01

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

Transfer Learning with Convolutional Neural Networks for SAR Ship Recognition

Science.gov (United States)

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

2018-03-01

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

Biosignals learning and synthesis using deep neural networks.

Science.gov (United States)

Belo, David; Rodrigues, João; Vaz, João R; Pezarat-Correia, Pedro; Gamboa, Hugo

2017-09-25

Modeling physiological signals is a complex task both for understanding and synthesize biomedical signals. We propose a deep neural network model that learns and synthesizes biosignals, validated by the morphological equivalence of the original ones. This research could lead the creation of novel algorithms for signal reconstruction in heavily noisy data and source detection in biomedical engineering field. The present work explores the gated recurrent units (GRU) employed in the training of respiration (RESP), electromyograms (EMG) and electrocardiograms (ECG). Each signal is pre-processed, segmented and quantized in a specific number of classes, corresponding to the amplitude of each sample and fed to the model, which is composed by an embedded matrix, three GRU blocks and a softmax function. This network is trained by adjusting its internal parameters, acquiring the representation of the abstract notion of the next value based on the previous ones. The simulated signal was generated by forecasting a random value and re-feeding itself. The resulting generated signals are similar with the morphological expression of the originals. During the learning process, after a set of iterations, the model starts to grasp the basic morphological characteristics of the signal and later their cyclic characteristics. After training, these models' prediction are closer to the signals that trained them, specially the RESP and ECG. This synthesis mechanism has shown relevant results that inspire the use to characterize signals from other physiological sources.

Temporal neural networks and transient analysis of complex engineering systems

Science.gov (United States)

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.

Recurrent Neural Network Based Boolean Factor Analysis and its Application to Word Clustering

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Polyakov, P.Y.

2009-01-01

Roč. 20, č. 7 (2009), s. 1073-1086 ISSN 1045-9227 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.889, year: 2009

Investigation of efficient features for image recognition by neural networks.

Science.gov (United States)

Goltsev, Alexander; Gritsenko, Vladimir

2012-04-01

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

Genetic optimization of neural network architecture

International Nuclear Information System (INIS)

Harp, S.A.; Samad, T.

1994-03-01

Neural networks are now a popular technology for a broad variety of application domains, including the electric utility industry. Yet, as the technology continues to gain increasing acceptance, it is also increasingly apparent that the power that neural networks provide is not an unconditional blessing. Considerable care must be exercised during application development if the full benefit of the technology is to be realized. At present, no fully general theory or methodology for neural network design is available, and application development is a trial-and-error process that is time-consuming and expertise-intensive. Each application demands appropriate selections of the network input space, the network structure, and values of learning algorithm parameters-design choices that are closely coupled in ways that largely remain a mystery. This EPRI-funded exploratory research project was initiated to take the key next step in this research program: the validation of the approach on a realistic problem. We focused on the problem of modeling the thermal performance of the TVA Sequoyah nuclear power plant (units 1 and 2)

Neural PID Control Strategy for Networked Process Control

Directory of Open Access Journals (Sweden)

Jianhua Zhang

2013-01-01

Full Text Available A new method with a two-layer hierarchy is presented based on a neural proportional-integral-derivative (PID iterative learning method over the communication network for the closed-loop automatic tuning of a PID controller. It can enhance the performance of the well-known simple PID feedback control loop in the local field when real networked process control applied to systems with uncertain factors, such as external disturbance or randomly delayed measurements. The proposed PID iterative learning method is implemented by backpropagation neural networks whose weights are updated via minimizing tracking error entropy of closed-loop systems. The convergence in the mean square sense is analysed for closed-loop networked control systems. To demonstrate the potential applications of the proposed strategies, a pressure-tank experiment is provided to show the usefulness and effectiveness of the proposed design method in network process control systems.

Advanced approach to numerical forecasting using artificial neural networks

Directory of Open Access Journals (Sweden)

Michael Štencl

2009-01-01

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

Artificial Neural Networks and the Mass Appraisal of Real Estate

Directory of Open Access Journals (Sweden)

Gang Zhou

2018-03-01

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

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

Science.gov (United States)

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.

Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function

Science.gov (United States)

Rodríguez-Quiñonez, J. C.; Sergiyenko, O.; Hernandez-Balbuena, D.; Rivas-Lopez, M.; Flores-Fuentes, W.; Basaca-Preciado, L. C.

2014-12-01

Many laser scanners depend on their mechanical construction to guarantee their measurements accuracy, however, the current computational technologies allow us to improve these measurements by mathematical methods implemented in neural networks. In this article we are going to introduce the current laser scanner technologies, give a description of our 3D laser scanner and adjust their measurement error by a previously trained feed forward back propagation (FFBP) neural network with a Widrow-Hoff weight/bias learning function. A comparative analysis with other learning functions such as the Kohonen algorithm and gradient descendent with momentum algorithm is presented. Finally, computational simulations are conducted to verify the performance and method uncertainty in the proposed system.

Some Issues of the Paradigm of Multi-learning Machine - Modular Neural Networks

DEFF Research Database (Denmark)

Wang, Pan; Feng, Shuai; Fan, Zhun

2009-01-01

This paper addresses some issues on the weighted linear integration of modular neural networks (MNN: a paradigm of hybrid multi-learning machines). First, from the general meaning of variable weights and variable elements synthesis, three basic kinds of integrated models are discussed...... a general form while the corresponding computational algorithms are described briefly. The authors present a new training algorithm of sub-networks named “'Expert in one thing and good at many' (EOGM).” In this algorithm, every sub-network is trained on a primary dataset with some of its near neighbors...... as the accessorial datasets. Simulated results with a kind of dynamic integration methods show the effectiveness of these algorithms, where the performance of the algorithm with EOGM is better than that of the algorithm with a common training method....

Neural networks. A new analytical tool, applicable also in nuclear technology

Energy Technology Data Exchange (ETDEWEB)

Stritar, A [Inst. Jozef Stefan, Ljubljana (Slovenia)

1992-07-01

The basic concept of neural networks and back propagation learning algorithm are described. The behaviour of typical neural network is demonstrated on a simple graphical case. A short literature survey about the application of neural networks in nuclear science and engineering is made. The application of the neural network to the probability density calculation is shown. (author) [Slovenian] Opisana je osnova nevronskih mrez in back propagation nacina njihovega ucenja. Obnasanje enostavne nevronske mreze je prikazano na graficnem primeru. Podan je kratek pregled literaure o uporabi nevronskih mrez v jedrski znanosti in tehnologiji. Prikazana je tudi uporaba nevronske mreze pri izracunu verjetnostne porazdelitve. (author)

Face recognition via Gabor and convolutional neural network

Science.gov (United States)

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.

Quantitative phase microscopy using deep neural networks

Science.gov (United States)

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.

A Tsallis’ statistics based neural network model for novel word learning

Science.gov (United States)

Hadzibeganovic, Tarik; Cannas, Sergio A.

2009-03-01

We invoke the Tsallis entropy formalism, a nonextensive entropy measure, to include some degree of non-locality in a neural network that is used for simulation of novel word learning in adults. A generalization of the gradient descent dynamics, realized via nonextensive cost functions, is used as a learning rule in a simple perceptron. The model is first investigated for general properties, and then tested against the empirical data, gathered from simple memorization experiments involving two populations of linguistically different subjects. Numerical solutions of the model equations corresponded to the measured performance states of human learners. In particular, we found that the memorization tasks were executed with rather small but population-specific amounts of nonextensivity, quantified by the entropic index q. Our findings raise the possibility of using entropic nonextensivity as a means of characterizing the degree of complexity of learning in both natural and artificial systems.

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

Science.gov (United States)

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.

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

Directory of Open Access Journals (Sweden)

Waddah Waheeb

Full Text Available 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.

Phylogenetic convolutional neural networks in metagenomics.

Science.gov (United States)

Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

2018-03-08

Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

Performance of artificial neural networks and genetical evolved artificial neural networks unfolding techniques

International Nuclear Information System (INIS)

Ortiz R, J. M.; Martinez B, M. R.; Vega C, H. R.; Gallego D, E.; Lorente F, A.; Mendez V, R.; Los Arcos M, J. M.; Guerrero A, J. E.

2011-01-01

With the Bonner spheres spectrometer neutron spectrum is obtained through an unfolding procedure. Monte Carlo methods, Regularization, Parametrization, Least-squares, and Maximum Entropy are some of the techniques utilized for unfolding. In the last decade methods based on Artificial Intelligence Technology have been used. Approaches based on Genetic Algorithms and Artificial Neural Networks (Ann) have been developed in order to overcome the drawbacks of previous techniques. Nevertheless the advantages of Ann still it has some drawbacks mainly in the design process of the network, vg the optimum selection of the architectural and learning Ann parameters. In recent years the use of hybrid technologies, combining Ann and genetic algorithms, has been utilized to. In this work, several Ann topologies were trained and tested using Ann and Genetically Evolved Artificial Neural Networks in the aim to unfold neutron spectra using the count rates of a Bonner sphere spectrometer. Here, a comparative study of both procedures has been carried out. (Author)

Classifying images using restricted Boltzmann machines and convolutional neural networks

Science.gov (United States)

Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

2017-07-01

To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

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

Science.gov (United States)

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.

Optimal neural networks for protein-structure prediction

International Nuclear Information System (INIS)

Head-Gordon, T.; Stillinger, F.H.

1993-01-01

The successful application of neural-network algorithms for prediction of protein structure is stymied by three problem areas: the sparsity of the database of known protein structures, poorly devised network architectures which make the input-output mapping opaque, and a global optimization problem in the multiple-minima space of the network variables. We present a simplified polypeptide model residing in two dimensions with only two amino-acid types, A and B, which allows the determination of the global energy structure for all possible sequences of pentamer, hexamer, and heptamer lengths. This model simplicity allows us to compile a complete structural database and to devise neural networks that reproduce the tertiary structure of all sequences with absolute accuracy and with the smallest number of network variables. These optimal networks reveal that the three problem areas are convoluted, but that thoughtful network designs can actually deconvolute these detrimental traits to provide network algorithms that genuinely impact on the ability of the network to generalize or learn the desired mappings. Furthermore, the two-dimensional polypeptide model shows sufficient chemical complexity so that transfer of neural-network technology to more realistic three-dimensional proteins is evident

Adaptive Control of Nonlinear Discrete-Time Systems by Using OS-ELM Neural Networks

Directory of Open Access Journals (Sweden)

Xiao-Li Li

2014-01-01

Full Text Available As a kind of novel feedforward neural network with single hidden layer, ELM (extreme learning machine neural networks are studied for the identification and control of nonlinear dynamic systems. The property of simple structure and fast convergence of ELM can be shown clearly. In this paper, we are interested in adaptive control of nonlinear dynamic plants by using OS-ELM (online sequential extreme learning machine neural networks. Based on data scope division, the problem that training process of ELM neural network is sensitive to the initial training data is also solved. According to the output range of the controlled plant, the data corresponding to this range will be used to initialize ELM. Furthermore, due to the drawback of conventional adaptive control, when the OS-ELM neural network is used for adaptive control of the system with jumping parameters, the topological structure of the neural network can be adjusted dynamically by using multiple model switching strategy, and an MMAC (multiple model adaptive control will be used to improve the control performance. Simulation results are included to complement the theoretical results.

Stable architectures for deep neural networks

Science.gov (United States)

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.

Image Encryption and Chaotic Cellular Neural Network

Science.gov (United States)

Peng, Jun; Zhang, Du

Machine learning has been playing an increasingly important role in information security and assurance. One of the areas of new applications is to design cryptographic systems by using chaotic neural network due to the fact that chaotic systems have several appealing features for information security applications. In this chapter, we describe a novel image encryption algorithm that is based on a chaotic cellular neural network. We start by giving an introduction to the concept of image encryption and its main technologies, and an overview of the chaotic cellular neural network. We then discuss the proposed image encryption algorithm in details, which is followed by a number of security analyses (key space analysis, sensitivity analysis, information entropy analysis and statistical analysis). The comparison with the most recently reported chaos-based image encryption algorithms indicates that the algorithm proposed in this chapter has a better security performance. Finally, we conclude the chapter with possible future work and application prospects of the chaotic cellular neural network in other information assurance and security areas.

EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks.

Science.gov (United States)

Xia, Peng; Hu, Jie; Peng, Yinghong

2017-10-25

A novel model based on deep learning is proposed to estimate kinematic information for myoelectric control from multi-channel electromyogram (EMG) signals. The neural information of limb movement is embedded in EMG signals that are influenced by all kinds of factors. In order to overcome the negative effects of variability in signals, the proposed model employs the deep architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The EMG signals are transformed to time-frequency frames as the input to the model. The limb movement is estimated by the model that is trained with the gradient descent and backpropagation procedure. We tested the model for simultaneous and proportional estimation of limb movement in eight healthy subjects and compared it with support vector regression (SVR) and CNNs on the same data set. The experimental studies show that the proposed model has higher estimation accuracy and better robustness with respect to time. The combination of CNNs and RNNs can improve the model performance compared with using CNNs alone. The model of deep architecture is promising in EMG decoding and optimization of network structures can increase the accuracy and robustness. © 2017 International Center for Artificial Organs and Transplantation and Wiley Periodicals, Inc.

Research on Fault Diagnosis Method Based on Rule Base Neural Network

Directory of Open Access Journals (Sweden)

Zheng Ni

2017-01-01

Full Text Available The relationship between fault phenomenon and fault cause is always nonlinear, which influences the accuracy of fault location. And neural network is effective in dealing with nonlinear problem. In order to improve the efficiency of uncertain fault diagnosis based on neural network, a neural network fault diagnosis method based on rule base is put forward. At first, the structure of BP neural network is built and the learning rule is given. Then, the rule base is built by fuzzy theory. An improved fuzzy neural construction model is designed, in which the calculated methods of node function and membership function are also given. Simulation results confirm the effectiveness of this method.

Evaluating the Visualization of What a Deep Neural Network Has Learned.

Science.gov (United States)

Samek, Wojciech; Binder, Alexander; Montavon, Gregoire; Lapuschkin, Sebastian; Muller, Klaus-Robert

Deep neural networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multilayer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision, given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and interpret the reasoning embodied in a DNN for a single test image. These methods quantify the "importance" of individual pixels with respect to the classification decision and allow a visualization in terms of a heatmap in pixel/input space. While the usefulness of heatmaps can be judged subjectively by a human, an objective quality measure is missing. In this paper, we present a general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps. We compare heatmaps computed by three different methods on the SUN397, ILSVRC2012, and MIT Places data sets. Our main result is that the recently proposed layer-wise relevance propagation algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method. We provide theoretical arguments to explain this result and discuss its practical implications. Finally, we investigate the use of heatmaps for unsupervised assessment of the neural network performance.Deep neural networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multilayer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision, given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and

Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations

OpenAIRE

Harradon, Michael; Druce, Jeff; Ruttenberg, Brian

2018-01-01

Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop methods to extract salient concepts throughout a target network by using autoencoders trained to extract human-understandable representations of network activations. We then bu...

Forex Market Prediction Using NARX Neural Network with Bagging

Directory of Open Access Journals (Sweden)

Shahbazi Nima

2016-01-01

Full Text Available We propose a new methodfor predicting movements in Forex market based on NARX neural network withtime shifting bagging techniqueand financial indicators, such as relative strength index and stochastic indicators. Neural networks have prominent learning ability but they often exhibit bad and unpredictable performance for noisy data. When compared with the static neural networks, our method significantly reducesthe error rate of the responseandimproves the performance of the prediction. We tested three different types ofarchitecture for predicting the response and determined the best network approach. We applied our method to prediction the hourly foreign exchange rates and found remarkable predictability in comprehensive experiments with 2 different foreign exchange rates (GBPUSD and EURUSD.

Advances in neural networks computational and theoretical issues

CERN Document Server

Esposito, Anna; Morabito, Francesco

2015-01-01

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

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

Science.gov (United States)

Tanohata, Naoki; Seki, Hirokazu

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

Analysis of the experimental positron lifetime spectra by neural networks

International Nuclear Information System (INIS)

Avdic, S.; Chakarova, R.; Pazsit, I.

2003-01-01

This paper deals with the analysis of experimental positron lifetime spectra in polymer materials by using various algorithms of neural networks. A method based on the use of artificial neural networks for unfolding the mean lifetime and intensity of the spectral components of simulated positron lifetime spectra was previously suggested and tested on simulated data [Pazsit et al., Applied Surface Science, 149 (1998), 97]. In this work, the applicability of the method to the analysis of experimental positron spectra has been verified in the case of spectra from polymer materials with three components. It has been demonstrated that the backpropagation neural network can determine the spectral parameters with a high accuracy and perform the decomposition of lifetimes which differ by 10% or more. The backpropagation network has not been suitable for the identification of both the parameters and the number of spectral components. Therefore, a separate artificial neural network module has been designed to solve the classification problem. Module types based on self-organizing map and learning vector quantization algorithms have been tested. The learning vector quantization algorithm was found to have better performance and reliability. A complete artificial neural network analysis tool of positron lifetime spectra has been constructed to include a spectra classification module and parameter evaluation modules for spectra with a different number of components. In this way, both flexibility and high resolution can be achieved. (author)

New backpropagation algorithm with type-2 fuzzy weights for neural networks

CERN Document Server

Gaxiola, Fernando; Valdez, Fevrier

2016-01-01

In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris bi...

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

Science.gov (United States)

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

2010-01-01

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

Do neural nets learn statistical laws behind natural language?

Directory of Open Access Journals (Sweden)

Shuntaro Takahashi

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

Implementation of neural networks on 'Connection Machine'

International Nuclear Information System (INIS)

Belmonte, Ghislain

1990-12-01

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

Neural network application to diesel generator diagnostics

International Nuclear Information System (INIS)

Logan, K.P.

1990-01-01

Diagnostic problems typically begin with the observation of some system behavior which is recognized as a deviation from the expected. The fundamental underlying process is one involving pattern matching cf observed symptoms to a set of compiled symptoms belonging to a fault-symptom mapping. Pattern recognition is often relied upon for initial fault detection and diagnosis. Parallel distributed processing (PDP) models employing neural network paradigms are known to be good pattern recognition devices. This paper describes the application of neural network processing techniques to the malfunction diagnosis of subsystems within a typical diesel generator configuration. Neural network models employing backpropagation learning were developed to correctly recognize fault conditions from the input diagnostic symptom patterns pertaining to various engine subsystems. The resulting network models proved to be excellent pattern recognizers for malfunction examples within the training set. The motivation for employing network models in lieu of a rule-based expert system, however, is related to the network's potential for generalizing malfunctions outside of the training set, as in the case of noisy or partial symptom patterns

Deep Neural Network-Based Chinese Semantic Role Labeling

Institute of Scientific and Technical Information of China (English)

ZHENG Xiaoqing; CHEN Jun; SHANG Guoqiang

2017-01-01

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

Neural network training by Kalman filtering in process system monitoring

International Nuclear Information System (INIS)

Ciftcioglu, Oe.

1996-03-01

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

Neural networks

International Nuclear Information System (INIS)

Denby, Bruce; Lindsey, Clark; Lyons, Louis

1992-01-01

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

Neural Network with Local Memory for Nuclear Reactor Power Level Control

International Nuclear Information System (INIS)

Uluyol, Oender; Ragheb, Magdi; Tsoukalas, Lefteri

2001-01-01

A methodology is introduced for a neural network with local memory called a multilayered local output gamma feedback (LOGF) neural network within the paradigm of locally-recurrent globally-feedforward neural networks. It appears to be well-suited for the identification, prediction, and control tasks in highly dynamic systems; it allows for the presentation of different timescales through incorporation of a gamma memory. A learning algorithm based on the backpropagation-through-time approach is derived. The spatial and temporal weights of the network are iteratively optimized for a given problem using the derived learning algorithm. As a demonstration of the methodology, it is applied to the task of power level control of a nuclear reactor at different fuel cycle conditions. The results demonstrate that the LOGF neural network controller outperforms the classical as well as the state feedback-assisted classical controllers for reactor power level control by showing a better tracking of the demand power, improving the fuel and exit temperature responses, and by performing robustly in different fuel cycle and power level conditions

Application of a neural network for reflectance spectrum classification

Science.gov (United States)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

A Telescopic Binary Learning Machine for Training Neural Networks.

Science.gov (United States)

Brunato, Mauro; Battiti, Roberto

2017-03-01

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

Liquefaction Microzonation of Babol City Using Artificial Neural Network

DEFF Research Database (Denmark)

Farrokhzad, F.; Choobbasti, A.J.; Barari, Amin

2012-01-01

that will be less susceptible to damage during earthquakes. The scope of present study is to prepare the liquefaction microzonation map for the Babol city based on Seed and Idriss (1983) method using artificial neural network. Artificial neural network (ANN) is one of the artificial intelligence (AI) approaches...... microzonation map is produced for research area. Based on the obtained results, it can be stated that the trained neural network is capable in prediction of liquefaction potential with an acceptable level of confidence. At the end, zoning of the city is carried out based on the prediction of liquefaction...... that can be classified as machine learning. Simplified methods have been practiced by researchers to assess nonlinear liquefaction potential of soil. In order to address the collective knowledge built-up in conventional liquefaction engineering, an alternative general regression neural network model...

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

NARCIS (Netherlands)

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

1992-01-01

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

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

OpenAIRE

Madahar, Abhinav; Ma, Yuze; Patel, Kunal

2017-01-01

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

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

Science.gov (United States)

Biswas, Surama; Acharyya, Sriyankar

2016-06-01

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

DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural Networks.

Science.gov (United States)

Kim, Lok-Won

2018-05-01

Although there have been many decades of research and commercial presence on high performance general purpose processors, there are still many applications that require fully customized hardware architectures for further computational acceleration. Recently, deep learning has been successfully used to learn in a wide variety of applications, but their heavy computation demand has considerably limited their practical applications. This paper proposes a fully pipelined acceleration architecture to alleviate high computational demand of an artificial neural network (ANN) which is restricted Boltzmann machine (RBM) ANNs. The implemented RBM ANN accelerator (integrating network size, using 128 input cases per batch, and running at a 303-MHz clock frequency) integrated in a state-of-the art field-programmable gate array (FPGA) (Xilinx Virtex 7 XC7V-2000T) provides a computational performance of 301-billion connection-updates-per-second and about 193 times higher performance than a software solution running on general purpose processors. Most importantly, the architecture enables over 4 times (12 times in batch learning) higher performance compared with a previous work when both are implemented in an FPGA device (XC2VP70).

Determining the confidence levels of sensor outputs using neural networks

Energy Technology Data Exchange (ETDEWEB)

Broten, G S; Wood, H C [Saskatchewan Univ., Saskatoon, SK (Canada). Dept. of Electrical Engineering

1996-12-31

This paper describes an approach for determining the confidence level of a sensor output using multi-sensor arrays, sensor fusion and artificial neural networks. The authors have shown in previous work that sensor fusion and artificial neural networks can be used to learn the relationships between the outputs of an array of simulated partially selective sensors and the individual analyte concentrations in a mixture of analyses. Other researchers have shown that an array of partially selective sensors can be used to determine the individual gas concentrations in a gaseous mixture. The research reported in this paper shows that it is possible to extract confidence level information from an array of partially selective sensors using artificial neural networks. The confidence level of a sensor output is defined as a numeric value, ranging from 0% to 100%, that indicates the confidence associated with a output of a given sensor. A three layer back-propagation neural network was trained on a subset of the sensor confidence level space, and was tested for its ability to generalize, where the confidence level space is defined as all possible deviations from the correct sensor output. A learning rate of 0.1 was used and no momentum terms were used in the neural network. This research has shown that an artificial neural network can accurately estimate the confidence level of individual sensors in an array of partially selective sensors. This research has also shown that the neural network`s ability to determine the confidence level is influenced by the complexity of the sensor`s response and that the neural network is able to estimate the confidence levels even if more than one sensor is in error. The fundamentals behind this research could be applied to other configurations besides arrays of partially selective sensors, such as an array of sensors separated spatially. An example of such a configuration could be an array of temperature sensors in a tank that is not in

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

Science.gov (United States)

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.

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

Science.gov (United States)

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.

Neural network based approach for tuning of SNS feedback and feedforward controllers

International Nuclear Information System (INIS)

Kwon, Sung-Il; Prokop, Mark S.; Regan, Amy H.

2002-01-01

The primary controllers in the SNS low level RF system are proportional-integral (PI) feedback controllers. To obtain the best performance of the linac control systems, approximately 91 individual PI controller gains should be optimally tuned. Tuning is time consuming and requires automation. In this paper, a neural network is used for the controller gain tuning. A neural network can approximate any continuous mapping through learning. In a sense, the cavity loop PI controller is a continuous mapping of the tracking error and its one-sample-delay inputs to the controller output. Also, monotonic cavity output with respect to its input makes knowing the detailed parameters of the cavity unnecessary. Hence the PI controller is a prime candidate for approximation through a neural network. Using mean square error minimization to train the neural network along with a continuous mapping of appropriate weights, optimally tuned PI controller gains can be determined. The same neural network approximation property is also applied to enhance the adaptive feedforward controller performance. This is done by adjusting the feedforward controller gains, forgetting factor, and learning ratio. Lastly, the automation of the tuning procedure data measurement, neural network training, tuning and loading the controller gain to the DSP is addressed.

Fundamental study of interpretation technique for 3-D magnetotelluric data using neural networks; Neural network wo mochiita sanjigen MT ho data kaishaku gijutsu no kisoteki kenkyu

Energy Technology Data Exchange (ETDEWEB)

Kobayashi, T; Fukuoka, K; Shima, H [Oyo Corp., Tokyo (Japan); Mogi, T [Kyushu University, Fukuoka (Japan). Faculty of Engineering; Spichak, V

1997-05-27

The research and development have been conducted to apply neural networks to interpretation technique for 3-D MT data. In this study, a data base of various data was made from the numerical modeling of 3-D fault model, and the data base management system was constructed. In addition, an unsupervised neural network for treating noise and a supervised neural network for estimating fault parameters such as dip, strike and specific resistance were made, and a basic neural network system was constructed. As a result of the application to the various data, basically sufficient performance for estimating the fault parameters was confirmed. Thus, the optimum MT data for this system were selected. In future, it is necessary to investigate the optimum model and the number of models for learning these neural networks. 3 refs., 5 figs., 2 tabs.

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

Science.gov (United States)

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.

Stability and synchronization control of stochastic neural networks

CERN Document Server

Zhou, Wuneng; Zhou, Liuwei; Tong, Dongbing

2016-01-01

This book reports on the latest findings in the study of Stochastic Neural Networks (SNN). The book collects the novel model of the disturbance driven by Levy process, the research method of M-matrix, and the adaptive control method of the SNN in the context of stability and synchronization control. The book will be of interest to university researchers, graduate students in control science and engineering and neural networks who wish to learn the core principles, methods, algorithms and applications of SNN.

Prediction of proteasome cleavage motifs by neural networks

DEFF Research Database (Denmark)

Kesimir, C.; Nussbaum, A.K.; Schild, H.

2002-01-01

physiological conditions. Our algorithm has been trained not only on in vitro data, but also on MHC Class I ligand data, which reflect a combination of immunoproteasome and constitutive proteasome specificity. This feature, together with the use of neural networks, a non-linear classification technique, make...... the prediction of MHC Class I ligand boundaries more accurate: 65% of the cleavage sites and 85% of the non-cleavage sites are correctly determined. Moreover, we show that the neural networks trained on the constitutive proteasome data learns a specificity that differs from that of the networks trained on MHC...

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

Science.gov (United States)

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.

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

Science.gov (United States)

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

2016-04-01

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

An H(∞) control approach to robust learning of feedforward neural networks.

Science.gov (United States)

Jing, Xingjian

2011-09-01

A novel H(∞) robust control approach is proposed in this study to deal with the learning problems of feedforward neural networks (FNNs). The analysis and design of a desired weight update law for the FNN is transformed into a robust controller design problem for a discrete dynamic system in terms of the estimation error. The drawbacks of some existing learning algorithms can therefore be revealed, especially for the case that the output data is fast changing with respect to the input or the output data is corrupted by noise. Based on this approach, the optimal learning parameters can be found by utilizing the linear matrix inequality (LMI) optimization techniques to achieve a predefined H(∞) "noise" attenuation level. Several existing BP-type algorithms are shown to be special cases of the new H(∞)-learning algorithm. Theoretical analysis and several examples are provided to show the advantages of the new method. Copyright © 2011 Elsevier Ltd. All rights reserved.

Associative memory in an analog iterated-map neural network

Science.gov (United States)

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.

Artificial neural networks, a new alternative to Monte Carlo calculations for radiotherapy

International Nuclear Information System (INIS)

Martin, E.; Gschwind, R.; Henriet, J.; Sauget, M.; Makovicka, L.

2010-01-01

In order to reduce the computing time needed by Monte Carlo codes in the field of irradiation physics, notably in dosimetry, the authors report the use of artificial neural networks in combination with preliminary Monte Carlo calculations. During the learning phase, Monte Carlo calculations are performed in homogeneous media to allow the building up of the neural network. Then, dosimetric calculations (in heterogeneous media, unknown by the network) can be performed by the so-learned network. Results with an equivalent precision can be obtained within less than one minute on a simple PC whereas several days are needed with a Monte Carlo calculation

Transformation-invariant visual representations in self-organizing spiking neural networks.

Science.gov (United States)

Evans, Benjamin D; Stringer, Simon M

2012-01-01

The ventral visual pathway achieves object and face recognition by building transformation-invariant representations from elementary visual features. In previous computer simulation studies with rate-coded neural networks, the development of transformation-invariant representations has been demonstrated using either of two biologically plausible learning mechanisms, Trace learning and Continuous Transformation (CT) learning. However, it has not previously been investigated how transformation-invariant representations may be learned in a more biologically accurate spiking neural network. A key issue is how the synaptic connection strengths in such a spiking network might self-organize through Spike-Time Dependent Plasticity (STDP) where the change in synaptic strength is dependent on the relative times of the spikes emitted by the presynaptic and postsynaptic neurons rather than simply correlated activity driving changes in synaptic efficacy. Here we present simulations with conductance-based integrate-and-fire (IF) neurons using a STDP learning rule to address these gaps in our understanding. It is demonstrated that with the appropriate selection of model parameters and training regime, the spiking network model can utilize either Trace-like or CT-like learning mechanisms to achieve transform-invariant representations.

Transform-invariant visual representations in self-organizing spiking neural networks

Directory of Open Access Journals (Sweden)

Benjamin eEvans

2012-07-01

Full Text Available The ventral visual pathway achieves object and face recognition by building transform-invariant representations from elementary visual features. In previous computer simulation studies with rate-coded neural networks, the development of transform invariant representations has been demonstrated using either of two biologically plausible learning mechanisms, Trace learning and Continuous Transformation (CT learning. However, it has not previously been investigated how transform invariant representations may be learned in a more biologically accurate spiking neural network. A key issue is how the synaptic connection strengths in such a spiking network might self-organize through Spike-Time Dependent Plasticity (STDP where the change in synaptic strength is dependent on the relative times of the spikes emitted by the pre- and postsynaptic neurons rather than simply correlated activity driving changes in synaptic efficacy. Here we present simulations with conductance-based integrate-and-fire (IF neurons using a STDP learning rule to address these gaps in our understanding. It is demonstrated that with the appropriate selection of model pa- rameters and training regime, the spiking network model can utilize either Trace-like or CT-like learning mechanisms to achieve transform-invariant representations.

Daily rainfall-runoff modelling by neural networks in semi-arid zone ...

African Journals Online (AJOL)

This research work will allow checking efficiency of formal neural networks for flows' modelling of wadi Ouahrane's basin from rainfall-runoff relation which is non-linear. Two models of neural networks were optimized through supervised learning and compared in order to achieve this goal, the first model with input rain, and ...

Patterns recognition of electric brain activity using artificial neural networks

Science.gov (United States)

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

2017-04-01

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

Quantum Entanglement in Neural Network States

Directory of Open Access Journals (Sweden)

Dong-Ling Deng

2017-05-01

Full Text Available Machine learning, one of today’s most rapidly growing interdisciplinary fields, promises an unprecedented perspective for solving intricate quantum many-body problems. Understanding the physical aspects of the representative artificial neural-network states has recently become highly desirable in the applications of machine-learning techniques to quantum many-body physics. In this paper, we explore the data structures that encode the physical features in the network states by studying the quantum entanglement properties, with a focus on the restricted-Boltzmann-machine (RBM architecture. We prove that the entanglement entropy of all short-range RBM states satisfies an area law for arbitrary dimensions and bipartition geometry. For long-range RBM states, we show by using an exact construction that such states could exhibit volume-law entanglement, implying a notable capability of RBM in representing quantum states with massive entanglement. Strikingly, the neural-network representation for these states is remarkably efficient, in the sense that the number of nonzero parameters scales only linearly with the system size. We further examine the entanglement properties of generic RBM states by randomly sampling the weight parameters of the RBM. We find that their averaged entanglement entropy obeys volume-law scaling, and the meantime strongly deviates from the Page entropy of the completely random pure states. We show that their entanglement spectrum has no universal part associated with random matrix theory and bears a Poisson-type level statistics. Using reinforcement learning, we demonstrate that RBM is capable of finding the ground state (with power-law entanglement of a model Hamiltonian with a long-range interaction. In addition, we show, through a concrete example of the one-dimensional symmetry-protected topological cluster states, that the RBM representation may also be used as a tool to analytically compute the entanglement spectrum. Our

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

International Nuclear Information System (INIS)

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

2015-01-01

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

Energy Technology Data Exchange (ETDEWEB)

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin, E-mail: xmli@cqu.edu.cn [Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education, Chongqing University, Chongqing 400044 (China); College of Automation, Chongqing University, Chongqing 400044 (China)

2015-11-15

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.

Distributed Extreme Learning Machine for Nonlinear Learning over Network

Directory of Open Access Journals (Sweden)

Songyan Huang

2015-02-01

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

Adaptive Graph Convolutional Neural Networks

OpenAIRE

Li, Ruoyu; Wang, Sheng; Zhu, Feiyun; Huang, Junzhou

2018-01-01

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for eac...

Determining the confidence levels of sensor outputs using neural networks

International Nuclear Information System (INIS)

Broten, G.S.; Wood, H.C.

1995-01-01

This paper describes an approach for determining the confidence level of a sensor output using multi-sensor arrays, sensor fusion and artificial neural networks. The authors have shown in previous work that sensor fusion and artificial neural networks can be used to learn the relationships between the outputs of an array of simulated partially selective sensors and the individual analyte concentrations in a mixture of analyses. Other researchers have shown that an array of partially selective sensors can be used to determine the individual gas concentrations in a gaseous mixture. The research reported in this paper shows that it is possible to extract confidence level information from an array of partially selective sensors using artificial neural networks. The confidence level of a sensor output is defined as a numeric value, ranging from 0% to 100%, that indicates the confidence associated with a output of a given sensor. A three layer back-propagation neural network was trained on a subset of the sensor confidence level space, and was tested for its ability to generalize, where the confidence level space is defined as all possible deviations from the correct sensor output. A learning rate of 0.1 was used and no momentum terms were used in the neural network. This research has shown that an artificial neural network can accurately estimate the confidence level of individual sensors in an array of partially selective sensors. This research has also shown that the neural network's ability to determine the confidence level is influenced by the complexity of the sensor's response and that the neural network is able to estimate the confidence levels even if more than one sensor is in error. The fundamentals behind this research could be applied to other configurations besides arrays of partially selective sensors, such as an array of sensors separated spatially. An example of such a configuration could be an array of temperature sensors in a tank that is not in

A Model to Explain the Emergence of Reward Expectancy neurons using Reinforcement Learning and Neural Network

OpenAIRE

Shinya, Ishii; Munetaka, Shidara; Katsunari, Shibata

2006-01-01

In an experiment of multi-trial task to obtain a reward, reward expectancy neurons,###which responded only in the non-reward trials that are necessary to advance###toward the reward, have been observed in the anterior cingulate cortex of monkeys.###In this paper, to explain the emergence of the reward expectancy neuron in###terms of reinforcement learning theory, a model that consists of a recurrent neural###network trained based on reinforcement learning is proposed. The analysis of the###hi...

Convolutional Neural Networks - Generalizability and Interpretations

DEFF Research Database (Denmark)

Malmgren-Hansen, David

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

Parameter estimation using compensatory neural networks

Indian Academy of Sciences (India)

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

Polarity-specific high-level information propagation in neural networks.

Science.gov (United States)

Lin, Yen-Nan; Chang, Po-Yen; Hsiao, Pao-Yueh; Lo, Chung-Chuan

2014-01-01

Analyzing the connectome of a nervous system provides valuable information about the functions of its subsystems. Although much has been learned about the architectures of neural networks in various organisms by applying analytical tools developed for general networks, two distinct and functionally important properties of neural networks are often overlooked. First, neural networks are endowed with polarity at the circuit level: Information enters a neural network at input neurons, propagates through interneurons, and leaves via output neurons. Second, many functions of nervous systems are implemented by signal propagation through high-level pathways involving multiple and often recurrent connections rather than by the shortest paths between nodes. In the present study, we analyzed two neural networks: the somatic nervous system of Caenorhabditis elegans (C. elegans) and the partial central complex network of Drosophila, in light of these properties. Specifically, we quantified high-level propagation in the vertical and horizontal directions: the former characterizes how signals propagate from specific input nodes to specific output nodes and the latter characterizes how a signal from a specific input node is shared by all output nodes. We found that the two neural networks are characterized by very efficient vertical and horizontal propagation. In comparison, classic small-world networks show a trade-off between vertical and horizontal propagation; increasing the rewiring probability improves the efficiency of horizontal propagation but worsens the efficiency of vertical propagation. Our result provides insights into how the complex functions of natural neural networks may arise from a design that allows them to efficiently transform and combine input signals.

An interpretable LSTM neural network for autoregressive exogenous model

OpenAIRE

Guo, Tian; Lin, Tao; Lu, Yao

2018-01-01

In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, our multi-variable LSTM equipped with tensorized hidden states is developed to learn variable specific representations, which give rise to both temporal and variable lev...

Target recognition based on convolutional neural network

Science.gov (United States)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

Identifying Tracks Duplicates via Neural Network

CERN Document Server

Sunjerga, Antonio; CERN. Geneva. EP Department

2017-01-01

The goal of the project is to study feasibility of state of the art machine learning techniques in track reconstruction. Machine learning techniques provide promising ways to speed up the pattern recognition of tracks by adding more intelligence in the algorithms. Implementation of neural network to process of track duplicates identifying will be discussed. Different approaches are shown and results are compared to method that is currently in use.

A new source difference artificial neural network for enhanced positioning accuracy

International Nuclear Information System (INIS)

Bhatt, Deepak; Aggarwal, Priyanka; Devabhaktuni, Vijay; Bhattacharya, Prabir

2012-01-01

Integrated inertial navigation system (INS) and global positioning system (GPS) units provide reliable navigation solution compared to standalone INS or GPS. Traditional Kalman filter-based INS/GPS integration schemes have several inadequacies related to sensor error model and immunity to noise. Alternatively, multi-layer perceptron (MLP) neural networks with three layers have been implemented to improve the position accuracy of the integrated system. However, MLP neural networks show poor accuracy for low-cost INS because of the large inherent sensor errors. For the first time the paper demonstrates the use of knowledge-based source difference artificial neural network (SDANN) to improve navigation performance of low-cost sensor, with or without external aiding sources. Unlike the conventional MLP or artificial neural networks (ANN), the structure of SDANN consists of two MLP neural networks called the coarse model and the difference model. The coarse model learns the input–output data relationship whereas the difference model adds knowledge to the system and fine-tunes the coarse model output by learning the associated training or estimation error. Our proposed SDANN model illustrated a significant improvement in navigation accuracy of up to 81% over conventional MLP. The results demonstrate that the proposed SDANN method is effective for GPS/INS integration schemes using low-cost inertial sensors, with and without GPS

Decomposition of Rotor Hopfield Neural Networks Using Complex Numbers.

Science.gov (United States)

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.

Predicting Expressive Dynamics in Piano Performances using Neural Networks

NARCIS (Netherlands)

van Herwaarden, Sam; Grachten, Maarten; de Haas, W. Bas

2014-01-01

This paper presents a model for predicting expressive accentuation in piano performances with neural networks. Using Restricted Boltzmann Machines (RBMs), features are learned from performance data, after which these features are used to predict performed loudness. During feature learning, data

Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography

Directory of Open Access Journals (Sweden)

Murilo Coutinho

2018-04-01

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

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

Science.gov (United States)

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

2018-04-24

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

UNMANNED AIR VEHICLE STABILIZATION BASED ON NEURAL NETWORK REGULATOR

Directory of Open Access Journals (Sweden)

S. S. Andropov

2016-09-01

Full Text Available A problem of stabilizing for the multirotor unmanned aerial vehicle in an environment with external disturbances is researched. A classic proportional-integral-derivative controller is analyzed, its flaws are outlined: inability to respond to changing of external conditions and the need for manual adjustment of coefficients. The paper presents an adaptive adjustment method for coefficients of the proportional-integral-derivative controller based on neural networks. A neural network structure, its input and output data are described. Neural networks with three layers are used to create an adaptive stabilization system for the multirotor unmanned aerial vehicle. Training of the networks is done with the back propagation method. Each neural network produces regulator coefficients for each angle of stabilization as its output. A method for network training is explained. Several graphs of transition process on different stages of learning, including processes with external disturbances, are presented. It is shown that the system meets stabilization requirements with sufficient number of iterations. Described adjustment method for coefficients can be used in remote control of unmanned aerial vehicles, operating in the changing environment.

Empirical modeling of nuclear power plants using neural networks

International Nuclear Information System (INIS)

Parlos, A.G.; Atiya, A.; Chong, K.T.

1991-01-01

A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios

Application of different entropy formalisms in a neural network for novel word learning

Science.gov (United States)

Khordad, R.; Rastegar Sedehi, H. R.

2015-12-01

In this paper novel word learning in adults is studied. For this goal, four entropy formalisms are employed to include some degree of non-locality in a neural network. The entropy formalisms are Tsallis, Landsberg-Vedral, Kaniadakis, and Abe entropies. First, we have analytically obtained non-extensive cost functions for the all entropies. Then, we have used a generalization of the gradient descent dynamics as a learning rule in a simple perceptron. The Langevin equations are numerically solved and the error function (learning curve) is obtained versus time for different values of the parameters. The influence of index q and number of neuron N on learning is investigated for the all entropies. It is found that learning is a decreasing function of time for the all entropies. The rate of learning for the Landsberg-Vedral entropy is slower than other entropies. The variation of learning with time for the Landsberg-Vedral entropy is not appreciable when the number of neurons increases. It is said that entropy formalism can be used as a means for studying the learning.