WorldWideScience

Sample records for neural networks learn

  1. Neural networks and statistical learning

    CERN Document Server

    Du, Ke-Lin

    2014-01-01

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

  2. Neural networks and perceptual learning

    Science.gov (United States)

    Tsodyks, Misha; Gilbert, Charles

    2005-01-01

    Sensory perception is a learned trait. The brain strategies we use to perceive the world are constantly modified by experience. With practice, we subconsciously become better at identifying familiar objects or distinguishing fine details in our environment. Current theoretical models simulate some properties of perceptual learning, but neglect the underlying cortical circuits. Future neural network models must incorporate the top-down alteration of cortical function by expectation or perceptual tasks. These newly found dynamic processes are challenging earlier views of static and feedforward processing of sensory information. PMID:15483598

  3. Learning Processes of Layered Neural Networks

    OpenAIRE

    Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.

    1995-01-01

    A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network, and a learning equation similar to that of the Boltzmann machine algorithm is obtained. By applying a mean field approximation to the same stochastic feed-forward neural network, a deterministic analog feed-forward network is obtained and the back-propagation learning rule is re-derived.

  4. Logarithmic learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2014-12-01

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

  5. Learning chaotic attractors by neural networks

    NARCIS (Netherlands)

    Bakker, R; Schouten, JC; Giles, CL; Takens, F; van den Bleek, CM

    2000-01-01

    An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time series. During training, the algorithm learns to short-term predict the time series. At the same time a criterion, developed by Diks, van Zwet, Takens, and de Goede (1996) is monitored

  6. Deep Learning in Neural Networks: An Overview

    OpenAIRE

    Schmidhuber, Juergen

    2014-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpr...

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

    Science.gov (United States)

    Chernoded, Andrey; Dudko, Lev; Myagkov, Igor; Volkov, Petr

    2017-10-01

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

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

    Directory of Open Access Journals (Sweden)

    Chernoded Andrey

    2017-01-01

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

  9. 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.

  10. Learning of N-layers neural network

    Directory of Open Access Journals (Sweden)

    Vladimír Konečný

    2005-01-01

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

  11. One pass learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2016-01-01

    Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network is proposed to overcome this disadvantage. Proposed method utilizes standard deviation of each class to calculate corresponding smoothing parameter. Since different datasets may have different standard deviations and data distributions, proposed method tries to handle these differences by defining two functions for smoothing parameter calculation. Thresholding is applied to determine which function will be used. One of these functions is defined for datasets having different range of values. It provides balanced smoothing parameters for these datasets through logarithmic function and changing the operation range to lower boundary. On the other hand, the other function calculates smoothing parameter value for classes having standard deviation smaller than the threshold value. Proposed method is tested on 14 datasets and performance of one pass learning generalized classifier neural network is compared with that of probabilistic neural network, radial basis function neural network, extreme learning machines, and standard and logarithmic learning generalized classifier neural network in MATLAB environment. One pass learning generalized classifier neural network provides more than a thousand times faster classification than standard and logarithmic generalized classifier neural network. Due to its classification accuracy and speed, one pass generalized classifier neural network can be considered as an efficient alternative to probabilistic neural network. Test results show that proposed method overcomes computational drawback of generalized classifier neural network and may increase the classification performance. Copyright

  12. Supervised Learning with Complex-valued Neural Networks

    CERN Document Server

    Suresh, Sundaram; Savitha, Ramasamy

    2013-01-01

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

  13. Digital associative memory neural network with optical learning capability

    Science.gov (United States)

    Watanabe, Minoru; Ohtsubo, Junji

    1994-12-01

    A digital associative memory neural network system with optical learning and recalling capabilities is proposed by using liquid crystal television spatial light modulators and an Optic RAM detector. In spite of the drawback of the limited memory capacity compared with optical analogue associative memory neural network, the proposed optical digital neural network has the advantage of all optical learning and recalling capabilities, thus an all optics network system is easily realized. Some experimental results of the learning and the recalling for character recognitions are presented. This new optical architecture offers compactness of the system and the fast learning and recalling properties. Based on the results, the practical system for the implementation of a faster optical digital associative memory neural network system with ferro-electric liquid crystal SLMs is also proposed.

  14. 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

  15. A constructive algorithm for unsupervised learning with incremental neural network

    OpenAIRE

    Wang, Jenq-Haur; Wang, Hsin-Yang; Chen, Yen-Lin; Liu, Chuan-Ming

    2015-01-01

    Artificial neural network (ANN) has wide applications such as data processing and classification. However, comparing with other classification methods, ANN needs enormous memory space and training time to build the model. This makes ANN infeasible in practical applications. In this paper, we try to integrate the ideas of human learning mechanism with the existing models of ANN. We propose an incremental neural network construction framework for unsupervised learning. In this framework, a neur...

  16. 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...... by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery...

  17. An ART neural network model of discrimination shift learning

    NARCIS (Netherlands)

    Raijmakers, M.E.J.; Coffey, E.; Stevenson, C.; Winkel, J.; Berkeljon, A.; Taatgen, N.; van Rijn, H.

    2009-01-01

    We present an ART-based neural network model (adapted from [2]) of the development of discrimination-shift learning that models the trial-by-trial learning process in great detail. In agreement with the results of human participants (4-20 years of age) in [1] the model revealed two distinct learning

  18. Neural networks for relational learning: An experimental comparison

    OpenAIRE

    Uwents, Werner; Monfardini, Gabriele; Blockeel, Hendrik; Gori, Marco De; Scarselli, Franco

    2011-01-01

    In the last decade, connectionist models have been proposed that can process structured information directly. These methods, which are based on the use of graphs for the representation of the data and the relationships within the data, are particularly suitable for handling relational learning tasks. In this paper, two recently proposed architectures of this kind, i.e. Graph Neural Networks (GNNs) and Relational Neural Networks (RelNNs), are compared and discussed, along with their correspond...

  19. Projection learning algorithm for threshold - controlled neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Reznik, A.M.

    1995-03-01

    The projection learning algorithm proposed in [1, 2] and further developed in [3] substantially improves the efficiency of memorizing information and accelerates the learning process in neural networks. This algorithm is compatible with the completely connected neural network architecture (the Hopfield network [4]), but its application to other networks involves a number of difficulties. The main difficulties include constraints on interconnection structure and the need to eliminate the state uncertainty of latent neurons if such are present in the network. Despite the encouraging preliminary results of [3], further extension of the applications of the projection algorithm therefore remains problematic. In this paper, which is a continuation of the work begun in [3], we consider threshold-controlled neural networks. Networks of this type are quite common. They represent the receptor neuron layers in some neurocomputer designs. A similar structure is observed in the lower divisions of biological sensory systems [5]. In multilayer projection neural networks with lateral interconnections, the neuron layers or parts of these layers may also have the structure of a threshold-controlled completely connected network. Here the thresholds are the potentials delivered through the projection connections from other parts of the network. The extension of the projection algorithm to the class of threshold-controlled networks may accordingly prove to be useful both for extending its technical applications and for better understanding of the operation of the nervous system in living organisms.

  20. Neural network models of learning and categorization in multigame experiments

    Directory of Open Access Journals (Sweden)

    Davide eMarchiori

    2011-12-01

    Full Text Available Previous research has shown that regret-driven neural networks predict behavior in repeated completely mixed games remarkably well, substantially equating the performance of the most accurate established models of learning. This result prompts the question of what is the added value of modeling learning through neural networks. We submit that this modeling approach allows for models that are able to distinguish among and respond differently to different payoff structures. Moreover, the process of categorization of a game is implicitly carried out by these models, thus without the need of any external explicit theory of similarity between games. To validate our claims, we designed and ran two multigame experiments in which subjects faced, in random sequence, different instances of two completely mixed 2x2 games. Then, we tested on our experimental data two regret-driven neural network models, and compared their performance with that of other established models of learning and Nash equilibrium.

  1. 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.

  2. Thermodynamic efficiency of learning a rule in neural networks

    Science.gov (United States)

    Goldt, Sebastian; Seifert, Udo

    2017-11-01

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

  3. 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…

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

    Science.gov (United States)

    Miconi, Thomas

    2017-02-23

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

  5. Effective learning in recurrent max-min neural networks.

    Science.gov (United States)

    Loe, Kia Fock; Teow, Loo Nin

    1998-04-01

    Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly differentiable, we propose a mathematically sound learning method based on using Fourier convergence analysis of side-derivatives to derive a gradient descent technique for max-min error functions. We then propose a novel recurrent max-min neural network model that is trained to perform grammatical inference as an application example. Comparisons made between this model and recurrent sigmoidal neural networks show that our model not only performs better in terms of learning speed and generalization, but that its final weight configuration allows a deterministic finite automation (DFA) to be extracted in a straightforward manner. In essence, we are able to demonstrate that our proposed gradient descent technique does allow max-min neural networks to learn effectively.

  6. 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.

  7. Regularized negative correlation learning for neural network ensembles.

    Science.gov (United States)

    Chen, Huanhuan; Yao, Xin

    2009-12-01

    Negative correlation learning (NCL) is a neural network ensemble learning algorithm that introduces a correlation penalty term to the cost function of each individual network so that each neural network minimizes its mean square error (MSE) together with the correlation of the ensemble. This paper analyzes NCL and reveals that the training of NCL (when lambda = 1) corresponds to training the entire ensemble as a single learning machine that only minimizes the MSE without regularization. This analysis explains the reason why NCL is prone to overfitting the noise in the training set. This paper also demonstrates that tuning the correlation parameter lambda in NCL by cross validation cannot overcome the overfitting problem. The paper analyzes this problem and proposes the regularized negative correlation learning (RNCL) algorithm which incorporates an additional regularization term for the whole ensemble. RNCL decomposes the ensemble's training objectives, including MSE and regularization, into a set of sub-objectives, and each sub-objective is implemented by an individual neural network. In this paper, we also provide a Bayesian interpretation for RNCL and provide an automatic algorithm to optimize regularization parameters based on Bayesian inference. The RNCL formulation is applicable to any nonlinear estimator minimizing the MSE. The experiments on synthetic as well as real-world data sets demonstrate that RNCL achieves better performance than NCL, especially when the noise level is nontrivial in the data set.

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

    Science.gov (United States)

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

    2018-04-01

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

  9. A Novel Learning Scheme for Chebyshev Functional Link Neural Networks

    Directory of Open Access Journals (Sweden)

    Satchidananda Dehuri

    2011-01-01

    dimensional-space where linear separability is possible. Moreover, the proposed HCFLNN combines the best attribute of particle swarm optimization (PSO, back propagation learning (BP learning, and functional link neural networks (FLNNs. The proposed method eliminates the need of hidden layer by expanding the input patterns using Chebyshev orthogonal polynomials. We have shown its effectiveness of classifying the unknown pattern using the publicly available datasets obtained from UCI repository. The computational results are then compared with functional link neural network (FLNN with a generic basis functions, PSO-based FLNN, and EFLN. From the comparative study, we observed that the performance of the HCFLNN outperforms FLNN, PSO-based FLNN, and EFLN in terms of classification accuracy.

  10. Robust adaptive learning of feedforward neural networks via LMI optimizations.

    Science.gov (United States)

    Jing, Xingjian

    2012-07-01

    Feedforward neural networks (FNNs) have been extensively applied to various areas such as control, system identification, function approximation, pattern recognition etc. A novel robust control approach to the learning problems of FNNs is further investigated in this study in order to develop efficient learning algorithms which can be implemented with optimal parameter settings and considering noise effect in the data. To this aim, the learning problem of a FNN is cast into a robust output feedback control problem of a discrete time-varying linear dynamic system. New robust learning algorithms with adaptive learning rate are therefore developed, using linear matrix inequality (LMI) techniques to find the appropriate learning rates and to guarantee the fast and robust convergence. Theoretical analysis and examples are given to illustrate the theoretical results. Copyright © 2012 Elsevier Ltd. All rights reserved.

  11. Experienced Gray Wolf Optimization Through Reinforcement Learning and Neural Networks.

    Science.gov (United States)

    Emary, E; Zawbaa, Hossam M; Grosan, Crina

    2017-01-10

    In this paper, a variant of gray wolf optimization (GWO) that uses reinforcement learning principles combined with neural networks to enhance the performance is proposed. The aim is to overcome, by reinforced learning, the common challenge of setting the right parameters for the algorithm. In GWO, a single parameter is used to control the exploration/exploitation rate, which influences the performance of the algorithm. Rather than using a global way to change this parameter for all the agents, we use reinforcement learning to set it on an individual basis. The adaptation of the exploration rate for each agent depends on the agent's own experience and the current terrain of the search space. In order to achieve this, experience repository is built based on the neural network to map a set of agents' states to a set of corresponding actions that specifically influence the exploration rate. The experience repository is updated by all the search agents to reflect experience and to enhance the future actions continuously. The resulted algorithm is called experienced GWO (EGWO) and its performance is assessed on solving feature selection problems and on finding optimal weights for neural networks algorithm. We use a set of performance indicators to evaluate the efficiency of the method. Results over various data sets demonstrate an advance of the EGWO over the original GWO and over other metaheuristics, such as genetic algorithms and particle swarm optimization.

  12. Prespeech motor learning in a neural network using reinforcement.

    Science.gov (United States)

    Warlaumont, Anne S; Westermann, Gert; Buder, Eugene H; Oller, D Kimbrough

    2013-02-01

    Vocal motor development in infancy provides a crucial foundation for language development. Some significant early accomplishments include learning to control the process of phonation (the production of sound at the larynx) and learning to produce the sounds of one's language. Previous work has shown that social reinforcement shapes the kinds of vocalizations infants produce. We present a neural network model that provides an account of how vocal learning may be guided by reinforcement. The model consists of a self-organizing map that outputs to muscles of a realistic vocalization synthesizer. Vocalizations are spontaneously produced by the network. If a vocalization meets certain acoustic criteria, it is reinforced, and the weights are updated to make similar muscle activations increasingly likely to recur. We ran simulations of the model under various reinforcement criteria and tested the types of vocalizations it produced after learning in the different conditions. When reinforcement was contingent on the production of phonated (i.e. voiced) sounds, the network's post-learning productions were almost always phonated, whereas when reinforcement was not contingent on phonation, the network's post-learning productions were almost always not phonated. When reinforcement was contingent on both phonation and proximity to English vowels as opposed to Korean vowels, the model's post-learning productions were more likely to resemble the English vowels and vice versa. Copyright © 2012 Elsevier Ltd. All rights reserved.

  13. Statistical learning of parts and wholes: A neural network approach.

    Science.gov (United States)

    Plaut, David C; Vande Velde, Anna K

    2017-03-01

    Statistical learning is often considered to be a means of discovering the units of perception, such as words and objects, and representing them as explicit "chunks." However, entities are not undifferentiated wholes but often contain parts that contribute systematically to their meanings. Studies of incidental auditory or visual statistical learning suggest that, as participants learn about wholes they become insensitive to parts embedded within them, but this seems difficult to reconcile with a broad range of findings in which parts and wholes work together to contribute to behavior. Bayesian approaches provide a principled description of how parts and wholes can contribute simultaneously to performance, but are generally not intended to model the computations that actually give rise to this performance. In the current work, we develop an account based on learning in artificial neural networks in which the representation of parts and wholes is a matter of degree, and the extent to which they cooperate or compete arises naturally through incidental learning. We show that the approach accounts for a wide range of findings concerning the relationship between parts and wholes in auditory and visual statistical learning, including some findings previously thought to be problematic for neural network approaches. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  14. 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.

  15. 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.

  16. 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.

  17. Are deep neural networks really learning relevant features?

    DEFF Research Database (Denmark)

    Kereliuk, Corey; Sturm, Bob L.; Larsen, Jan

    In recent years deep neural networks (DNNs) have become a popular choice for audio content analysis. This may be attributed to various factors including advancements in training algorithms, computational power, and the potential for DNNs to implicitly learn a set of feature detectors. We have...... recently re-examined two works \\cite{sigtiaimproved}\\cite{hamel2010learning} that consider DNNs for the task of music genre recognition (MGR). These papers conclude that frame-level features learned by DNNs offer an improvement over traditional, hand-crafted features such as Mel-frequency cepstrum...... leads one to question the degree to which the learned frame-level features are actually useful for MGR. We make available a reproducible software package allowing other researchers to completely duplicate our figures and results....

  18. 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....

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

    NARCIS (Netherlands)

    van den Dries, Sjoerd; Wiering, Marco A.

    2012-01-01

    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

  20. Structure Learning for Deep Neural Networks Based on Multiobjective Optimization.

    Science.gov (United States)

    Liu, Jia; Gong, Maoguo; Miao, Qiguang; Wang, Xiaogang; Li, Hao

    2017-05-05

    This paper focuses on the connecting structure of deep neural networks and proposes a layerwise structure learning method based on multiobjective optimization. A model with better generalization can be obtained by reducing the connecting parameters in deep networks. The aim is to find the optimal structure with high representation ability and better generalization for each layer. Then, the visible data are modeled with respect to structure based on the products of experts. In order to mitigate the difficulty of estimating the denominator in PoE, the denominator is simplified and taken as another objective, i.e., the connecting sparsity. Moreover, for the consideration of the contradictory nature between the representation ability and the network connecting sparsity, the multiobjective model is established. An improved multiobjective evolutionary algorithm is used to solve this model. Two tricks are designed to decrease the computational cost according to the properties of input data. The experiments on single-layer level, hierarchical level, and application level demonstrate the effectiveness of the proposed algorithm, and the learned structures can improve the performance of deep neural networks.

  1. Learning to play Go using recursive neural networks.

    Science.gov (United States)

    Wu, Lin; Baldi, Pierre

    2008-11-01

    Go is an ancient board game that poses unique opportunities and challenges for artificial intelligence. Currently, there are no computer Go programs that can play at the level of a good human player. However, the emergence of large repositories of games is opening the door for new machine learning approaches to address this challenge. Here we develop a machine learning approach to Go, and related board games, focusing primarily on the problem of learning a good evaluation function in a scalable way. Scalability is essential at multiple levels, from the library of local tactical patterns, to the integration of patterns across the board, to the size of the board itself. The system we propose is capable of automatically learning the propensity of local patterns from a library of games. Propensity and other local tactical information are fed into recursive neural networks, derived from a probabilistic Bayesian network architecture. The recursive neural networks in turn integrate local information across the board in all four cardinal directions and produce local outputs that represent local territory ownership probabilities. The aggregation of these probabilities provides an effective strategic evaluation function that is an estimate of the expected area at the end, or at various other stages, of the game. Local area targets for training can be derived from datasets of games played by human players. In this approach, while requiring a learning time proportional to N(4), skills learned on a board of size N(2) can easily be transferred to boards of other sizes. A system trained using only 9 x 9 amateur game data performs surprisingly well on a test set derived from 19 x 19 professional game data. Possible directions for further improvements are briefly discussed.

  2. 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.

  3. Prespeech motor learning in a neural network using reinforcement☆

    Science.gov (United States)

    Warlaumont, Anne S.; Westermann, Gert; Buder, Eugene H.; Oller, D. Kimbrough

    2012-01-01

    Vocal motor development in infancy provides a crucial foundation for language development. Some significant early accomplishments include learning to control the process of phonation (the production of sound at the larynx) and learning to produce the sounds of one’s language. Previous work has shown that social reinforcement shapes the kinds of vocalizations infants produce. We present a neural network model that provides an account of how vocal learning may be guided by reinforcement. The model consists of a self-organizing map that outputs to muscles of a realistic vocalization synthesizer. Vocalizations are spontaneously produced by the network. If a vocalization meets certain acoustic criteria, it is reinforced, and the weights are updated to make similar muscle activations increasingly likely to recur. We ran simulations of the model under various reinforcement criteria and tested the types of vocalizations it produced after learning in the differ-ent conditions. When reinforcement was contingent on the production of phonated (i.e. voiced) sounds, the network’s post learning productions were almost always phonated, whereas when reinforcement was not contingent on phonation, the network’s post-learning productions were almost always not phonated. When reinforcement was contingent on both phonation and proximity to English vowels as opposed to Korean vowels, the model’s post-learning productions were more likely to resemble the English vowels and vice versa. PMID:23275137

  4. Neural Networks that Learn Temporal Sequences by Selection

    Science.gov (United States)

    Dehaene, Stanislas; Changeux, Jean-Pierre; Nadal, Jean-Pierre

    1987-05-01

    A model for formal neural networks that learn temporal sequences by selection is proposed on the basis of observations on the acquisition of song by birds, on sequence-detecting neurons, and on allosteric receptors. The model relies on hypothetical elementary devices made up of three neurons, the synaptic triads, which yield short-term modification of synaptic efficacy through heterosynaptic interactions, and on a local Hebbian learning rule. The functional units postulated are mutually inhibiting clusters of synergic neurons and bundles of synapses. Networks formalized on this basis display capacities for passive recognition and for production of temporal sequences that may include repetitions. Introduction of the learning rule leads to the differentiation of sequence-detecting neurons and to the stabilization of ongoing temporal sequences. A network architecture composed of three layers of neuronal clusters is shown to exhibit active recognition and learning of time sequences by selection: the network spontaneously produces prerepresentations that are selected according to their resonance with the input percepts. Predictions of the model are discussed.

  5. The effects of cultural learning in populations of neural networks.

    Science.gov (United States)

    Curran, Dara; O'Riordan, Colm

    2007-01-01

    Population learning can be described as the iterative Darwinian process of fitness-based selection and genetic transfer of information leading to populations of higher fitness and is often simulated using genetic algorithms. Cultural learning describes the process of information transfer between individuals in a population through non-genetic means. Cultural learning has been simulated by combining genetic algorithms and neural networks using a teacher-pupil scenario where highly fit individuals are selected as teachers and instruct the next generation. By examining the innate fitness of a population (i.e., the fitness of the population measured before any cultural learning takes place), it is possible to examine the effects of cultural learning on the population's genetic makeup. Our model explores the effect of cultural learning on a population and employs three benchmark sequential decision tasks as the evolutionary task for the population: connect-four, tic-tac-toe, and blackjack. Experiments are conducted with populations employing population learning alone and populations combining population and cultural learning. The article presents results showing the gradual transfer of knowledge from genes to the cultural process, illustrated by the simultaneous decrease in the population's innate fitness and the increase of its acquired fitness measured after learning takes place.

  6. 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.

  7. 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.

  8. Are deep neural networks really learning relevant features?

    DEFF Research Database (Denmark)

    Kereliuk, Corey Mose; Larsen, Jan; Sturm, Bob L.

    In recent years deep neural networks (DNNs) have become a popular choice for audio content analysis. This may be attributed to various factors including advancements in training algorithms, computational power, and the potential for DNNs to implicitly learn a set of feature detectors. We have...... recently re-examined two works that consider DNNs for the task of music genre recognition (MGR). These papers conclude that frame-level features learned by DNNs offer an improvement over traditional, hand-crafted features such as Mel-frequency cepstrum coefficients (MFCCs). However, these conclusions were...... drawn based on training/testing using the GTZAN dataset, which is now known to contain several flaws including replicated observations and artists. We illustrate how considering these flaws dramatically changes the results, which leads one to question the degree to which the learned frame-level features...

  9. Neural Networks

    Directory of Open Access Journals (Sweden)

    Schwindling Jerome

    2010-04-01

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

  10. Adaptive Neural Network Nonparametric Identifier With Normalized Learning Laws.

    Science.gov (United States)

    Chairez, Isaac

    2017-05-01

    This paper addresses the design of a normalized convergent learning law for neural networks (NNs) with continuous dynamics. The NN is used here to obtain a nonparametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties is the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on normalized algorithms was used to adjust the weights of the NN. The adaptive algorithm was derived by means of a nonstandard logarithmic Lyapunov function (LLF). Two identifiers were designed using two variations of LLFs leading to a normalized learning law for the first identifier and a variable gain normalized learning law. In the case of the second identifier, the inclusion of normalized learning laws yields to reduce the size of the convergence region obtained as solution of the practical stability analysis. On the other hand, the velocity of convergence for the learning laws depends on the norm of errors in inverse form. This fact avoids the peaking transient behavior in the time evolution of weights that accelerates the convergence of identification error. A numerical example demonstrates the improvements achieved by the algorithm introduced in this paper compared with classical schemes with no-normalized continuous learning methods. A comparison of the identification performance achieved by the no-normalized identifier and the ones developed in this paper shows the benefits of the learning law proposed in this paper.

  11. A Model for Improving the Learning Curves of Artificial Neural Networks.

    Directory of Open Access Journals (Sweden)

    Roberto L S Monteiro

    Full Text Available In this article, the performance of a hybrid artificial neural network (i.e. scale-free and small-world was analyzed and its learning curve compared to three other topologies: random, scale-free and small-world, as well as to the chemotaxis neural network of the nematode Caenorhabditis Elegans. One hundred equivalent networks (same number of vertices and average degree for each topology were generated and each was trained for one thousand epochs. After comparing the mean learning curves of each network topology with the C. elegans neural network, we found that the networks that exhibited preferential attachment exhibited the best learning curves.

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

    Science.gov (United States)

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

    2017-03-01

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

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

    Science.gov (United States)

    Walter, Florian; Röhrbein, Florian; Knoll, Alois

    2015-12-01

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

  14. 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…

  15. Composite learning from adaptive backstepping neural network control.

    Science.gov (United States)

    Pan, Yongping; Sun, Tairen; Liu, Yiqi; Yu, Haoyong

    2017-11-01

    In existing neural network (NN) learning control methods, the trajectory of NN inputs must be recurrent to satisfy a stringent condition termed persistent excitation (PE) so that NN parameter convergence is obtainable. This paper focuses on command-filtered backstepping adaptive control for a class of strict-feedback nonlinear systems with functional uncertainties, where an NN composite learning technique is proposed to guarantee convergence of NN weights to their ideal values without the PE condition. In the NN composite learning, spatially localized NN approximation is employed to handle functional uncertainties, online historical data together with instantaneous data are exploited to generate prediction errors, and both tracking errors and prediction errors are employed to update NN weights. The influence of NN approximation errors on the control performance is also clearly shown. The distinctive feature of the proposed NN composite learning is that NN parameter convergence is guaranteed without the requirement of the trajectory of NN inputs being recurrent. Illustrative results have verified effectiveness and superiority of the proposed method compared with existing NN learning control methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

  16. 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

    Training neural networks to quickly learn new skills without forgetting previously learned skills is an important open challenge in machine learning. A common problem for adaptive networks that can learn during their lifetime is that the weights encoding a particular task are often overridden when...... 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...

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

    National Research Council Canada - National Science Library

    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...

  18. Structured learning via convolutional neural networks for vehicle detection

    Science.gov (United States)

    Maqueda, Ana I.; del Blanco, Carlos R.; Jaureguizar, Fernando; García, Narciso

    2017-05-01

    One of the main tasks in a vision-based traffic monitoring system is the detection of vehicles. Recently, deep neural networks have been successfully applied to this end, outperforming previous approaches. However, most of these works generally rely on complex and high-computational region proposal networks. Others employ deep neural networks as a segmentation strategy to achieve a semantic representation of the object of interest, which has to be up-sampled later. In this paper, a new design for a convolutional neural network is applied to vehicle detection in highways for traffic monitoring. This network generates a spatially structured output that encodes the vehicle locations. Promising results have been obtained in the GRAM-RTM dataset.

  19. Recurrent Neural Network for Text Classification with Multi-Task Learning

    OpenAIRE

    Liu, Pengfei; Qiu, Xipeng; Huang, Xuanjing

    2016-01-01

    Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we use the multi-task learning framework to jointly learn across multiple related tasks. Based on recurrent neural network, we propose three different mechanisms of sharing information to model text with task-specific and...

  20. A hybrid ART-GRNN online learning neural network with a epsilon -insensitive loss function.

    Science.gov (United States)

    Yap, Keem Siah; Lim, Chee Peng; Abidin, Izham Zainal

    2008-09-01

    In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

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

    Science.gov (United States)

    Finnegan, Alex; Song, Jun S

    2017-10-01

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

  2. Image aesthetic quality evaluation using convolution neural network embedded learning

    Science.gov (United States)

    Li, Yu-xin; Pu, Yuan-yuan; Xu, Dan; Qian, Wen-hua; Wang, Li-peng

    2017-11-01

    A way of embedded learning convolution neural network (ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also score the image aesthetic quality. First, we chose Alexnet and VGG_S to compare for confirming which is more suitable for this image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tuning cannot make full use of the small-scale data set. Third, to solve the problem in second step, a way of using twice fine-tuning continually based on the aesthetic quality label and content label respective is proposed, the classification probability of the trained CNN models is used to evaluate the image aesthetic quality. The experiments are carried on the small-scale data set of Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.

  3. 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.

  4. 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.

  5. Artificial Neural Networks for Modeling Knowing and Learning in Science.

    Science.gov (United States)

    Roth, Wolff-Michael

    2000-01-01

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

  6. Active random noise control using adaptive learning rate neural networks with an immune feedback law

    Science.gov (United States)

    Sasaki, Minoru; Kuribayashi, Takumi; Ito, Satoshi

    2005-12-01

    In this paper an active random noise control using adaptive learning rate neural networks with an immune feedback law is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased by a proportion of its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without leading to oscillation. In the proposed method, because of the immune feedback law change a learning rate of the neural networks individually and adaptively, it is expected that a cost function minimize rapidly and training time is decreased. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed, to validate the convergence properties of the adaptive learning rate Neural Networks with the immune feedback law. Control results show that adaptive learning rate Neural Networks control structure can outperform linear controllers and conventional neural network controller for the active random noise control.

  7. 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.

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

    Science.gov (United States)

    Tonelli, Paul; Mouret, Jean-Baptiste

    2013-01-01

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

  9. A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation.

    Science.gov (United States)

    Vuković, Najdan; Miljković, Zoran

    2013-10-01

    Radial basis function (RBF) neural network is constructed of certain number of RBF neurons, and these networks are among the most used neural networks for modeling of various nonlinear problems in engineering. Conventional RBF neuron is usually based on Gaussian type of activation function with single width for each activation function. This feature restricts neuron performance for modeling the complex nonlinear problems. To accommodate limitation of a single scale, this paper presents neural network with similar but yet different activation function-hyper basis function (HBF). The HBF allows different scaling of input dimensions to provide better generalization property when dealing with complex nonlinear problems in engineering practice. The HBF is based on generalization of Gaussian type of neuron that applies Mahalanobis-like distance as a distance metrics between input training sample and prototype vector. Compared to the RBF, the HBF neuron has more parameters to optimize, but HBF neural network needs less number of HBF neurons to memorize relationship between input and output sets in order to achieve good generalization property. However, recent research results of HBF neural network performance have shown that optimal way of constructing this type of neural network is needed; this paper addresses this issue and modifies sequential learning algorithm for HBF neural network that exploits the concept of neuron's significance and allows growing and pruning of HBF neuron during learning process. Extensive experimental study shows that HBF neural network, trained with developed learning algorithm, achieves lower prediction error and more compact neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.

  10. 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...

  11. 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.

  12. "FORCE" learning in recurrent neural networks as data assimilation

    Science.gov (United States)

    Duane, Gregory S.

    2017-12-01

    It is shown that the "FORCE" algorithm for learning in arbitrarily connected networks of simple neuronal units can be cast as a Kalman Filter, with a particular state-dependent form for the background error covariances. The resulting interpretation has implications for initialization of the learning algorithm, leads to an extension to include interactions between the weight updates for different neurons, and can represent relationships within groups of multiple target output signals.

  13. 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.

  14. Biologically-inspired Learning in Pulsed Neural Networks

    DEFF Research Database (Denmark)

    Lehmann, Torsten; Woodburn, Robin

    1999-01-01

    , 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...

  15. Cascaded VLSI Chips Help Neural Network To Learn

    Science.gov (United States)

    Duong, Tuan A.; Daud, Taher; Thakoor, Anilkumar P.

    1993-01-01

    Cascading provides 12-bit resolution needed for learning. Using conventional silicon chip fabrication technology of VLSI, fully connected architecture consisting of 32 wide-range, variable gain, sigmoidal neurons along one diagonal and 7-bit resolution, electrically programmable, synaptic 32 x 31 weight matrix implemented on neuron-synapse chip. To increase weight nominally from 7 to 13 bits, synapses on chip individually cascaded with respective synapses on another 32 x 32 matrix chip with 7-bit resolution synapses only (without neurons). Cascade correlation algorithm varies number of layers effectively connected into network; adds hidden layers one at a time during learning process in such way as to optimize overall number of neurons and complexity and configuration of network.

  16. 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.

  17. A constructive algorithm for unsupervised learning with incremental neural network

    Directory of Open Access Journals (Sweden)

    Jenq-Haur Wang

    2015-04-01

    In our experiment, Reuters-21578 was used as the dataset to show the effectiveness of the proposed method on text classification. The experimental results showed that our method can effectively classify texts with the best F1-measure of 92.5%. It also showed the learning algorithm can enhance the accuracy effectively and efficiently. This framework also validates scalability in terms of the network size, in which the training and testing times both showed a constant trend. This also validates the feasibility of the method for practical uses.

  18. 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.

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

    Science.gov (United States)

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

    2017-07-01

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

  20. 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.

  1. Unsupervised learning in neural networks with short range synapses

    Science.gov (United States)

    Brunnet, L. G.; Agnes, E. J.; Mizusaki, B. E. P.; Erichsen, R., Jr.

    2013-01-01

    Different areas of the brain are involved in specific aspects of the information being processed both in learning and in memory formation. For example, the hippocampus is important in the consolidation of information from short-term memory to long-term memory, while emotional memory seems to be dealt by the amygdala. On the microscopic scale the underlying structures in these areas differ in the kind of neurons involved, in their connectivity, or in their clustering degree but, at this level, learning and memory are attributed to neuronal synapses mediated by longterm potentiation and long-term depression. In this work we explore the properties of a short range synaptic connection network, a nearest neighbor lattice composed mostly by excitatory neurons and a fraction of inhibitory ones. The mechanism of synaptic modification responsible for the emergence of memory is Spike-Timing-Dependent Plasticity (STDP), a Hebbian-like rule, where potentiation/depression is acquired when causal/non-causal spikes happen in a synapse involving two neurons. The system is intended to store and recognize memories associated to spatial external inputs presented as simple geometrical forms. The synaptic modifications are continuously applied to excitatory connections, including a homeostasis rule and STDP. In this work we explore the different scenarios under which a network with short range connections can accomplish the task of storing and recognizing simple connected patterns.

  2. 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

  3. Application of analytical learning to the syntesis of neural network for process control of physical rehabilitation

    OpenAIRE

    Alexander Trunov

    2015-01-01

    The problem of analytical learning of artificial neural network (ANN) is consider. Solutions in the analytic form for synaptic weight coefficients (SWC) as recurrent sequence are obtained. Convergence of recurrent approximation for two scheme of approach by a linear and quadratic curve are proved and discussed

  4. Image Classification System Based on Cortical Representations and Unsupervised Neural Network Learning

    NARCIS (Netherlands)

    Petkov, Nikolay

    1995-01-01

    A preprocessor based on a computational model of simple cells in the mammalian primary visual cortex is combined with a self-organising artificial neural network classifier. After learning with a sequence of input images, the output units of the system turn out to correspond to classes of input

  5. 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...

  6. 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...

  7. Adjoint-operators and non-adiabatic learning algorithms in neural networks

    Science.gov (United States)

    Toomarian, N.; Barhen, J.

    1991-01-01

    Adjoint sensitivity equations are presented, which can be solved simultaneously (i.e., forward in time) with the dynamics of a nonlinear neural network. These equations provide the foundations for a new methodology which enables the implementation of temporal learning algorithms in a highly efficient manner.

  8. 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.

  9. Image retrieval method based on metric learning for convolutional neural network

    Science.gov (United States)

    Wang, Jieyuan; Qian, Ying; Ye, Qingqing; Wang, Biao

    2017-09-01

    At present, the research of content-based image retrieval (CBIR) focuses on learning effective feature for the representations of origin images and similarity measures. The retrieval accuracy and efficiency are crucial to a CBIR. With the rise of deep learning, convolutional network is applied in the domain of image retrieval and achieved remarkable results, but the image visual feature extraction of convolutional neural network exist high dimension problems, this problem makes the image retrieval and speed ineffective. This paper uses the metric learning for the image visual features extracted from the convolutional neural network, decreased the feature redundancy, improved the retrieval performance. The work in this paper is also a necessary part for further implementation of feature hashing to the approximate-nearest-neighbor (ANN) retrieval method.

  10. Simulated apoptosis/neurogenesis regulates learning and memory capabilities of adaptive neural networks.

    Science.gov (United States)

    Chambers, R Andrew; Potenza, Marc N; Hoffman, Ralph E; Miranker, Willard

    2004-04-01

    Characterization of neuronal death and neurogenesis in the adult brain of birds, humans, and other mammals raises the possibility that neuronal turnover represents a special form of neuroplasticity associated with stress responses, cognition, and the pathophysiology and treatment of psychiatric disorders. Multilayer neural network models capable of learning alphabetic character representations via incremental synaptic connection strength changes were used to assess additional learning and memory effects incurred by simulation of coordinated apoptotic and neurogenic events in the middle layer. Using a consistent incremental learning capability across all neurons and experimental conditions, increasing the number of middle layer neurons undergoing turnover increased network learning capacity for new information, and increased forgetting of old information. Simulations also showed that specific patterns of neural turnover based on individual neuronal connection characteristics, or the temporal-spatial pattern of neurons chosen for turnover during new learning impacts new learning performance. These simulations predict that apoptotic and neurogenic events could act together to produce specific learning and memory effects beyond those provided by ongoing mechanisms of connection plasticity in neuronal populations. Regulation of rates as well as patterns of neuronal turnover may serve an important function in tuning the informatic properties of plastic networks according to novel informational demands. Analogous regulation in the hippocampus may provide for adaptive cognitive and emotional responses to novel and stressful contexts, or operate suboptimally as a basis for psychiatric disorders. The implications of these elementary simulations for future biological and neural modeling research on apoptosis and neurogenesis are discussed.

  11. 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.

  12. 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.

  13. Sign language recognition using competitive learning in the HAVNET neural network

    Science.gov (United States)

    Sujan, Vivek A.; Meggiolaro, Marco A.

    2000-04-01

    An optical modeless Sign Language Recognition (SLR) system is presented. The system uses the HAusdorf-Voronoi NETwork (HAVNET), an artificial neural network designed for 2D binary pattern recognition. It uses adaptation of the Hausdorff distance to determine the similarity between an input pattern and a learned representation. A detailed review of the architecture, the learning equations, and the recognition equations for the HAVNET network are presented. Competitive learning has been implemented in training the network using a nearest-neighbor technique. The SLR system is applied to the optical recognition of 24 static symbols from the American Sign Language convention. The SLR system represents the target images in a 80 X 80 pixel format. The implemented HAVNET network classifies the inputs into categories representing each of the symbols, using an output layer of 24 nodes. The network is trained with 5 different formats for each symbol and is tested with all 24 symbols in 15 new formats. Results from the SLR system without competitive training show shape identification problems, when distinguishing symbols with similar shapes. Implementation of competitive learning in the HAVNET neural network improved recognition accuracy on this task to 89%. The hand gestures are identified through a window search algorithm. Feature recognition is obtained from edge enhancement by applying a Laplacian filter and thresholding, which provides robustness to pose, color and background variations.

  14. 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.

  15. Biologically Inspired Modular Neural Networks

    OpenAIRE

    Azam, Farooq

    2000-01-01

    This dissertation explores the modular learning in artificial neural networks that mainly driven by the inspiration from the neurobiological basis of the human learning. The presented modularization approaches to the neural network design and learning are inspired by the engineering, complexity, psychological and neurobiological aspects. The main theme of this dissertation is to explore the organization and functioning of the brain to discover new structural and learning ...

  16. 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.

  17. Introduction to neural networks

    CERN Document Server

    James, Frederick E

    1994-02-02

    1. Introduction and overview of Artificial Neural Networks. 2,3. The Feed-forward Network as an inverse Problem, and results on the computational complexity of network training. 4.Physics applications of neural networks.

  18. 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 that are in......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...... that are intrinsic-factors-determined, extrinsic-factors-determined, and hybrid-factors-determined. The authors point out: integrations dominated by both of the internal and external elements are highly correlative with not only the historical quality of the sub-networks, but also with the environment in which...

  19. 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.

  20. 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.

  1. Learning Efficiency of Consciousness System for Robot Using Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Osama Shoubaky

    2014-12-01

    Full Text Available This paper presents learning efficiency of a consciousness system for robot using artificial neural network. The proposed conscious system consists of reason system, feeling system and association system. The three systems are modeled using Module of Nerves for Advanced Dynamics (ModNAD. Artificial neural network of the type of supervised learning with the back propagation is used to train the ModNAD. The reason system imitates behaviour and represents self-condition and other-condition. The feeling system represents sensation and emotion. The association system represents behaviour of self and determines whether self is comfortable or not. A robot is asked to perform cognition and tasks using the consciousness system. Learning converges to about 0.01 within about 900 orders for imitation, pain, solitude and the association modules. It converges to about 0.01 within about 400 orders for the comfort and discomfort modules. It can be concluded that learning in the ModNAD completed after a relatively small number of times because the learning efficiency of the ModNAD artificial neural network is good. The results also show that each ModNAD has a function to imitate and cognize emotion. The consciousness system presented in this paper may be considered as a fundamental step for developing a robot having consciousness and feelings similar to humans.

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

    Science.gov (United States)

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

    1992-01-01

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

  3. 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.

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

    Science.gov (United States)

    Gjaja, Marin N.

    1997-11-01

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

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

    Science.gov (United States)

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

    2016-01-01

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

  6. 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

  7. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.

    Science.gov (United States)

    Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji

    2018-01-11

    In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10 × 10 board, using TD(λ) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa(λ) agent with SiLU and dSiLU hidden units. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.

  8. [Artificial neural networks in Neurosciences].

    Science.gov (United States)

    Porras Chavarino, Carmen; Salinas Martínez de Lecea, José María

    2011-11-01

    This article shows that artificial neural networks are used for confirming the relationships between physiological and cognitive changes. Specifically, we explore the influence of a decrease of neurotransmitters on the behaviour of old people in recognition tasks. This artificial neural network recognizes learned patterns. When we change the threshold of activation in some units, the artificial neural network simulates the experimental results of old people in recognition tasks. However, the main contributions of this paper are the design of an artificial neural network and its operation inspired by the nervous system and the way the inputs are coded and the process of orthogonalization of patterns.

  9. A Review of Neural Network Based Machine Learning Approaches for Rotor Angle Stability Control

    OpenAIRE

    Yousefian, Reza; Kamalasadan, Sukumar

    2017-01-01

    This paper reviews the current status and challenges of Neural Networks (NNs) based machine learning approaches for modern power grid stability control including their design and implementation methodologies. NNs are widely accepted as Artificial Intelligence (AI) approaches offering an alternative way to control complex and ill-defined problems. In this paper various application of NNs for power system rotor angle stabilization and control problem is discussed. The main focus of this paper i...

  10. Learning Orthographic Structure with Sequential Generative Neural Networks

    Science.gov (United States)

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

    2016-01-01

    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…

  11. Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach

    Directory of Open Access Journals (Sweden)

    Ajit Kumar Rout

    2017-10-01

    Full Text Available The paper presents a low complexity recurrent Functional Link Artificial Neural Network for predicting the financial time series data like the stock market indices over a time frame varying from 1 day ahead to 1 month ahead. Although different types of basis functions have been used for low complexity neural networks earlier for stock market prediction, a comparative study is needed to choose the optimal combinations of these for a reasonably accurate forecast. Further several evolutionary learning methods like the Particle Swarm Optimization (PSO and modified version of its new variant (HMRPSO, and the Differential Evolution (DE are adopted here to find the optimal weights for the recurrent computationally efficient functional link neural network (RCEFLANN using a combination of linear and hyperbolic tangent basis functions. The performance of the recurrent computationally efficient FLANN model is compared with that of low complexity neural networks using the Trigonometric, Chebyshev, Laguerre, Legendre, and tangent hyperbolic basis functions in predicting stock prices of Bombay Stock Exchange data and Standard & Poor’s 500 data sets using different evolutionary methods and has been presented in this paper and the results clearly reveal that the recurrent FLANN model trained with the DE outperforms all other FLANN models similarly trained.

  12. Deep Manifold Learning Combined With Convolutional Neural Networks for Action Recognition.

    Science.gov (United States)

    Chen, Xin; Weng, Jian; Lu, Wei; Xu, Jiaming; Weng, Jiasi

    2017-09-15

    Learning deep representations have been applied in action recognition widely. However, there have been a few investigations on how to utilize the structural manifold information among different action videos to enhance the recognition accuracy and efficiency. In this paper, we propose to incorporate the manifold of training samples into deep learning, which is defined as deep manifold learning (DML). The proposed DML framework can be adapted to most existing deep networks to learn more discriminative features for action recognition. When applied to a convolutional neural network, DML embeds the previous convolutional layer's manifold into the next convolutional layer; thus, the discriminative capacity of the next layer can be promoted. We also apply the DML on a restricted Boltzmann machine, which can alleviate the overfitting problem. Experimental results on four standard action databases (i.e., UCF101, HMDB51, KTH, and UCF sports) show that the proposed method outperforms the state-of-the-art methods.

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

    National Research Council Canada - National Science Library

    Tonelli, Paul; Mouret, Jean-Baptiste

    2013-01-01

    .... 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...

  14. 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 neural networks may be used to construct effective classifiers for abdominal ultrasound images.

  15. Learning Networks, Networked Learning

    NARCIS (Netherlands)

    Sloep, Peter; Berlanga, Adriana

    2010-01-01

    Sloep, P. B., & Berlanga, A. J. (2011). Learning Networks, Networked Learning [Redes de Aprendizaje, Aprendizaje en Red]. Comunicar, XIX(37), 55-63. Retrieved from http://dx.doi.org/10.3916/C37-2011-02-05

  16. HIERtalker: A default hierarchy of high order neural networks that learns to read English aloud

    Energy Technology Data Exchange (ETDEWEB)

    An, Z.G.; Mniszewski, S.M.; Lee, Y.C.; Papcun, G.; Doolen, G.D.

    1988-01-01

    A new learning algorithm based on a default hierarchy of high order neural networks has been developed that is able to generalize as well as handle exceptions. It learns the ''building blocks'' or clusters of symbols in a stream that appear repeatedly and convey certain messages. The default hierarchy prevents a combinatoric explosion of rules. A simulator of such a hierarchy, HIERtalker, has been applied to the conversion of English words to phonemes. Achieved accuracy is 99% for trained words and ranges from 76% to 96% for sets of new words. 8 refs., 4 figs., 1 tab.

  17. 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.

  18. 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.

  19. A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks.

    Science.gov (United States)

    Xu, Yan; Zeng, Xiaoqin; Han, Lixin; Yang, Jing

    2013-07-01

    We use a supervised multi-spike learning algorithm for spiking neural networks (SNNs) with temporal encoding to simulate the learning mechanism of biological neurons in which the SNN output spike trains are encoded by firing times. We first analyze why existing gradient-descent-based learning methods for SNNs have difficulty in achieving multi-spike learning. We then propose a new multi-spike learning method for SNNs based on gradient descent that solves the problems of error function construction and interference among multiple output spikes during learning. The method could be widely applied to single spiking neurons to learn desired output spike trains and to multilayer SNNs to solve classification problems. By overcoming learning interference among multiple spikes, our method has high learning accuracy when there are a relatively large number of output spikes in need of learning. We also develop an output encoding strategy with respect to multiple spikes for classification problems. This effectively improves the classification accuracy of multi-spike learning compared to that of single-spike learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

  20. 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.

  1. 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.

  2. SKYNET: an efficient and robust neural network training tool for machine learning in astronomy

    Science.gov (United States)

    Graff, Philip; Feroz, Farhan; Hobson, Michael P.; Lasenby, Anthony

    2014-06-01

    We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a `pre-training' method to obtain a set of network parameters that has empirically been shown to be close to a good solution, followed by further optimization using a regularized variant of Newton's method, where the level of regularization is determined and adjusted automatically; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimize using standard backpropagation techniques. SKYNET employs convergence criteria that naturally prevent overfitting, and also includes a fast algorithm for estimating the accuracy of network outputs. The utility and flexibility of SKYNET are demonstrated by application to a number of toy problems, and to astronomical problems focusing on the recovery of structure from blurred and noisy images, the identification of gamma-ray bursters, and the compression and denoising of galaxy images. The SKYNET software, which is implemented in standard ANSI C and fully parallelized using MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.

  3. 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.

  4. 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

  5. A study on the performance comparison of metaheuristic algorithms on the learning of neural networks

    Science.gov (United States)

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

    2017-08-01

    The learning or training process of neural networks entails the task of finding the most optimal set of parameters, which includes translation vectors, dilation parameter, synaptic weights, and bias terms. Apart from the traditional gradient descent-based methods, metaheuristic methods can also be used for this learning purpose. Since the inception of genetic algorithm half a century ago, the last decade witnessed the explosion of a variety of novel metaheuristic algorithms, such as harmony search algorithm, bat algorithm, and whale optimization algorithm. Despite the proof of the no free lunch theorem in the discipline of optimization, a survey in the literature of machine learning gives contrasting results. Some researchers report that certain metaheuristic algorithms are superior to the others, whereas some others argue that different metaheuristic algorithms give comparable performance. As such, this paper aims to investigate if a certain metaheuristic algorithm will outperform the other algorithms. In this work, three metaheuristic algorithms, namely genetic algorithms, particle swarm optimization, and harmony search algorithm are considered. The algorithms are incorporated in the learning of neural networks and their classification results on the benchmark UCI machine learning data sets are compared. It is found that all three metaheuristic algorithms give similar and comparable performance, as captured in the average overall classification accuracy. The results corroborate the findings reported in the works done by previous researchers. Several recommendations are given, which include the need of statistical analysis to verify the results and further theoretical works to support the obtained empirical results.

  6. 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.

  7. Evaluation of Raman spectra of human brain tumor tissue using the learning vector quantization neural network

    Science.gov (United States)

    Liu, Tuo; Chen, Changshui; Shi, Xingzhe; Liu, Chengyong

    2016-05-01

    The Raman spectra of tissue of 20 brain tumor patients was recorded using a confocal microlaser Raman spectroscope with 785 nm excitation in vitro. A total of 133 spectra were investigated. Spectra peaks from normal white matter tissue and tumor tissue were analyzed. Algorithms, such as principal component analysis, linear discriminant analysis, and the support vector machine, are commonly used to analyze spectral data. However, in this study, we employed the learning vector quantization (LVQ) neural network, which is typically used for pattern recognition. By applying the proposed method, a normal diagnosis accuracy of 85.7% and a glioma diagnosis accuracy of 89.5% were achieved. The LVQ neural network is a recent approach to excavating Raman spectra information. Moreover, it is fast and convenient, does not require the spectra peak counterpart, and achieves a relatively high accuracy. It can be used in brain tumor prognostics and in helping to optimize the cutting margins of gliomas.

  8. 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...

  9. Short-Term Load Forecasting Using Adaptive Annealing Learning Algorithm Based Reinforcement Neural Network

    Directory of Open Access Journals (Sweden)

    Cheng-Ming Lee

    2016-11-01

    Full Text Available A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF in this article. The proposed model integrates radial basis function neural network (RBFNN, support vector regression (SVR, and adaptive annealing learning algorithm (AALA. In the proposed methodology, firstly, the initial structure of RBFNN is determined by using an SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVR-RBFNN. In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from the Taiwan Power Company (TPC. Simulation results reveal that the proposed AALA-SVR-RBFNN can achieve a better load forecasting precision compared to various RBFNNs.

  10. Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems.

    Science.gov (United States)

    Luitel, Bipul; Venayagamoorthy, Ganesh Kumar

    2010-06-01

    Training a single simultaneous recurrent neural network (SRN) to learn all outputs of a multiple-input-multiple-output (MIMO) system is a difficult problem. A new training algorithm developed from combined concepts of swarm intelligence and quantum principles is presented. The training algorithm is called particle swarm optimization with quantum infusion (PSO-QI). To improve the effectiveness of learning, a two-step learning approach is introduced in the training. The objective of the learning in the first step is to find the optimal set of weights in the SRN considering all output errors. In the second step, the objective is to maximize the learning of each output dynamics by fine tuning the respective SRN output weights. To demonstrate the effectiveness of the PSO-QI training algorithm and the two-step learning approach, two examples of an SRN learning MIMO systems are presented. The first example is learning a benchmark MIMO system and the second one is the design of a wide area monitoring system for a multimachine power system. From the results, it is observed that SRNs can effectively learn MIMO systems when trained using the PSO-QI algorithm and the two-step learning approach. Copyright 2009 Elsevier Ltd. All rights reserved.

  11. Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn.

    Science.gov (United States)

    Patra, Tarak K; Meenakshisundaram, Venkatesh; Hung, Jui-Hsiang; Simmons, David S

    2017-02-13

    Machine learning has the potential to dramatically accelerate high-throughput approaches to materials design, as demonstrated by successes in biomolecular design and hard materials design. However, in the search for new soft materials exhibiting properties and performance beyond those previously achieved, machine learning approaches are frequently limited by two shortcomings. First, because they are intrinsically interpolative, they are better suited to the optimization of properties within the known range of accessible behavior than to the discovery of new materials with extremal behavior. Second, they require large pre-existing data sets, which are frequently unavailable and prohibitively expensive to produce. Here we describe a new strategy, the neural-network-biased genetic algorithm (NBGA), for combining genetic algorithms, machine learning, and high-throughput computation or experiment to discover materials with extremal properties in the absence of pre-existing data. Within this strategy, predictions from a progressively constructed artificial neural network are employed to bias the evolution of a genetic algorithm, with fitness evaluations performed via direct simulation or experiment. In effect, this strategy gives the evolutionary algorithm the ability to "learn" and draw inferences from its experience to accelerate the evolutionary process. We test this algorithm against several standard optimization problems and polymer design problems and demonstrate that it matches and typically exceeds the efficiency and reproducibility of standard approaches including a direct-evaluation genetic algorithm and a neural-network-evaluated genetic algorithm. The success of this algorithm in a range of test problems indicates that the NBGA provides a robust strategy for employing informatics-accelerated high-throughput methods to accelerate materials design in the absence of pre-existing data.

  12. 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.

  13. 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.

  14. Artificial Neural Networks·

    Indian Academy of Sciences (India)

    differences between biological neural networks (BNNs) of the brain and ANN s. A thorough understanding of ... neurons. Artificial neural models are loosely based on biology since a complete understanding of the .... A learning scheme for updating a neuron's connections (weights) was proposed by Donald Hebb in 1949.

  15. 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.

  16. Biological oscillations for learning walking coordination: dynamic recurrent neural network functionally models physiological central pattern generator.

    Science.gov (United States)

    Hoellinger, Thomas; Petieau, Mathieu; Duvinage, Matthieu; Castermans, Thierry; Seetharaman, Karthik; Cebolla, Ana-Maria; Bengoetxea, Ana; Ivanenko, Yuri; Dan, Bernard; Cheron, Guy

    2013-01-01

    The existence of dedicated neuronal modules such as those organized in the cerebral cortex, thalamus, basal ganglia, cerebellum, or spinal cord raises the question of how these functional modules are coordinated for appropriate motor behavior. Study of human locomotion offers an interesting field for addressing this central question. The coordination of the elevation of the 3 leg segments under a planar covariation rule (Borghese et al., 1996) was recently modeled (Barliya et al., 2009) by phase-adjusted simple oscillators shedding new light on the understanding of the central pattern generator (CPG) processing relevant oscillation signals. We describe the use of a dynamic recurrent neural network (DRNN) mimicking the natural oscillatory behavior of human locomotion for reproducing the planar covariation rule in both legs at different walking speeds. Neural network learning was based on sinusoid signals integrating frequency and amplitude features of the first three harmonics of the sagittal elevation angles of the thigh, shank, and foot of each lower limb. We verified the biological plausibility of the neural networks. Best results were obtained with oscillations extracted from the first three harmonics in comparison to oscillations outside the harmonic frequency peaks. Physiological replication steadily increased with the number of neuronal units from 1 to 80, where similarity index reached 0.99. Analysis of synaptic weighting showed that the proportion of inhibitory connections consistently increased with the number of neuronal units in the DRNN. This emerging property in the artificial neural networks resonates with recent advances in neurophysiology of inhibitory neurons that are involved in central nervous system oscillatory activities. The main message of this study is that this type of DRNN may offer a useful model of physiological central pattern generator for gaining insights in basic research and developing clinical applications.

  17. Effect of signal noise on the learning capability of an artificial neural network

    Science.gov (United States)

    Vega, J. J.; Reynoso, R.; Calvet, H. Carrillo

    2009-07-01

    Digital Pulse Shape Analysis (DPSA) by artificial neural networks (ANN) is becoming an important tool to extract relevant information from digitized signals in different areas. In this paper, we present a systematic evidence of how the concomitant noise that distorts the signals or patterns to be identified by an ANN set limits to its learning capability. Also, we present evidence that explains overtraining as a competition between the relevant pattern features, on the one side, against the signal noise, on the other side, as the main cause defining the shape of the error surface in weight space and, consequently, determining the steepest descent path that controls the ANN adaptation process.

  18. Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule.

    Science.gov (United States)

    Lee, D L

    2001-01-01

    Jankowski et al. proposed (1996) a complex-valued neural network (CVNN) which is capable of storing and recalling gray-scale images. The convergence property of the CVNN has also been proven by means of the energy function approach. However, the memory capacity of the CVNN is very low because they use a generalized Hebb rule to construct the connection matrix. In this letter, a modified gradient descent learning rule (MGDR) is proposed to enhance the capacity of the CVNN. The proposed technique is derived by applying gradient search over a complex error surface. Simulation shows that the capacity of CVNN with MGDR is greatly improved.

  19. Effect of signal noise on the learning capability of an artificial neural network

    Energy Technology Data Exchange (ETDEWEB)

    Vega, J.J. [Departamento del Acelerador, Gerencia de Ciencias Ambientales, Instituto Nacional de Investigaciones Nucleares, Apartado Postal 18-1027, Mexico D.F. 11801 (Mexico)], E-mail: jjvc@nuclear.inin.mx; Reynoso, R. [Departamento del Acelerador, Gerencia de Ciencias Ambientales, Instituto Nacional de Investigaciones Nucleares, Apartado Postal 18-1027, Mexico D.F. 11801 (Mexico); Calvet, H. Carrillo [Laboratorio de Dinamica no Lineal, Facultad de Ciencias, Universidad Nacional Autonoma de Mexico, Mexico D.F. 04510 (Mexico)

    2009-07-21

    Digital Pulse Shape Analysis (DPSA) by artificial neural networks (ANN) is becoming an important tool to extract relevant information from digitized signals in different areas. In this paper, we present a systematic evidence of how the concomitant noise that distorts the signals or patterns to be identified by an ANN set limits to its learning capability. Also, we present evidence that explains overtraining as a competition between the relevant pattern features, on the one side, against the signal noise, on the other side, as the main cause defining the shape of the error surface in weight space and, consequently, determining the steepest descent path that controls the ANN adaptation process.

  20. 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...... tasks, mixed results have been reported, and little is known about the conditions under which MTL leads to gains in NLP. This paper sheds light on the specific task relations that can lead to gains from MTL models over single-task setups....

  1. 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.

  2. 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

  3. 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…

  4. Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems

    Science.gov (United States)

    Lima, Pedro; Beard, Randal

    1992-01-01

    The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a

  5. Learning Control of Fixed-Wing Unmanned Aerial Vehicles Using Fuzzy Neural Networks

    Directory of Open Access Journals (Sweden)

    Erdal Kayacan

    2017-01-01

    Full Text Available A learning control strategy is preferred for the control and guidance of a fixed-wing unmanned aerial vehicle to deal with lack of modeling and flight uncertainties. For learning the plant model as well as changing working conditions online, a fuzzy neural network (FNN is used in parallel with a conventional P (proportional controller. Among the learning algorithms in the literature, a derivative-free one, sliding mode control (SMC theory-based learning algorithm, is preferred as it has been proved to be computationally efficient in real-time applications. Its proven robustness and finite time converging nature make the learning algorithm appropriate for controlling an unmanned aerial vehicle as the computational power is always limited in unmanned aerial vehicles (UAVs. The parameter update rules and stability conditions of the learning are derived, and the proof of the stability of the learning algorithm is shown by using a candidate Lyapunov function. Intensive simulations are performed to illustrate the applicability of the proposed controller which includes the tracking of a three-dimensional trajectory by the UAV subject to time-varying wind conditions. The simulation results show the efficiency of the proposed control algorithm, especially in real-time control systems because of its computational efficiency.

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

    Science.gov (United States)

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

    2015-01-01

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

  7. Learning from adaptive neural network output feedback control of a unicycle-type mobile robot.

    Science.gov (United States)

    Zeng, Wei; Wang, Qinghui; Liu, Fenglin; Wang, Ying

    2016-03-01

    This paper studies learning from adaptive neural network (NN) output feedback control of nonholonomic unicycle-type mobile robots. The major difficulties are caused by the unknown robot system dynamics and the unmeasurable states. To overcome these difficulties, a new adaptive control scheme is proposed including designing a new adaptive NN output feedback controller and two high-gain observers. It is shown that the stability of the closed-loop robot system and the convergence of tracking errors are guaranteed. The unknown robot system dynamics can be approximated by radial basis function NNs. When repeating same or similar control tasks, the learned knowledge can be recalled and reused to achieve guaranteed stability and better control performance, thereby avoiding the tremendous repeated training process of NNs. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

  8. Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network

    CERN Document Server

    Zhang, Hanming; Qiao, Kai; Wang, Linyuan; Yan, Bin; Li, Lei; Hu, Guoen

    2016-01-01

    Limited angle problem is a challenging issue in x-ray computed tomography (CT) field. Iterative reconstruction methods that utilize the additional prior can suppress artifacts and improve image quality, but unfortunately require increased computation time. An interesting way is to restrain the artifacts in the images reconstructed from the practical ?ltered back projection (FBP) method. Frikel and Quinto have proved that the streak artifacts in FBP results could be characterized. It indicates that the artifacts created by FBP method have specific and similar characteristics in a stationary limited-angle scanning configuration. Based on this understanding, this work aims at developing a method to extract and suppress specific artifacts of FBP reconstructions for limited-angle tomography. A data-driven learning-based method is proposed based on a deep convolutional neural network. An end-to-end mapping between the FBP and artifact-free images is learned and the implicit features involving artifacts will be extr...

  9. Machine Learning for Information Retrieval: Neural Networks, Symbolic Learning, and Genetic Algorithms.

    Science.gov (United States)

    Chen, Hsinchun

    1995-01-01

    Presents an overview of artificial-intelligence-based inductive learning techniques and their use in information science research. Three methods are discussed: the connectionist Hopfield network; the symbolic ID3/ID5R; evolution-based genetic algorithms. The knowledge representations and algorithms of these methods are examined in the context of…

  10. Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks

    OpenAIRE

    Chen, Mingzhe; Challita, Ursula; Saad, Walid; Yin, Changchuan; Debbah, Mérouane

    2017-01-01

    Next-generation wireless networks must support ultra-reliable, low-latency communication and intelligently manage a massive number of Internet of Things (IoT) devices in real-time, within a highly dynamic environment. This need for stringent communication quality-of-service (QoS) requirements as well as mobile edge and core intelligence can only be realized by integrating fundamental notions of artificial intelligence (AI) and machine learning across the wireless infrastructure and end-user d...

  11. Complementary learning systems within the hippocampus: a neural network modelling approach to reconciling episodic memory with statistical learning.

    Science.gov (United States)

    Schapiro, Anna C; Turk-Browne, Nicholas B; Botvinick, Matthew M; Norman, Kenneth A

    2017-01-05

    A growing literature suggests that the hippocampus is critical for the rapid extraction of regularities from the environment. Although this fits with the known role of the hippocampus in rapid learning, it seems at odds with the idea that the hippocampus specializes in memorizing individual episodes. In particular, the Complementary Learning Systems theory argues that there is a computational trade-off between learning the specifics of individual experiences and regularities that hold across those experiences. We asked whether it is possible for the hippocampus to handle both statistical learning and memorization of individual episodes. We exposed a neural network model that instantiates known properties of hippocampal projections and subfields to sequences of items with temporal regularities. We found that the monosynaptic pathway-the pathway connecting entorhinal cortex directly to region CA1-was able to support statistical learning, while the trisynaptic pathway-connecting entorhinal cortex to CA1 through dentate gyrus and CA3-learned individual episodes, with apparent representations of regularities resulting from associative reactivation through recurrence. Thus, in paradigms involving rapid learning, the computational trade-off between learning episodes and regularities may be handled by separate anatomical pathways within the hippocampus itself.This article is part of the themed issue 'New frontiers for statistical learning in the cognitive sciences'. © 2016 The Author(s).

  12. Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis.

    Science.gov (United States)

    Christodoulidis, Stergios; Anthimopoulos, Marios; Ebner, Lukas; Christe, Andreas; Mougiakakou, Stavroula

    2017-01-01

    Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns, and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture.

  13. Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

    Directory of Open Access Journals (Sweden)

    Haobo Lyu

    2016-06-01

    Full Text Available When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1 the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2 the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3 to the authors’ best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

  14. A method for medulloblastoma tumor differentiation based on convolutional neural networks and transfer learning

    Science.gov (United States)

    Cruz-Roa, Angel; Arévalo, John; Judkins, Alexander; Madabhushi, Anant; González, Fabio

    2015-12-01

    Convolutional neural networks (CNN) have been very successful at addressing different computer vision tasks thanks to their ability to learn image representations directly from large amounts of labeled data. Features learned from a dataset can be used to represent images from a different dataset via an approach called transfer learning. In this paper we apply transfer learning to the challenging task of medulloblastoma tumor differentiation. We compare two different CNN models which were previously trained in two different domains (natural and histopathology images). The first CNN is a state-of-the-art approach in computer vision, a large and deep CNN with 16-layers, Visual Geometry Group (VGG) CNN. The second (IBCa-CNN) is a 2-layer CNN trained for invasive breast cancer tumor classification. Both CNNs are used as visual feature extractors of histopathology image regions of anaplastic and non-anaplastic medulloblastoma tumor from digitized whole-slide images. The features from the two models are used, separately, to train a softmax classifier to discriminate between anaplastic and non-anaplastic medulloblastoma image regions. Experimental results show that the transfer learning approach produce competitive results in comparison with the state of the art approaches for IBCa detection. Results also show that features extracted from the IBCa-CNN have better performance in comparison with features extracted from the VGG-CNN. The former obtains 89.8% while the latter obtains 76.6% in terms of average accuracy.

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

    Science.gov (United States)

    Lary, David J.; Mussa, Yussuf

    2004-01-01

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

  16. Application of neural networks and other machine learning algorithms to DNA sequence analysis

    Energy Technology Data Exchange (ETDEWEB)

    Lapedes, A.; Barnes, C.; Burks, C.; Farber, R.; Sirotkin, K.

    1988-01-01

    In this article we report initial, quantitative results on application of simple neutral networks, and simple machine learning methods, to two problems in DNA sequence analysis. The two problems we consider are: (1) determination of whether procaryotic and eucaryotic DNA sequences segments are translated to protein. An accuracy of 99.4% is reported for procaryotic DNA (E. coli) and 98.4% for eucaryotic DNA (H. Sapiens genes known to be expressed in liver); (2) determination of whether eucaryotic DNA sequence segments containing the dinucleotides ''AG'' or ''GT'' are transcribed to RNA splice junctions. Accuracy of 91.2% was achieved on intron/exon splice junctions (acceptor sites) and 92.8% on exon/intron splice junctions (donor sites). The solution of these two problems, by use of information processing algorithms operating on unannotated base sequences and without recourse to biological laboratory work, is relevant to the Human Genome Project. A variety of neural network, machine learning, and information theoretic algorithms are used. The accuracies obtained exceed those of previous investigations for which quantitative results are available in the literature. They result from an ongoing program of research that applies machine learning algorithms to the problem of determining biological function of DNA sequences. Some predictions of possible new genes using these methods are listed -- although a complete survey of the H. sapiens and E. coli sections of GenBank will be given elsewhere. 36 refs., 6 figs., 6 tabs.

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

    Science.gov (United States)

    Kim, Lok-Won

    2017-03-08

    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 1024 x 1024 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).

  18. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

    Science.gov (United States)

    Hoo-Chang, Shin; Roth, Holger R.; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel

    2016-01-01

    Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets (i.e. ImageNet) and the revival of deep convolutional neural networks (CNN). CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models (supervised) pre-trained from natural image dataset to medical image tasks (although domain transfer between two medical image datasets is also possible). In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computeraided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance

  19. Deep learning with convolutional neural networks for EEG decoding and visualization.

    Science.gov (United States)

    Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

    2017-11-01

    Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

  20. Deep learning with convolutional neural networks for EEG decoding and visualization

    Science.gov (United States)

    Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

    2017-01-01

    Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

  1. Spiking Neural Network With Distributed Plasticity Reproduces Cerebellar Learning in Eye Blink Conditioning Paradigms.

    Science.gov (United States)

    Antonietti, Alberto; Casellato, Claudia; Garrido, Jesús A; Luque, Niceto R; Naveros, Francisco; Ros, Eduardo; D' Angelo, Egidio; Pedrocchi, Alessandra

    2016-01-01

    In this study, we defined a realistic cerebellar model through the use of artificial spiking neural networks, testing it in computational simulations that reproduce associative motor tasks in multiple sessions of acquisition and extinction. By evolutionary algorithms, we tuned the cerebellar microcircuit to find out the near-optimal plasticity mechanism parameters that better reproduced human-like behavior in eye blink classical conditioning, one of the most extensively studied paradigms related to the cerebellum. We used two models: one with only the cortical plasticity and another including two additional plasticity sites at nuclear level. First, both spiking cerebellar models were able to well reproduce the real human behaviors, in terms of both "timing" and "amplitude", expressing rapid acquisition, stable late acquisition, rapid extinction, and faster reacquisition of an associative motor task. Even though the model with only the cortical plasticity site showed good learning capabilities, the model with distributed plasticity produced faster and more stable acquisition of conditioned responses in the reacquisition phase. This behavior is explained by the effect of the nuclear plasticities, which have slow dynamics and can express memory consolidation and saving. We showed how the spiking dynamics of multiple interactive neural mechanisms implicitly drive multiple essential components of complex learning processes.  This study presents a very advanced computational model, developed together by biomedical engineers, computer scientists, and neuroscientists. Since its realistic features, the proposed model can provide confirmations and suggestions about neurophysiological and pathological hypotheses and can be used in challenging clinical applications.

  2. Neural Networks: Implementations and Applications

    NARCIS (Netherlands)

    Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.

    1996-01-01

    Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

  3. A neural network-based exploratory learning and motor planning system for co-robots

    Directory of Open Access Journals (Sweden)

    Byron V Galbraith

    2015-07-01

    Full Text Available Collaborative robots, or co-robots, are semi-autonomous robotic agents designed to work alongside humans in shared workspaces. To be effective, co-robots require the ability to respond and adapt to dynamic scenarios encountered in natural environments. One way to achieve this is through exploratory learning, or learning by doing, an unsupervised method in which co-robots are able to build an internal model for motor planning and coordination based on real-time sensory inputs. In this paper, we present an adaptive neural network-based system for co-robot control that employs exploratory learning to achieve the coordinated motor planning needed to navigate toward, reach for, and grasp distant objects. To validate this system we used the 11-degrees-of-freedom RoPro Calliope mobile robot. Through motor babbling of its wheels and arm, the Calliope learned how to relate visual and proprioceptive information to achieve hand-eye-body coordination. By continually evaluating sensory inputs and externally provided goal directives, the Calliope was then able to autonomously select the appropriate wheel and joint velocities needed to perform its assigned task, such as following a moving target or retrieving an indicated object.

  4. A neural network-based exploratory learning and motor planning system for co-robots.

    Science.gov (United States)

    Galbraith, Byron V; Guenther, Frank H; Versace, Massimiliano

    2015-01-01

    Collaborative robots, or co-robots, are semi-autonomous robotic agents designed to work alongside humans in shared workspaces. To be effective, co-robots require the ability to respond and adapt to dynamic scenarios encountered in natural environments. One way to achieve this is through exploratory learning, or "learning by doing," an unsupervised method in which co-robots are able to build an internal model for motor planning and coordination based on real-time sensory inputs. In this paper, we present an adaptive neural network-based system for co-robot control that employs exploratory learning to achieve the coordinated motor planning needed to navigate toward, reach for, and grasp distant objects. To validate this system we used the 11-degrees-of-freedom RoPro Calliope mobile robot. Through motor babbling of its wheels and arm, the Calliope learned how to relate visual and proprioceptive information to achieve hand-eye-body coordination. By continually evaluating sensory inputs and externally provided goal directives, the Calliope was then able to autonomously select the appropriate wheel and joint velocities needed to perform its assigned task, such as following a moving target or retrieving an indicated object.

  5. A Deep Learning based Approach to Reduced Order Modeling of Fluids using LSTM Neural Networks

    Science.gov (United States)

    Mohan, Arvind; Gaitonde, Datta

    2017-11-01

    Reduced Order Modeling (ROM) can be used as surrogates to prohibitively expensive simulations to model flow behavior for long time periods. ROM is predicated on extracting dominant spatio-temporal features of the flow from CFD or experimental datasets. We explore ROM development with a deep learning approach, which comprises of learning functional relationships between different variables in large datasets for predictive modeling. Although deep learning and related artificial intelligence based predictive modeling techniques have shown varied success in other fields, such approaches are in their initial stages of application to fluid dynamics. Here, we explore the application of the Long Short Term Memory (LSTM) neural network to sequential data, specifically to predict the time coefficients of Proper Orthogonal Decomposition (POD) modes of the flow for future timesteps, by training it on data at previous timesteps. The approach is demonstrated by constructing ROMs of several canonical flows. Additionally, we show that statistical estimates of stationarity in the training data can indicate a priori how amenable a given flow-field is to this approach. Finally, the potential and limitations of deep learning based ROM approaches will be elucidated and further developments discussed.

  6. 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…

  7. A Study of the Classification Capabilities of Neural Networks Using Unsupervised Learning: A Comparison with K-Means Clustering.

    Science.gov (United States)

    Balakrishnan, P. V. (Sunder); And Others

    1994-01-01

    A simulation study compares nonhierarchical clustering capabilities of a class of neural networks using Kohonen learning with a K-means clustering procedure. The focus is on the ability of the procedures to recover correctly the known cluster structure in the data. Advantages and disadvantages of the procedures are reviewed. (SLD)

  8. Visual Control of Autonomous Vehicle by Neural Networks Using Fuzzy-Supervised Learning

    Energy Technology Data Exchange (ETDEWEB)

    Ryoo, Young Jae [Kumho Information and Telecommunications Laboratory, Kwangju (Korea, Republic of); Lim, Young Cheol [Cheonnam National University, Kwangju (Korea, Republic of)

    1997-04-01

    This paper describes a control scheme for an autonomous vehicle with visual sensors, which uses visual information to guide itself along roadways. The control system integrates visual data into the steering servo process directly, instead of subdividing the process by geometric reasoning for a vehicle-centered representation of the road from two-dimensional visual image data. A neural network using fuzzy-supervised learning is used for determining the steering angle required to move the vanishing point and vanishing line of the road to the desired position in the camera image. The validity and the effectiveness of the proposed control scheme are confirmed by a computer simulation of the autonomous vehicle`s driving performance. (author). 12 refs., 8 figs., 4 tabs.

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

    Directory of Open Access Journals (Sweden)

    Yang Liu

    2015-01-01

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

  10. Hybrid Spintronic-CMOS Spiking Neural Network with On-Chip Learning: Devices, Circuits, and Systems

    Science.gov (United States)

    Sengupta, Abhronil; Banerjee, Aparajita; Roy, Kaushik

    2016-12-01

    Over the past decade, spiking neural networks (SNNs) have emerged as one of the popular architectures to emulate the brain. In SNNs, information is temporally encoded and communication between neurons is accomplished by means of spikes. In such networks, spike-timing-dependent plasticity mechanisms require the online programing of synapses based on the temporal information of spikes transmitted by spiking neurons. In this work, we propose a spintronic synapse with decoupled spike-transmission and programing-current paths. The spintronic synapse consists of a ferromagnet-heavy-metal heterostructure where the programing current through the heavy metal generates spin-orbit torque to modulate the device conductance. Low programing energy and fast programing times demonstrate the efficacy of the proposed device as a nanoelectronic synapse. We perform a simulation study based on an experimentally benchmarked device-simulation framework to demonstrate the interfacing of such spintronic synapses with CMOS neurons and learning circuits operating in the transistor subthreshold region to form a network of spiking neurons that can be utilized for pattern-recognition problems.

  11. Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

    Directory of Open Access Journals (Sweden)

    Weixun Zhou

    2017-05-01

    Full Text Available Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs for high-resolution remote sensing image retrieval (HRRSIR. To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.

  12. Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

    Science.gov (United States)

    Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L

    2016-07-01

    Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text

  13. Oscillatory neural network for pattern recognition: trajectory based classification and supervised learning.

    Science.gov (United States)

    Miller, Vonda H; Jansen, Ben H

    2008-12-01

    Computer algorithms that match human performance in recognizing written text or spoken conversation remain elusive. The reasons why the human brain far exceeds any existing recognition scheme to date in the ability to generalize and to extract invariant characteristics relevant to category matching are not clear. However, it has been postulated that the dynamic distribution of brain activity (spatiotemporal activation patterns) is the mechanism by which stimuli are encoded and matched to categories. This research focuses on supervised learning using a trajectory based distance metric for category discrimination in an oscillatory neural network model. Classification is accomplished using a trajectory based distance metric. Since the distance metric is differentiable, a supervised learning algorithm based on gradient descent is demonstrated. Classification of spatiotemporal frequency transitions and their relation to a priori assessed categories is shown along with the improved classification results after supervised training. The results indicate that this spatiotemporal representation of stimuli and the associated distance metric is useful for simple pattern recognition tasks and that supervised learning improves classification results.

  14. Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Na Li

    2016-01-01

    Full Text Available Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

  15. Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks.

    Science.gov (United States)

    Kelley, David R; Snoek, Jasper; Rinn, John L

    2016-07-01

    The complex language of eukaryotic gene expression remains incompletely understood. Despite the importance suggested by many noncoding variants statistically associated with human disease, nearly all such variants have unknown mechanisms. Here, we address this challenge using an approach based on a recent machine learning advance-deep convolutional neural networks (CNNs). We introduce the open source package Basset to apply CNNs to learn the functional activity of DNA sequences from genomics data. We trained Basset on a compendium of accessible genomic sites mapped in 164 cell types by DNase-seq, and demonstrate greater predictive accuracy than previous methods. Basset predictions for the change in accessibility between variant alleles were far greater for Genome-wide association study (GWAS) SNPs that are likely to be causal relative to nearby SNPs in linkage disequilibrium with them. With Basset, a researcher can perform a single sequencing assay in their cell type of interest and simultaneously learn that cell's chromatin accessibility code and annotate every mutation in the genome with its influence on present accessibility and latent potential for accessibility. Thus, Basset offers a powerful computational approach to annotate and interpret the noncoding genome. © 2016 Kelley et al.; Published by Cold Spring Harbor Laboratory Press.

  16. 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.

  17. Hidden neural networks

    DEFF Research Database (Denmark)

    Krogh, Anders Stærmose; Riis, Søren Kamaric

    1999-01-01

    A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...

  18. A neural network model for familiarity and context learning during honeybee foraging flights.

    Science.gov (United States)

    Müller, Jurek; Nawrot, Martin; Menzel, Randolf; Landgraf, Tim

    2017-09-15

    How complex is the memory structure that honeybees use to navigate? Recently, an insect-inspired parsimonious spiking neural network model was proposed that enabled simulated ground-moving agents to follow learned routes. We adapted this model to flying insects and evaluate the route following performance in three different worlds with gradually decreasing object density. In addition, we propose an extension to the model to enable the model to associate sensory input with a behavioral context, such as foraging or homing. The spiking neural network model makes use of a sparse stimulus representation in the mushroom body and reward-based synaptic plasticity at its output synapses. In our experiments, simulated bees were able to navigate correctly even when panoramic cues were missing. The context extension we propose enabled agents to successfully discriminate partly overlapping routes. The structure of the visual environment, however, crucially determines the success rate. We find that the model fails more often in visually rich environments due to the overlap of features represented by the Kenyon cell layer. Reducing the landmark density improves the agents route following performance. In very sparse environments, we find that extended landmarks, such as roads or field edges, may help the agent stay on its route, but often act as strong distractors yielding poor route following performance. We conclude that the presented model is valid for simple route following tasks and may represent one component of insect navigation. Additional components might still be necessary for guidance and action selection while navigating along different memorized routes in complex natural environments.

  19. An Optoelectronic Neural Network

    Science.gov (United States)

    Neil, Mark A. A.; White, Ian H.; Carroll, John E.

    1990-02-01

    We describe and present results of an optoelectronic neural network processing system. The system uses an algorithm based on the Hebbian learning rule to memorise a set of associated vector pairs. Recall occurs by the processing of the input vector with these stored associations in an incoherent optical vector multiplier using optical polarisation rotating liquid crystal spatial light modulators to store the vectors and an optical polarisation shadow casting technique to perform multiplications. Results are detected on a photodiode array and thresholded electronically by a controlling microcomputer. The processor is shown to work in autoassociative and heteroassociative modes with up to 10 stored memory vectors of length 64 (equivalent to 64 neurons) and a cycle time of 50ms. We discuss the limiting factors at work in this system, how they affect its scalability and the general applicability of its principles to other systems.

  20. Neural Network Ensembles

    DEFF Research Database (Denmark)

    Hansen, Lars Kai; Salamon, Peter

    1990-01-01

    We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....

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

    Science.gov (United States)

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

    2016-03-01

    Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate

  2. Fuzzy neural networks: theory and applications

    Science.gov (United States)

    Gupta, Madan M.

    1994-10-01

    During recent years, significant advances have been made in two distinct technological areas: fuzzy logic and computational neural networks. The theory of fuzzy logic provides a mathematical framework to capture the uncertainties associated with human cognitive processes, such as thinking and reasoning. It also provides a mathematical morphology to emulate certain perceptual and linguistic attributes associated with human cognition. On the other hand, the computational neural network paradigms have evolved in the process of understanding the incredible learning and adaptive features of neuronal mechanisms inherent in certain biological species. Computational neural networks replicate, on a small scale, some of the computational operations observed in biological learning and adaptation. The integration of these two fields, fuzzy logic and neural networks, have given birth to an emerging technological field -- fuzzy neural networks. Fuzzy neural networks, have the potential to capture the benefits of these two fascinating fields, fuzzy logic and neural networks, into a single framework. The intent of this tutorial paper is to describe the basic notions of biological and computational neuronal morphologies, and to describe the principles and architectures of fuzzy neural networks. Towards this goal, we develop a fuzzy neural architecture based upon the notion of T-norm and T-conorm connectives. An error-based learning scheme is described for this neural structure.

  3. CAPES: Unsupervised Storage Performance Tuning Using Neural Network-Based Deep Reinforcement Learning

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Parameter tuning is an important task of storage performance optimization. Current practice usually involves numerous tweak-benchmark cycles that are slow and costly. To address this issue, we developed CAPES, a model-less deep reinforcement learning-based unsupervised parameter tuning system driven by a deep neural network (DNN). It is designed to nd the optimal values of tunable parameters in computer systems, from a simple client-server system to a large data center, where human tuning can be costly and often cannot achieve optimal performance. CAPES takes periodic measurements of a target computer system’s state, and trains a DNN which uses Q-learning to suggest changes to the system’s current parameter values. CAPES is minimally intrusive, and can be deployed into a production system to collect training data and suggest tuning actions during the system’s daily operation. Evaluation of a prototype on a Lustre system demonstrates an increase in I/O throughput up to 45% at saturation point. About the...

  4. Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

    Science.gov (United States)

    Zhou, Weixun; Newsam, Shawn; Li, Congmin; Shao, Zhenfeng

    2017-05-01

    Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the content complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNN) for high-resolution remote sensing image retrieval (HRRSIR). To this end, two effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, the deep features are extracted from the fully-connected and convolutional layers of the pre-trained CNN models, respectively; in the second scheme, we propose a novel CNN architecture based on conventional convolution layers and a three-layer perceptron. The novel CNN model is then trained on a large remote sensing dataset to learn low dimensional features. The two schemes are evaluated on several public and challenging datasets, and the results indicate that the proposed schemes and in particular the novel CNN are able to achieve state-of-the-art performance.

  5. Critical Branching Neural Networks

    Science.gov (United States)

    Kello, Christopher T.

    2013-01-01

    It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…

  6. Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications

    Science.gov (United States)

    Ferreria, Paulo; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy; Bilen, Sven; Reinhart, Richard; Mortensen, Dale

    2017-01-01

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

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

    Science.gov (United States)

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

    2017-01-01

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

  8. Three-terminal ferroelectric synapse device with concurrent learning function for artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Nishitani, Y.; Kaneko, Y.; Ueda, M.; Fujii, E. [Advanced Technology Research Laboratories, Panasonic Corporation, Seika, Kyoto 619-0237 (Japan); Morie, T. [Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Wakamatsu-ku, Kitakyushu 808-0196 (Japan)

    2012-06-15

    Spike-timing-dependent synaptic plasticity (STDP) is demonstrated in a synapse device based on a ferroelectric-gate field-effect transistor (FeFET). STDP is a key of the learning functions observed in human brains, where the synaptic weight changes only depending on the spike timing of the pre- and post-neurons. The FeFET is composed of the stacked oxide materials with ZnO/Pr(Zr,Ti)O{sub 3} (PZT)/SrRuO{sub 3}. In the FeFET, the channel conductance can be altered depending on the density of electrons induced by the polarization of PZT film, which can be controlled by applying the gate voltage in a non-volatile manner. Applying a pulse gate voltage enables the multi-valued modulation of the conductance, which is expected to be caused by a change in PZT polarization. This variation depends on the height and the duration of the pulse gate voltage. Utilizing these characteristics, symmetric and asymmetric STDP learning functions are successfully implemented in the FeFET-based synapse device by applying the non-linear pulse gate voltage generated from a set of two pulses in a sampling circuit, in which the two pulses correspond to the spikes from the pre- and post-neurons. The three-terminal structure of the synapse device enables the concurrent learning, in which the weight update can be performed without canceling signal transmission among neurons, while the neural networks using the previously reported two-terminal synapse devices need to stop signal transmission for learning.

  9. Neural network applications

    Science.gov (United States)

    Padgett, Mary L.; Desai, Utpal; Roppel, T.A.; White, Charles R.

    1993-01-01

    A design procedure is suggested for neural networks which accommodates the inclusion of such knowledge-based systems techniques as fuzzy logic and pairwise comparisons. The use of these procedures in the design of applications combines qualitative and quantitative factors with empirical data to yield a model with justifiable design and parameter selection procedures. The procedure is especially relevant to areas of back-propagation neural network design which are highly responsive to the use of precisely recorded expert knowledge.

  10. An Indoor Positioning Technique Based on a Feed-Forward Artificial Neural Network Using Levenberg-Marquardt Learning Method

    Science.gov (United States)

    Pahlavani, P.; Gholami, A.; Azimi, S.

    2017-09-01

    This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF) artificial neural networks (ANN). Most of the indoor received signal strength (RSS)-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration) phase and the online (estimation) phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening). Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg-Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.

  11. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks.

    Science.gov (United States)

    Kim, D H; MacKinnon, T

    2017-12-18

    To identify the extent to which transfer learning from deep convolutional neural networks (CNNs), pre-trained on non-medical images, can be used for automated fracture detection on plain radiographs. The top layer of the Inception v3 network was re-trained using lateral wrist radiographs to produce a model for the classification of new studies as either "fracture" or "no fracture". The model was trained on a total of 11,112 images, after an eightfold data augmentation technique, from an initial set of 1,389 radiographs (695 "fracture" and 694 "no fracture"). The training data set was split 80:10:10 into training, validation, and test groups, respectively. An additional 100 wrist radiographs, comprising 50 "fracture" and 50 "no fracture" images, were used for final testing and statistical analysis. The area under the receiver operator characteristic curve (AUC) for this test was 0.954. Setting the diagnostic cut-off at a threshold designed to maximise both sensitivity and specificity resulted in values of 0.9 and 0.88, respectively. The AUC scores for this test were comparable to state-of-the-art providing proof of concept for transfer learning from CNNs in fracture detection on plain radiographs. This was achieved using only a moderate sample size. This technique is largely transferable, and therefore, has many potential applications in medical imaging, which may lead to significant improvements in workflow productivity and in clinical risk reduction. Copyright © 2017 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

  12. Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

    Science.gov (United States)

    Chen, Fangyue; Chen, Guanrong Ron; He, Guolong; Xu, Xiubin; He, Qinbin

    2009-10-01

    Universal perceptron (UP), a generalization of Rosenblatt's perceptron, is considered in this paper, which is capable of implementing all Boolean functions (BFs). In the classification of BFs, there are: 1) linearly separable Boolean function (LSBF) class, 2) parity Boolean function (PBF) class, and 3) non-LSBF and non-PBF class. To implement these functions, UP takes different kinds of simple topological structures in which each contains at most one hidden layer along with the smallest possible number of hidden neurons. Inspired by the concept of DNA sequences in biological systems, a novel learning algorithm named DNA-like learning is developed, which is able to quickly train a network with any prescribed BF. The focus is on performing LSBF and PBF by a single-layer perceptron (SLP) with the new algorithm. Two criteria for LSBF and PBF are proposed, respectively, and a new measure for a BF, named nonlinearly separable degree (NLSD), is introduced. In the sense of this measure, the PBF is the most complex one. The new algorithm has many advantages including, in particular, fast running speed, good robustness, and no need of considering the convergence property. For example, the number of iterations and computations in implementing the basic 2-bit logic operations such as AND, OR, and XOR by using the new algorithm is far smaller than the ones needed by using other existing algorithms such as error-correction (EC) and backpropagation (BP) algorithms. Moreover, the synaptic weights and threshold values derived from UP can be directly used in designing of the template of cellular neural networks (CNNs), which has been considered as a new spatial-temporal sensory computing paradigm.

  13. The No-Prop algorithm: a new learning algorithm for multilayer neural networks.

    Science.gov (United States)

    Widrow, Bernard; Greenblatt, Aaron; Kim, Youngsik; Park, Dookun

    2013-01-01

    A new learning algorithm for multilayer neural networks that we have named No-Propagation (No-Prop) is hereby introduced. With this algorithm, the weights of the hidden-layer neurons are set and fixed with random values. Only the weights of the output-layer neurons are trained, using steepest descent to minimize mean square error, with the LMS algorithm of Widrow and Hoff. The purpose of introducing nonlinearity with the hidden layers is examined from the point of view of Least Mean Square Error Capacity (LMS Capacity), which is defined as the maximum number of distinct patterns that can be trained into the network with zero error. This is shown to be equal to the number of weights of each of the output-layer neurons. The No-Prop algorithm and the Back-Prop algorithm are compared. Our experience with No-Prop is limited, but from the several examples presented here, it seems that the performance regarding training and generalization of both algorithms is essentially the same when the number of training patterns is less than or equal to LMS Capacity. When the number of training patterns exceeds Capacity, Back-Prop is generally the better performer. But equivalent performance can be obtained with No-Prop by increasing the network Capacity by increasing the number of neurons in the hidden layer that drives the output layer. The No-Prop algorithm is much simpler and easier to implement than Back-Prop. Also, it converges much faster. It is too early to definitively say where to use one or the other of these algorithms. This is still a work in progress. Copyright © 2012 Elsevier Ltd. All rights reserved.

  14. Self-organization of neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Clark, J.W.; Winston, J.V.; Rafelski, J.

    1984-05-14

    The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (brainwashing) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conducive to the simulation of memory and learning phenomena. 18 references, 2 figures.

  15. Adaptive Neurons For Artificial Neural Networks

    Science.gov (United States)

    Tawel, Raoul

    1990-01-01

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

  16. Neural correlates of motor learning, transfer of learning, and learning to learn.

    Science.gov (United States)

    Seidler, Rachael D

    2010-01-01

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

  17. 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

  18. Influence of Acoustic Feedback on the Learning Strategies of Neural Network-Based Sound Classifiers in Digital Hearing Aids

    Directory of Open Access Journals (Sweden)

    Lorena Álvarez

    2009-01-01

    Full Text Available Sound classifiers embedded in digital hearing aids are usually designed by using sound databases that do not include the distortions associated to the feedback that often occurs when these devices have to work at high gain and low gain margin to oscillation. The consequence is that the classifier learns inappropriate sound patterns. In this paper we explore the feasibility of using different sound databases (generated according to 18 configurations of real patients, and a variety of learning strategies for neural networks in the effort of reducing the probability of erroneous classification. The experimental work basically points out that the proposed methods assist the neural network-based classifier in reducing its error probability in more than 18%. This helps enhance the elderly user's comfort: the hearing aid automatically selects, with higher success probability, the program that is best adapted to the changing acoustic environment the user is facing.

  19. Hindcasting cyclonic waves using neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Rao, S.; Chakravarty, N.V.

    the backpropagation networks with updated algorithms are used in this paper. A brief description about the working of a back propagation neural network and three updated algorithms is given below. Backpropagation learning: Backpropagation is the most widely used... algorithm for supervised learning with multi layer feed forward networks. The idea of the backpropagation learning algorithm is the repeated application of the chain rule to compute the influence of each weight in the network with respect to an arbitrary...

  20. On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks: e79138

    National Research Council Canada - National Science Library

    Paul Tonelli; Jean-Baptiste Mouret

    2013-01-01

    .... 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...

  1. Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts.

    Science.gov (United States)

    Cocos, Anne; Fiks, Alexander G; Masino, Aaron J

    2017-07-01

    Social media is an important pharmacovigilance data source for adverse drug reaction (ADR) identification. Human review of social media data is infeasible due to data quantity, thus natural language processing techniques are necessary. Social media includes informal vocabulary and irregular grammar, which challenge natural language processing methods. Our objective is to develop a scalable, deep-learning approach that exceeds state-of-the-art ADR detection performance in social media. We developed a recurrent neural network (RNN) model that labels words in an input sequence with ADR membership tags. The only input features are word-embedding vectors, which can be formed through task-independent pretraining or during ADR detection training. Our best-performing RNN model used pretrained word embeddings created from a large, non-domain-specific Twitter dataset. It achieved an approximate match F-measure of 0.755 for ADR identification on the dataset, compared to 0.631 for a baseline lexicon system and 0.65 for the state-of-the-art conditional random field model. Feature analysis indicated that semantic information in pretrained word embeddings boosted sensitivity and, combined with contextual awareness captured in the RNN, precision. Our model required no task-specific feature engineering, suggesting generalizability to additional sequence-labeling tasks. Learning curve analysis showed that our model reached optimal performance with fewer training examples than the other models. ADR detection performance in social media is significantly improved by using a contextually aware model and word embeddings formed from large, unlabeled datasets. The approach reduces manual data-labeling requirements and is scalable to large social media datasets.

  2. Learning Styles' Recognition in E-Learning Environments with Feed-Forward Neural Networks

    Science.gov (United States)

    Villaverde, J. E.; Godoy, D.; Amandi, A.

    2006-01-01

    People have unique ways of learning, which may greatly affect the learning process and, therefore, its outcome. In order to be effective, e-learning systems should be capable of adapting the content of courses to the individual characteristics of students. In this regard, some educational systems have proposed the use of questionnaires for…

  3. Hyperresponsiveness of the Neural Fear Network During Fear Conditioning and Extinction Learning in Male Cocaine Users

    NARCIS (Netherlands)

    Kaag, A.M.; Levar, N.; Woutersen, K.; Homberg, J.; van den Brink, W.; Reneman, L.; van Wingen, G.

    2016-01-01

    OBJECTIVE: The authors investigated whether cocaine use disorder is associated with abnormalities in the neural underpinnings of aversive conditioning and extinction learning, as these processes may play an important role in the development and persistence of drug abuse. METHOD: Forty male regular

  4. Hyperresponsiveness of the Neural Fear Network During Fear Conditioning and Extinction Learning in Male Cocaine Users

    NARCIS (Netherlands)

    Kaag, Anne Marije; Levar, Nina; Woutersen, Karlijn; Homberg, Judith; van den Brink, Wim; Reneman, Liesbeth; van Wingen, Guido

    2016-01-01

    The authors investigated whether cocaine use disorder is associated with abnormalities in the neural underpinnings of aversive conditioning and extinction learning, as these processes may play an important role in the development and persistence of drug abuse. Forty male regular cocaine users and 51

  5. Hyperbolic Hopfield neural networks.

    Science.gov (United States)

    Kobayashi, M

    2013-02-01

    In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states.

  6. Diagnosing coronary artery disease with a backpropagation neural network: Lessons learned

    Energy Technology Data Exchange (ETDEWEB)

    Turner, D.D. [Pacific Northwest Lab., Richland, WA (United States); Holmes, E.R. [Sacred Heart Medical Center, Spokane, WA (United States)

    1995-12-31

    The SPECT (single photon emitted computed tomography) procedure, while widely used for diagnosing coronary artery disease, is not a perfect technology. We have investigated using a backpropagation neural network to diagnose patients suffering from coronary artery disease that is independent from the SPECT procedure. The raw thallium-201 scintigrams produced before the SPECT tomographic reconstruction were used as input patterns for the backpropagation neural network, and the diagnoses resulting mainly from cardiac catheterization as the desired outputs for each pattern. Several preprocessing techniques were applied to the scintigrams, in an attempt to improve the information to noise ratio. After using the a procedure that extracted a subimage containing the heart from each scintigram, we used a data reduction technique, thereby encoding the scintigram in 12 values, which were the inputs to the backpropagation neural network. The network was then trained. This network per-formed superbly for patients suffering from inferolateral disease (classifying 10 out of 10 correctly), but performance was less than optimal for cases involving other coronary zones. While the scope of this project was limited to diagnosing coronary artery disease, this initial work can be extended to other medical imaging procedures, such as diagnosing breast cancer from a mammogram and evaluating lung perfusion studies.

  7. Stochastic Neural Network Approach for Learning High-Dimensional Free Energy Surfaces

    Science.gov (United States)

    Schneider, Elia; Dai, Luke; Topper, Robert Q.; Drechsel-Grau, Christof; Tuckerman, Mark E.

    2017-10-01

    The generation of free energy landscapes corresponding to conformational equilibria in complex molecular systems remains a significant computational challenge. Adding to this challenge is the need to represent, store, and manipulate the often high-dimensional surfaces that result from rare-event sampling approaches employed to compute them. In this Letter, we propose the use of artificial neural networks as a solution to these issues. Using specific examples, we discuss network training using enhanced-sampling methods and the use of the networks in the calculation of ensemble averages.

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

    Science.gov (United States)

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

    2015-11-01

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

  9. 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.

  10. A neural network multi-task learning approach to biomedical named entity recognition.

    Science.gov (United States)

    Crichton, Gamal; Pyysalo, Sampo; Chiu, Billy; Korhonen, Anna

    2017-08-15

    Named Entity Recognition (NER) is a key task in biomedical text mining. Accurate NER systems require task-specific, manually-annotated datasets, which are expensive to develop and thus limited in size. Since such datasets contain related but different information, an interesting question is whether it might be possible to use them together to improve NER performance. To investigate this, we develop supervised, multi-task, convolutional neural network models and apply them to a large number of varied existing biomedical named entity datasets. Additionally, we investigated the effect of dataset size on performance in both single- and multi-task settings. We present a single-task model for NER, a Multi-output multi-task model and a Dependent multi-task model. We apply the three models to 15 biomedical datasets containing multiple named entities including Anatomy, Chemical, Disease, Gene/Protein and Species. Each dataset represent a task. The results from the single-task model and the multi-task models are then compared for evidence of benefits from Multi-task Learning. With the Multi-output multi-task model we observed an average F-score improvement of 0.8% when compared to the single-task model from an average baseline of 78.4%. Although there was a significant drop in performance on one dataset, performance improves significantly for five datasets by up to 6.3%. For the Dependent multi-task model we observed an average improvement of 0.4% when compared to the single-task model. There were no significant drops in performance on any dataset, and performance improves significantly for six datasets by up to 1.1%. The dataset size experiments found that as dataset size decreased, the multi-output model's performance increased compared to the single-task model's. Using 50, 25 and 10% of the training data resulted in an average drop of approximately 3.4, 8 and 16.7% respectively for the single-task model but approximately 0.2, 3.0 and 9.8% for the multi-task model. Our

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

    Directory of Open Access Journals (Sweden)

    Mark D McDonnell

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

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

    Science.gov (United States)

    McDonnell, Mark D; Tissera, Migel D; Vladusich, Tony; van Schaik, André; Tapson, Jonathan

    2015-01-01

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

  13. Introduction to Artificial Neural Networks

    DEFF Research Database (Denmark)

    Larsen, Jan

    1999-01-01

    The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....

  14. Deconvolution using a neural network

    Energy Technology Data Exchange (ETDEWEB)

    Lehman, S.K.

    1990-11-15

    Viewing one dimensional deconvolution as a matrix inversion problem, we compare a neural network backpropagation matrix inverse with LMS, and pseudo-inverse. This is a largely an exercise in understanding how our neural network code works. 1 ref.

  15. Recognition of prokaryotic and eukaryotic promoters using convolutional deep learning neural networks

    KAUST Repository

    Umarov, Ramzan

    2017-02-03

    Accurate computational identification of promoters remains a challenge as these key DNA regulatory regions have variable structures composed of functional motifs that provide gene-specific initiation of transcription. In this paper we utilize Convolutional Neural Networks (CNN) to analyze sequence characteristics of prokaryotic and eukaryotic promoters and build their predictive models. We trained a similar CNN architecture on promoters of five distant organisms: human, mouse, plant (Arabidopsis), and two bacteria (Escherichia coli and Bacillus subtilis). We found that CNN trained on sigma70 subclass of Escherichia coli promoter gives an excellent classification of promoters and non-promoter sequences (Sn = 0.90, Sp = 0.96, CC = 0.84). The Bacillus subtilis promoters identification CNN model achieves Sn = 0.91, Sp = 0.95, and CC = 0.86. For human, mouse and Arabidopsis promoters we employed CNNs for identification of two well-known promoter classes (TATA and non-TATA promoters). CNN models nicely recognize these complex functional regions. For human promoters Sn/Sp/CC accuracy of prediction reached 0.95/0.98/0,90 on TATA and 0.90/0.98/0.89 for non-TATA promoter sequences, respectively. For Arabidopsis we observed Sn/Sp/CC 0.95/0.97/0.91 (TATA) and 0.94/0.94/0.86 (non-TATA) promoters. Thus, the developed CNN models, implemented in CNNProm program, demonstrated the ability of deep learning approach to grasp complex promoter sequence characteristics and achieve significantly higher accuracy compared to the previously developed promoter prediction programs. We also propose random substitution procedure to discover positionally conserved promoter functional elements. As the suggested approach does not require knowledge of any specific promoter features, it can be easily extended to identify promoters and other complex functional regions in sequences of many other and especially newly sequenced genomes. The CNNProm program is available to run at web server http://www.softberry.com.

  16. Artificial neural network modelling

    CERN Document Server

    Samarasinghe, Sandhya

    2016-01-01

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

  17. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

  18. 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.

  19. Learning from a carbon dioxide capture system dataset: Application of the piecewise neural network algorithm

    Directory of Open Access Journals (Sweden)

    Veronica Chan

    2017-03-01

    Full Text Available This paper presents the application of a neural network rule extraction algorithm, called the piece-wise linear artificial neural network or PWL-ANN algorithm, on a carbon capture process system dataset. The objective of the application is to enhance understanding of the intricate relationships among the key process parameters. The algorithm extracts rules in the form of multiple linear regression equations by approximating the sigmoid activation functions of the hidden neurons in an artificial neural network (ANN. The PWL-ANN algorithm overcomes the weaknesses of the statistical regression approach, in which accuracies of the generated predictive models are often not satisfactory, and the opaqueness of the ANN models. The results show that the generated PWL-ANN models have accuracies that are as high as the originally trained ANN models of the four datasets of the carbon capture process system. An analysis of the extracted rules and the magnitude of the coefficients in the equations revealed that the three most significant parameters of the CO2 production rate are the steam flow rate through reboiler, reboiler pressure, and the CO2 concentration in the flue gas.

  20. Developmental word acquisition and grammar learning by humanoid robots through a self-organizing incremental neural network.

    Science.gov (United States)

    He, Xiaoyuan; Ogura, Tomotaka; Satou, Akihiro; Hasegawa, Osamu

    2007-10-01

    We present a new approach for online incremental word acquisition and grammar learning by humanoid robots. Using no data set provided in advance, the proposed system grounds language in a physical context, as mediated by its perceptual capacities. It is carried out using show-and-tell procedures, interacting with its human partner. Moreover, this procedure is open-ended for new words and multiword utterances. These facilities are supported by a self-organizing incremental neural network, which can execute online unsupervised classification and topology learning. Embodied with a mental imagery, the system also learns by both top-down and bottom-up processes, which are the syntactic structures that are contained in utterances. Thereby, it performs simple grammar learning. Under such a multimodal scheme, the robot is able to describe online a given physical context (both static and dynamic) through natural language expressions. It can also perform actions through verbal interactions with its human partner.

  1. Neural network technologies

    Science.gov (United States)

    Villarreal, James A.

    1991-01-01

    A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.

  2. Deep learning with convolutional neural networks: a resource for the control of robotic prosthetic hands via electromyography

    Directory of Open Access Journals (Sweden)

    Manfredo Atzori

    2016-09-01

    Full Text Available Motivation: Natural control methods based on surface electromyography and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications and commercial prostheses are in the best case capable to offer natural control for only a few movements. Objective: In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its capabilities for the natural control of robotic hands via surface electromyography by providing a baseline on a large number of intact and amputated subjects. Methods: We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 hand amputated subjects. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets.Results: The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods but lower than the results obtained with the best reference methods in our tests. Significance: The results show that convolutional neural networks with a very simple architecture can produce accuracy comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters can be fundamental for the analysis of surface electromyography data. Finally, the results suggest that deeper and more complex networks may increase dexterous control robustness, thus contributing to bridge the gap between the market and scientific research

  3. Program Aids Simulation Of Neural Networks

    Science.gov (United States)

    Baffes, Paul T.

    1990-01-01

    Computer program NETS - Tool for Development and Evaluation of Neural Networks - provides simulation of neural-network algorithms plus software environment for development of such algorithms. Enables user to customize patterns of connections between layers of network, and provides features for saving weight values of network, providing for more precise control over learning process. Consists of translating problem into format using input/output pairs, designing network configuration for problem, and finally training network with input/output pairs until acceptable error reached. Written in C.

  4. 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...

  5. Cascade Convolutional Neural Network Based on Transfer-Learning for Aircraft Detection on High-Resolution Remote Sensing Images

    Directory of Open Access Journals (Sweden)

    Bin Pan

    2017-01-01

    Full Text Available Aircraft detection from high-resolution remote sensing images is important for civil and military applications. Recently, detection methods based on deep learning have rapidly advanced. However, they require numerous samples to train the detection model and cannot be directly used to efficiently handle large-area remote sensing images. A weakly supervised learning method (WSLM can detect a target with few samples. However, it cannot extract an adequate number of features, and the detection accuracy requires improvement. We propose a cascade convolutional neural network (CCNN framework based on transfer-learning and geometric feature constraints (GFC for aircraft detection. It achieves high accuracy and efficient detection with relatively few samples. A high-accuracy detection model is first obtained using transfer-learning to fine-tune pretrained models with few samples. Then, a GFC region proposal filtering method improves detection efficiency. The CCNN framework completes the aircraft detection for large-area remote sensing images. The framework first-level network is an image classifier, which filters the entire image, excluding most areas with no aircraft. The second-level network is an object detector, which rapidly detects aircraft from the first-level network output. Compared with WSLM, detection accuracy increased by 3.66%, false detection decreased by 64%, and missed detection decreased by 23.1%.

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

    Science.gov (United States)

    Lee, Jun-Ki; Kwon, Yong-Ju

    2011-01-01

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

  7. Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography.

    Science.gov (United States)

    Samala, Ravi K; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A; Wei, Jun; Cha, Kenny

    2016-12-01

    Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a

  8. Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms

    Science.gov (United States)

    Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir M.; Helvie, Mark A.; Cha, Kenny H.; Richter, Caleb D.

    2017-12-01

    Transfer learning in deep convolutional neural networks (DCNNs) is an important step in its application to medical imaging tasks. We propose a multi-task transfer learning DCNN with the aim of translating the ‘knowledge’ learned from non-medical images to medical diagnostic tasks through supervised training and increasing the generalization capabilities of DCNNs by simultaneously learning auxiliary tasks. We studied this approach in an important application: classification of malignant and benign breast masses. With Institutional Review Board (IRB) approval, digitized screen-film mammograms (SFMs) and digital mammograms (DMs) were collected from our patient files and additional SFMs were obtained from the Digital Database for Screening Mammography. The data set consisted of 2242 views with 2454 masses (1057 malignant, 1397 benign). In single-task transfer learning, the DCNN was trained and tested on SFMs. In multi-task transfer learning, SFMs and DMs were used to train the DCNN, which was then tested on SFMs. N-fold cross-validation with the training set was used for training and parameter optimization. On the independent test set, the multi-task transfer learning DCNN was found to have significantly (p  =  0.007) higher performance compared to the single-task transfer learning DCNN. This study demonstrates that multi-task transfer learning may be an effective approach for training DCNN in medical imaging applications when training samples from a single modality are limited.

  9. Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms.

    Science.gov (United States)

    Samala, Ravi K; Chan, Heang-Ping; Hadjiiski, Lubomir M; Helvie, Mark A; Cha, Kenny; Richter, Caleb

    2017-10-16

    Transfer learning in deep convolutional neural networks (DCNNs) is an important step in its application to medical imaging tasks. We propose a multi-task transfer learning DCNN with the aims of translating the 'knowledge' learned from non-medical images to medical diagnostic tasks through supervised training and increasing the generalization capabilities of DCNNs by simultaneously learning auxiliary tasks. We studied this approach in an important application: classification of malignant and benign breast masses. With IRB approval, digitized screen-film mammograms (SFMs) and digital mammograms (DMs) were collected from our patient files and additional SFMs were obtained from the Digital Database for Screening Mammography. The data set consisted of 2,242 views with 2,454 masses (1,057 malignant, 1,397 benign). In single-task transfer learning, the DCNN was trained and tested on SFMs. In multi-task transfer learning, SFMs and DMs were used to train the DCNN, which was then tested on SFMs. N-fold cross-validation with the training set was used for training and parameter optimization. On the independent test set, the multi-task transfer learning DCNN was found to have significantly (p=0.007) higher performance compared to the single-task transfer learning DCNN. This study demonstrates that multi-task transfer learning may be an effective approach for training DCNN in medical imaging applications when training samples from a single modality are limited. © 2017 Institute of Physics and Engineering in Medicine.

  10. Object segmentation and reconstruction via an oscillatory neural network: interaction among learning, memory, topological organization and gamma-band synchronization.

    Science.gov (United States)

    Magosso, E; Cuppini, C; Ursino, M

    2006-01-01

    Synchronization of neuronal activity in the gamma-band has been shown to play an important role in higher cognitive functions, by grouping together the necessary information in different cortical areas to achieve a coherent perception. In the present work, we used a neural network of Wilson-Cowan oscillators to analyze the problem of binding and segmentation of high-level objects. Binding is achieved by implementing in the network the similarity and prior knowledge Gestalt rules. Similarity law is realized via topological maps within the network. Prior knowledge originates by means of a Hebbian rule of synaptic change; objects are memorized in the network with different strengths. Segmentation is realized via a global inhibitor which allows desynchronisation among multiple objects avoiding interference. Simulation results performed with a 40x40 neural grid, using three simultaneous input objects, show that the network is able to recognize and segment objects in several different conditions (different degrees of incompleteness or distortion of input patterns), exhibiting the higher reconstruction performances the higher the strength of object memory. The presented model represents an integrated approach for investigating the relationships among learning, memory, topological organization and gamma-band synchronization.

  11. Convergence of batch gradient learning with smoothing regularization and adaptive momentum for neural networks.

    Science.gov (United States)

    Fan, Qinwei; Wu, Wei; Zurada, Jacek M

    2016-01-01

    This paper presents new theoretical results on the backpropagation algorithm with smoothing [Formula: see text] regularization and adaptive momentum for feedforward neural networks with a single hidden layer, i.e., we show that the gradient of error function goes to zero and the weight sequence goes to a fixed point as n (n is iteration steps) tends to infinity, respectively. Also, our results are more general since we do not require the error function to be quadratic or uniformly convex, and neuronal activation functions are relaxed. Moreover, compared with existed algorithms, our novel algorithm can get more sparse network structure, namely it forces weights to become smaller during the training and can eventually removed after the training, which means that it can simply the network structure and lower operation time. Finally, two numerical experiments are presented to show the characteristics of the main results in detail.

  12. 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.

  13. New Neural Network Methods for Forecasting Regional Employment

    NARCIS (Netherlands)

    Patuelli, R.; Reggiani, A; Nijkamp, P.; Blien, U.

    2006-01-01

    In this paper, a set of neural network (NN) models is developed to compute short-term forecasts of regional employment patterns in Germany. Neural networks are modern statistical tools based on learning algorithms that are able to process large amounts of data. Neural networks are enjoying

  14. Person Movement Prediction Using Neural Networks

    OpenAIRE

    Vintan, Lucian; Gellert, Arpad; Petzold, Jan; Ungerer, Theo

    2006-01-01

    Ubiquitous systems use context information to adapt appliance behavior to human needs. Even more convenience is reached if the appliance foresees the user's desires and acts proactively. This paper proposes neural prediction techniques to anticipate a person's next movement. We focus on neural predictors (multi-layer perceptron with back-propagation learning) with and without pre-training. The optimal configuration of the neural network is determined by evaluating movement sequences of real p...

  15. Neural networks for triggering

    Energy Technology Data Exchange (ETDEWEB)

    Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))

    1990-01-01

    Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.

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

    Science.gov (United States)

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

    2009-01-01

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

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

    DEFF Research Database (Denmark)

    Lehmann, Torsten; Woodburn, Robin

    1999-01-01

    , 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...

  18. Modified Learning Strategy for Neural Networks to Support Spectroscopic Ellipsometric Data Evaluation

    NARCIS (Netherlands)

    Redei, L.; Fried, Miklós; Barsony, I.; Barsony, István; Wallinga, Hans

    1998-01-01

    It has been shown that worst-case learning, a slightly modified strategy in backpropagation network (BPN) training, results in constrained maximal error at the expense of slightly increased root mean squared error (RMSE) using BPN in spectroscopic ellipsometry (SE). Traditionally the evaluation of

  19. 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«.

  20. 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.

  1. Dynamic Object Identification with SOM-based neural networks

    Directory of Open Access Journals (Sweden)

    Aleksey Averkin

    2014-03-01

    Full Text Available In this article a number of neural networks based on self-organizing maps, that can be successfully used for dynamic object identification, is described. Unique SOM-based modular neural networks with vector quantized associative memory and recurrent self-organizing maps as modules are presented. The structured algorithms of learning and operation of such SOM-based neural networks are described in details, also some experimental results and comparison with some other neural networks are given.

  2. Learning ensembles of neural networks by means of a Bayesian artificial immune system.

    Science.gov (United States)

    Castro, Pablo A Dalbem; Von Zuben, Fernando José

    2011-02-01

    In this paper, we apply an immune-inspired approach to design ensembles of heterogeneous neural networks for classification problems. Our proposal, called Bayesian artificial immune system, is an estimation of distribution algorithm that replaces the traditional mutation and cloning operators with a probabilistic model, more specifically a Bayesian network, representing the joint distribution of promising solutions. Among the additional attributes provided by the Bayesian framework inserted into an immune-inspired search algorithm are the automatic control of the population size along the search and the inherent ability to promote and preserve diversity among the candidate solutions. Both are attributes generally absent from alternative estimation of distribution algorithms, and both were shown to be useful attributes when implementing the generation and selection of components of the ensemble, thus leading to high-performance classifiers. Several aspects of the design are illustrated in practical applications, including a comparative analysis with other attempts to synthesize ensembles.

  3. Application of Reinforcement Learning Algorithms for the Adaptive Computation of the Smoothing Parameter for Probabilistic Neural Network.

    Science.gov (United States)

    Kusy, Maciej; Zajdel, Roman

    2015-09-01

    In this paper, we propose new methods for the choice and adaptation of the smoothing parameter of the probabilistic neural network (PNN). These methods are based on three reinforcement learning algorithms: Q(0)-learning, Q(λ)-learning, and stateless Q-learning. We regard three types of PNN classifiers: the model that uses single smoothing parameter for the whole network, the model that utilizes single smoothing parameter for each data attribute, and the model that possesses the matrix of smoothing parameters different for each data variable and data class. Reinforcement learning is applied as the method of finding such a value of the smoothing parameter, which ensures the maximization of the prediction ability. PNN models with smoothing parameters computed according to the proposed algorithms are tested on eight databases by calculating the test error with the use of the cross validation procedure. The results are compared with state-of-the-art methods for PNN training published in the literature up to date and, additionally, with PNN whose sigma is determined by means of the conjugate gradient approach. The results demonstrate that the proposed approaches can be used as alternative PNN training procedures.

  4. Error-correction learning for artificial neural networks using the Bayesian paradigm. Application to automated medical diagnosis.

    Science.gov (United States)

    Belciug, Smaranda; Gorunescu, Florin

    2014-12-01

    Automated medical diagnosis models are now ubiquitous, and research for developing new ones is constantly growing. They play an important role in medical decision-making, helping physicians to provide a fast and accurate diagnosis. Due to their adaptive learning and nonlinear mapping properties, the artificial neural networks are widely used to support the human decision capabilities, avoiding variability in practice and errors based on lack of experience. Among the most common learning approaches, one can mention either the classical back-propagation algorithm based on the partial derivatives of the error function with respect to the weights, or the Bayesian learning method based on posterior probability distribution of weights, given training data. This paper proposes a novel training technique gathering together the error-correction learning, the posterior probability distribution of weights given the error function, and the Goodman-Kruskal Gamma rank correlation to assembly them in a Bayesian learning strategy. This study had two main purposes; firstly, to develop anovel learning technique based on both the Bayesian paradigm and the error back-propagation, and secondly,to assess its effectiveness. The proposed model performance is compared with those obtained by traditional machine learning algorithms using real-life breast and lung cancer, diabetes, and heart attack medical databases. Overall, the statistical comparison results indicate that thenovellearning approach outperforms the conventional techniques in almost all respects. Copyright © 2014 Elsevier Inc. All rights reserved.

  5. Recent progresses of neural network unsupervised learning: I. Independent component analyses generalizing PCA

    Science.gov (United States)

    Szu, Harold H.

    1999-03-01

    The early vision principle of redundancy reduction of 108 sensor excitations is understandable from computer vision viewpoint toward sparse edge maps. It is only recently derived using a truly unsupervised learning paradigm of artificial neural networks (ANN). In fact, the biological vision, Hubel- Wiesel edge maps, is reproduced seeking the underlying independent components analyses (ICA) among 102 image samples by maximizing the ANN output entropy (partial)H(V)/(partial)[W] equals (partial)[W]/(partial)t. When a pair of newborn eyes or ears meet the bustling and hustling world without supervision, they seek ICA by comparing 2 sensory measurements (x1(t), x2(t))T equalsV X(t). Assuming a linear and instantaneous mixture model of the external world X(t) equals [A] S(t), where both the mixing matrix ([A] equalsV [a1, a2] of ICA vectors and the source percentages (s1(t), s2(t))T equalsV S(t) are unknown, we seek the independent sources approximately equals [I] where the approximated sign indicates that higher order statistics (HOS) may not be trivial. Without a teacher, the ANN weight matrix [W] equalsV [w1, w2] adjusts the outputs V(t) equals tanh([W]X(t)) approximately equals [W]X(t) until no desired outputs except the (Gaussian) 'garbage' (neither YES '1' nor NO '-1' but at linear may-be range 'origin 0') defined by Gaussian covariance G equals [I] equals [W][A] GARBAGE-IN, GARBAGE-OUT,' the smarter neurocomputer will be equipped with an unsupervised learning that extracts 'RAW INFO-IN, (until) GARBAGE-OUT' for sensory knowledge acquisition in enhancing Machine IQ. We must go beyond the LMS error energy, and apply HOS To ANN. We begin with the Auto- Regression (AR) which extrapolates from the past X(t) to the future ui(t+1) equals wiTX(t) by varying the weight vector in minimizing LMS error energy E equals at the fixed point (partial)E/(partial)wi equals 0 resulted in an exact Toplitz matrix inversion for a stationary covariance assumption. We generalize AR by a

  6. Artificial Neural Network Approach in Laboratory Test Reporting:  Learning Algorithms.

    Science.gov (United States)

    Demirci, Ferhat; Akan, Pinar; Kume, Tuncay; Sisman, Ali Riza; Erbayraktar, Zubeyde; Sevinc, Suleyman

    2016-08-01

    In the field of laboratory medicine, minimizing errors and establishing standardization is only possible by predefined processes. The aim of this study was to build an experimental decision algorithm model open to improvement that would efficiently and rapidly evaluate the results of biochemical tests with critical values by evaluating multiple factors concurrently. The experimental model was built by Weka software (Weka, Waikato, New Zealand) based on the artificial neural network method. Data were received from Dokuz Eylül University Central Laboratory. "Training sets" were developed for our experimental model to teach the evaluation criteria. After training the system, "test sets" developed for different conditions were used to statistically assess the validity of the model. After developing the decision algorithm with three iterations of training, no result was verified that was refused by the laboratory specialist. The sensitivity of the model was 91% and specificity was 100%. The estimated κ score was 0.950. This is the first study based on an artificial neural network to build an experimental assessment and decision algorithm model. By integrating our trained algorithm model into a laboratory information system, it may be possible to reduce employees' workload without compromising patient safety. © American Society for Clinical Pathology, 2016. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

  7. Hyperresponsiveness of the Neural Fear Network During Fear Conditioning and Extinction Learning in Male Cocaine Users.

    Science.gov (United States)

    Kaag, Anne Marije; Levar, Nina; Woutersen, Karlijn; Homberg, Judith; van den Brink, Wim; Reneman, Liesbeth; van Wingen, Guido

    2016-10-01

    The authors investigated whether cocaine use disorder is associated with abnormalities in the neural underpinnings of aversive conditioning and extinction learning, as these processes may play an important role in the development and persistence of drug abuse. Forty male regular cocaine users and 51 male control subjects underwent a fear conditioning and extinction protocol during functional MRI. Skin conductance response was measured throughout the experiment as an index of conditioned responses. Cocaine users showed hyperresponsiveness of the amygdala and insula during fear conditioning, as well as hyporesponsiveness of the dorsomedial prefrontal cortex during extinction learning. In cocaine users, but not in control subjects, skin conductance responses were positively correlated with responsiveness of the insula, amygdala, and dorsomedial prefrontal cortex during fear conditioning but negatively correlated with responsiveness of the ventromedial prefrontal cortex during extinction learning. Increased sensitivity to aversive conditioned cues in cocaine users might be a risk factor for stress-relief craving in cocaine use disorder. These results support the postulated role of altered aversive conditioning in cocaine use disorder and may be an important step in understanding the role of aversive learning in the pathology of cocaine use disorder.

  8. 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…

  9. Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network

    Science.gov (United States)

    Fang, Kuai; Shen, Chaopeng; Kifer, Daniel; Yang, Xiao

    2017-11-01

    The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedules. Utilizing a state-of-the-art time series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 moisture product with atmospheric forcings, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-square errors (0.87 for over 75% of Continental United States, including the forested southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and environmental settings. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.

  10. Vision-based mobile robot navigation through deep convolutional neural networks and end-to-end learning

    Science.gov (United States)

    Zhang, Yachu; Zhao, Yuejin; Liu, Ming; Dong, Liquan; Kong, Lingqin; Liu, Lingling

    2017-09-01

    In contrast to humans, who use only visual information for navigation, many mobile robots use laser scanners and ultrasonic sensors along with vision cameras to navigate. This work proposes a vision-based robot control algorithm based on deep convolutional neural networks. We create a large 15-layer convolutional neural network learning system and achieve the advanced recognition performance. Our system is trained from end to end to map raw input images to direction in supervised mode. The images of data sets are collected in a wide variety of weather conditions and lighting conditions. Besides, the data sets are augmented by adding Gaussian noise and Salt-and-pepper noise to avoid overfitting. The algorithm is verified by two experiments, which are line tracking and obstacle avoidance. The line tracking experiment is proceeded in order to track the desired path which is composed of straight and curved lines. The goal of obstacle avoidance experiment is to avoid the obstacles indoor. Finally, we get 3.29% error rate on the training set and 5.1% error rate on the test set in the line tracking experiment, 1.8% error rate on the training set and less than 5% error rate on the test set in the obstacle avoidance experiment. During the actual test, the robot can follow the runway centerline outdoor and avoid the obstacle in the room accurately. The result confirms the effectiveness of the algorithm and our improvement in the network structure and train parameters

  11. Diagnosis of Malignancy in Thyroid Tumors by Multi-Layer Perceptron Neural Networks With Different Batch Learning Algorithms.

    Science.gov (United States)

    Pourahmad, Saeedeh; Azad, Mohsen; Paydar, Shahram

    2015-03-30

    To diagnose the malignancy in thyroid tumor, neural network approach is applied and the performances of thirteen batch learning algorithms are investigated on accuracy of the prediction. Therefore, a back propagation feed forward neural networks (BP FNNs) is designed and three different numbers of neuron in hidden layer are compared (5, 10 and 20 neurons). The pathology result after the surgery and clinical findings before surgery of the patients are used as the target outputs and the inputs, respectively. The best algorithm(s) is/are chosen based on mean or maximum accuracy values in the prediction and also area under Receiver Operating Characteristic Curve (ROC curve). The results show superiority of the network with 5 neurons in the hidden layer. In addition, the better performances are occurred for Polak-Ribiere conjugate gradient, BFGS quasi-newton and one step secant algorithms according to their accuracy percentage in prediction (83%) and for Scaled Conjugate Gradient and BFGS quasi-Newton based on their area under the ROC curve (0.905).

  12. Handwritten Chinese character recognition based on supervised competitive learning neural network and block-based relative fuzzy feature extraction

    Science.gov (United States)

    Sun, Limin; Wu, Shuanhu

    2005-02-01

    Offline handwritten chinese character recognition is still a difficult problem because of its large stroke changes, writing anomaly, and the difficulty for obtaining its stroke ranking information. Generally, offline handwritten chinese character can be divided into two procedures: feature extraction for capturing handwritten chinese character information and feature classifying for character recognition. In this paper, we proposed a new Chinese character recognition algorithm. In feature extraction part, we adopted elastic mesh dividing method for extracting the block features and its relative fuzzy features that utilized the relativities between different strokes and distribution probability of a stroke in its neighbor sub-blocks. In recognition part, we constructed a classifier based on a supervised competitive learning algorithm to train competitive learning neural network with the extracted features set. Experimental results show that the performance of our algorithm is encouraging and can be comparable to other algorithms.

  13. Unsupervised learning of mixture models based on swarm intelligence and neural networks with optimal completion using incomplete data

    Directory of Open Access Journals (Sweden)

    Ahmed R. Abas

    2012-07-01

    Full Text Available In this paper, a new algorithm is presented for unsupervised learning of finite mixture models (FMMs using data set with missing values. This algorithm overcomes the local optima problem of the Expectation-Maximization (EM algorithm via integrating the EM algorithm with Particle Swarm Optimization (PSO. In addition, the proposed algorithm overcomes the problem of biased estimation due to overlapping clusters in estimating missing values in the input data set by integrating locally-tuned general regression neural networks with Optimal Completion Strategy (OCS. A comparison study shows the superiority of the proposed algorithm over other algorithms commonly used in the literature in unsupervised learning of FMM parameters that result in minimum mis-classification errors when used in clustering incomplete data set that is generated from overlapping clusters and these clusters are largely different in their sizes.

  14. Developing Generic Image Search Strategies for Large Astronomical Data Sets and Archives using Convolutional Neural Networks and Transfer Learning

    Science.gov (United States)

    Peek, Joshua E. G.; Hargis, Jonathan R.; Jones, Craig R.

    2018-01-01

    Astronomical instruments produce petabytes of images every year, vastly more than can be inspected by a member of the astronomical community in search of a specific population of structures. Fortunately, the sky is mostly black and source extraction algorithms have been developed to provide searchable catalogs of unconfused sources like stars and galaxies. These tools often fail for studies of more diffuse structures like the interstellar medium and unresolved stellar structures in nearby galaxies, leaving astronomers interested in observations of photodissociation regions, stellar clusters, diffuse interstellar clouds without the crucial ability to search. In this work we present a new path forward for finding structures in large data sets similar to an input structure using convolutional neural networks, transfer learning, and machine learning clustering techniques. We show applications to archival data in the Mikulski Archive for Space Telescopes (MAST).

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

    Science.gov (United States)

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

    2017-09-05

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

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

    Science.gov (United States)

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

    2016-01-01

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

  17. Clustering: a neural network approach.

    Science.gov (United States)

    Du, K-L

    2010-01-01

    Clustering is a fundamental data analysis method. It is widely used for pattern recognition, feature extraction, vector quantization (VQ), image segmentation, function approximation, and data mining. As an unsupervised classification technique, clustering identifies some inherent structures present in a set of objects based on a similarity measure. Clustering methods can be based on statistical model identification (McLachlan & Basford, 1988) or competitive learning. In this paper, we give a comprehensive overview of competitive learning based clustering methods. Importance is attached to a number of competitive learning based clustering neural networks such as the self-organizing map (SOM), the learning vector quantization (LVQ), the neural gas, and the ART model, and clustering algorithms such as the C-means, mountain/subtractive clustering, and fuzzy C-means (FCM) algorithms. Associated topics such as the under-utilization problem, fuzzy clustering, robust clustering, clustering based on non-Euclidean distance measures, supervised clustering, hierarchical clustering as well as cluster validity are also described. Two examples are given to demonstrate the use of the clustering methods.

  18. Fractional-order gradient descent learning of BP neural networks with Caputo derivative.

    Science.gov (United States)

    Wang, Jian; Wen, Yanqing; Gou, Yida; Ye, Zhenyun; Chen, Hua

    2017-05-01

    Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well. Copyright © 2017 Elsevier Ltd. All rights reserved.

  19. Hierarchical Neural Network (HNN) for Closed Loop Decision Making: Designing the Architecture of a Hierarchical Neural Network to Model Attention, Learning and Goal Oriented Behavior

    Science.gov (United States)

    1990-12-01

    surveyed. Later control of1a robotiic system was used as the prototypical task and a HNN was designed and compared with the state of the art adaptive...Z Solution to the In’.erse kinematics efficiency foi the 6-DOF ,Lise is due to tihe Problem in Roboti s b% Neural Networks IEEE International3 trade...manipulator Desired Mechanism Actwl parameters in closed loop operation.T etr In operation, the controller is given a trajectory by a path Controller RobotI

  20. Representations in neural network based empirical potentials

    Science.gov (United States)

    Cubuk, Ekin D.; Malone, Brad D.; Onat, Berk; Waterland, Amos; Kaxiras, Efthimios

    2017-07-01

    Many structural and mechanical properties of crystals, glasses, and biological macromolecules can be modeled from the local interactions between atoms. These interactions ultimately derive from the quantum nature of electrons, which can be prohibitively expensive to simulate. Machine learning has the potential to revolutionize materials modeling due to its ability to efficiently approximate complex functions. For example, neural networks can be trained to reproduce results of density functional theory calculations at a much lower cost. However, how neural networks reach their predictions is not well understood, which has led to them being used as a "black box" tool. This lack of understanding is not desirable especially for applications of neural networks in scientific inquiry. We argue that machine learning models trained on physical systems can be used as more than just approximations since they had to "learn" physical concepts in order to reproduce the labels they were trained on. We use dimensionality reduction techniques to study in detail the representation of silicon atoms at different stages in a neural network, which provides insight into how a neural network learns to model atomic interactions.

  1. 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.

  2. Generalized hidden-mapping ridge regression, knowledge-leveraged inductive transfer learning for neural networks, fuzzy systems and kernel methods.

    Science.gov (United States)

    Deng, Zhaohong; Choi, Kup-Sze; Jiang, Yizhang; Wang, Shitong

    2014-12-01

    Inductive transfer learning has attracted increasing attention for the training of effective model in the target domain by leveraging the information in the source domain. However, most transfer learning methods are developed for a specific model, such as the commonly used support vector machine, which makes the methods applicable only to the adopted models. In this regard, the generalized hidden-mapping ridge regression (GHRR) method is introduced in order to train various types of classical intelligence models, including neural networks, fuzzy logical systems and kernel methods. Furthermore, the knowledge-leverage based transfer learning mechanism is integrated with GHRR to realize the inductive transfer learning method called transfer GHRR (TGHRR). Since the information from the induced knowledge is much clearer and more concise than that from the data in the source domain, it is more convenient to control and balance the similarity and difference of data distributions between the source and target domains. The proposed GHRR and TGHRR algorithms have been evaluated experimentally by performing regression and classification on synthetic and real world datasets. The results demonstrate that the performance of TGHRR is competitive with or even superior to existing state-of-the-art inductive transfer learning algorithms.

  3. Geographical topic learning for social images with a deep neural network

    Science.gov (United States)

    Feng, Jiangfan; Xu, Xin

    2017-03-01

    The use of geographical tagging in social-media images is becoming a part of image metadata and a great interest for geographical information science. It is well recognized that geographical topic learning is crucial for geographical annotation. Existing methods usually exploit geographical characteristics using image preprocessing, pixel-based classification, and feature recognition. How to effectively exploit the high-level semantic feature and underlying correlation among different types of contents is a crucial task for geographical topic learning. Deep learning (DL) has recently demonstrated robust capabilities for image tagging and has been introduced into geoscience. It extracts high-level features computed from a whole image component, where the cluttered background may dominate spatial features in the deep representation. Therefore, a method of spatial-attentional DL for geographical topic learning is provided and we can regard it as a special case of DL combined with various deep networks and tuning tricks. Results demonstrated that the method is discriminative for different types of geographical topic learning. In addition, it outperforms other sequential processing models in a tagging task for a geographical image dataset.

  4. 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

  5. Analysis of neural networks

    CERN Document Server

    Heiden, Uwe

    1980-01-01

    The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica­ ted throughout the text. However, they are not explored in de­ tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev­ els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be­ havior of neurons or neuron pools. In this respect the essay is writt...

  6. Wave transmission prediction of multilayer floating breakwater using neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Patil, S.G.; Hegde, A.V.

    in unison to solve a specific problem. The network learns through examples, so it requires good examples to train properly and further a trained network model can be used for prediction purpose. Proceedings of ICOE 2009 Wave transmission... prediction of multilayer floating breakwater using neural network 577 In order to allow the network to learn both non-linear and linear relationships between input nodes and output nodes, multiple-layer neural networks are often used...

  7. Characterizing cartilage microarchitecture on phase-contrast x-ray computed tomography using deep learning with convolutional neural networks

    Science.gov (United States)

    Deng, Botao; Abidin, Anas Z.; D'Souza, Adora M.; Nagarajan, Mahesh B.; Coan, Paola; Wismüller, Axel

    2017-03-01

    The effectiveness of phase contrast X-ray computed tomography (PCI-CT) in visualizing human patellar cartilage matrix has been demonstrated due to its ability to capture soft tissue contrast on a micrometer resolution scale. Recent studies have shown that off-the-shelf Convolutional Neural Network (CNN) features learned from a nonmedical data set can be used for medical image classification. In this paper, we investigate the ability of features extracted from two different CNNs for characterizing chondrocyte patterns in the cartilage matrix. We obtained features from 842 regions of interest annotated on PCI-CT images of human patellar cartilage using CaffeNet and Inception-v3 Network, which were then used in a machine learning task involving support vector machines with radial basis function kernel to classify the ROIs as healthy or osteoarthritic. Classification performance was evaluated using the area (AUC) under the Receiver Operating Characteristic (ROC) curve. The best classification performance was observed with features from Inception-v3 network (AUC = 0.95), which outperforms features extracted from CaffeNet (AUC = 0.91). These results suggest that such characterization of chondrocyte patterns using features from internal layers of CNNs can be used to distinguish between healthy and osteoarthritic tissue with high accuracy.

  8. Teaching learning based optimization-functional link artificial neural network filter for mixed noise reduction from magnetic resonance image.

    Science.gov (United States)

    Kumar, M; Mishra, S K

    2017-01-01

    The clinical magnetic resonance imaging (MRI) images may get corrupted due to the presence of the mixture of different types of noises such as Rician, Gaussian, impulse, etc. Most of the available filtering algorithms are noise specific, linear, and non-adaptive. There is a need to develop a nonlinear adaptive filter that adapts itself according to the requirement and effectively applied for suppression of mixed noise from different MRI images. In view of this, a novel nonlinear neural network based adaptive filter i.e. functional link artificial neural network (FLANN) whose weights are trained by a recently developed derivative free meta-heuristic technique i.e. teaching learning based optimization (TLBO) is proposed and implemented. The performance of the proposed filter is compared with five other adaptive filters and analyzed by considering quantitative metrics and evaluating the nonparametric statistical test. The convergence curve and computational time are also included for investigating the efficiency of the proposed as well as competitive filters. The simulation outcomes of proposed filter outperform the other adaptive filters. The proposed filter can be hybridized with other evolutionary technique and utilized for removing different noise and artifacts from others medical images more competently.

  9. Neural Networks for Optimal Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1995-01-01

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

  10. Quickprop method to speed up learning process of Artificial Neural Network in money's nominal value recognition case

    Science.gov (United States)

    Swastika, Windra

    2017-03-01

    A money's nominal value recognition system has been developed using Artificial Neural Network (ANN). ANN with Back Propagation has one disadvantage. The learning process is very slow (or never reach the target) in the case of large number of iteration, weight and samples. One way to speed up the learning process is using Quickprop method. Quickprop method is based on Newton's method and able to speed up the learning process by assuming that the weight adjustment (E) is a parabolic function. The goal is to minimize the error gradient (E'). In our system, we use 5 types of money's nominal value, i.e. 1,000 IDR, 2,000 IDR, 5,000 IDR, 10,000 IDR and 50,000 IDR. One of the surface of each nominal were scanned and digitally processed. There are 40 patterns to be used as training set in ANN system. The effectiveness of Quickprop method in the ANN system was validated by 2 factors, (1) number of iterations required to reach error below 0.1; and (2) the accuracy to predict nominal values based on the input. Our results shows that the use of Quickprop method is successfully reduce the learning process compared to Back Propagation method. For 40 input patterns, Quickprop method successfully reached error below 0.1 for only 20 iterations, while Back Propagation method required 2000 iterations. The prediction accuracy for both method is higher than 90%.

  11. LANN-SVD: A Non-Iterative SVD-Based Learning Algorithm for One-Layer Neural Networks.

    Science.gov (United States)

    Fontenla-Romero, Oscar; Perez-Sanchez, Beatriz; Guijarro-Berdinas, Bertha

    2017-09-01

    In the scope of data analytics, the volume of a data set can be defined as a product of instance size and dimensionality of the data. In many real problems, data sets are mainly large only on one of these aspects. Machine learning methods proposed in the literature are able to efficiently learn in only one of these two situations, when the number of variables is much greater than instances or vice versa. However, there is no proposal allowing to efficiently handle either circumstances in a large-scale scenario. In this brief, we present an approach to integrally address both situations, large dimensionality or large instance size, by using a singular value decomposition (SVD) within a learning algorithm for one-layer feedforward neural network. As a result, a noniterative solution is obtained, where the weights can be calculated in a closed-form manner, thereby avoiding low convergence rate and also hyperparameter tuning. The proposed learning method, LANN-SVD in short, presents a good computational efficiency for large-scale data analytic. Comprehensive comparisons were conducted to assess LANN-SVD against other state-of-the-art algorithms. The results of this brief exhibited the superior efficiency of the proposed method in any circumstance.

  12. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... examined, and it appears that considering 'normal' neural network models with, say, 500 samples, the problem of over-fitting is neglible, and therefore it is not taken into consideration afterwards. Numerous model types, often met in control applications, are implemented as neural network models...... Kalmann filter) representing state space description. The potentials of neural networks for control of non-linear processes are also examined, focusing on three different groups of control concepts, all considered as generalizations of known linear control concepts to handle also non-linear processes...

  13. Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

    Science.gov (United States)

    Lavreniuk, M. S.

    2016-12-01

    Land cover and crop type maps are one of the most essential inputs when dealing with environmental and agriculture monitoring tasks [1]. During long time neural network (NN) approach was one of the most efficient and popular approach for most applications, including crop classification using remote sensing data, with high an overall accuracy (OA) [2]. In the last years the most popular and efficient method for multi-sensor and multi-temporal land cover classification is convolution neural networks (CNNs). Taking into account presence clouds in optical data, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of optical imagery from Landsat-8 satellite. After missing data restoration, optical data from Landsat-8 was merged with Sentinel-1A radar data for better crop types discrimination [3]. An ensemble of CNNs is proposed for multi-temporal satellite images supervised classification. Each CNN in the corresponding ensemble is a 1-d CNN with 4 layers implemented using the Google's library TensorFlow. The efficiency of the proposed approach was tested on a time-series of Landsat-8 and Sentinel-1A images over the JECAM test site (Kyiv region) in Ukraine in 2015. Overall classification accuracy for ensemble of CNNs was 93.5% that outperformed an ensemble of multi-layer perceptrons (MLPs) by +0.8% and allowed us to better discriminate summer crops, in particular maize and soybeans. For 2016 we would like to validate this method using Sentinel-1 and Sentinel-2 data for Ukraine territory within ESA project on country level demonstration Sen2Agri. 1. A. Kolotii et al., "Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine," The Int. Arch. of Photogram., Rem. Sens. and Spatial Inform. Scie., vol. 40, no. 7, pp. 39-44, 2015. 2. F. Waldner et al., "Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity," Int. Journal of Rem. Sens. vol. 37, no. 14, pp

  14. Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

    Science.gov (United States)

    Choi, Joon Yul; Yoo, Tae Keun; Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

    2017-01-01

    Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

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

    Science.gov (United States)

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

    2012-01-01

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

  16. A compound memristive synapse model for statistical learning through STDP in spiking neural networks

    Directory of Open Access Journals (Sweden)

    Johannes eBill

    2014-12-01

    Full Text Available Memristors have recently emerged as promising circuit elements to mimic the function of biological synapses in neuromorphic computing. The fabrication of reliable nanoscale memristive synapses, that feature continuous conductance changes based on the timing of pre- and postsynaptic spikes, has however turned out to be challenging. In this article, we propose an alternative approach, the compound memristive synapse, that circumvents this problem by the use of memristors with binary memristive states. A compound memristive synapse employs multiple bistable memristors in parallel to jointly form one synapse, thereby providing a spectrum of synaptic efficacies. We investigate the computational implications of synaptic plasticity in the compound synapse by integrating the recently observed phenomenon of stochastic filament formation into an abstract model of stochastic switching. Using this abstract model, we first show how standard pulsing schemes give rise to spike-timing dependent plasticity (STDP with a stabilizing weight dependence in compound synapses. In a next step, we study unsupervised learning with compound synapses in networks of spiking neurons organized in a winner-take-all architecture. Our theoretical analysis reveals that compound-synapse STDP implements generalized Expectation-Maximization in the spiking network. Specifically, the emergent synapse configuration represents the most salient features of the input distribution in a Mixture-of-Gaussians generative model. Furthermore, the network’s spike response to spiking input streams approximates a well-defined Bayesian posterior distribution. We show in computer simulations how such networks learn to represent high-dimensional distributions over images of handwritten digits with high fidelity even in presence of substantial device variations and under severe noise conditions. Therefore, the compound memristive synapse may provide a synaptic design principle for future neuromorphic

  17. Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule

    Directory of Open Access Journals (Sweden)

    Ya-li Zhou

    2009-01-01

    Full Text Available In practical active noise control (ANC systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have nonminimum-phase response. A linear controller under such situations yields poor performance. A novel functional link artificial neural network (FLANN-based simultaneous perturbation stochastic approximation (SPSA algorithm, which functions as a nonlinear mode-free (MF controller, is proposed in this paper. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS algorithm, and performs better than the recently proposed filtered-s least mean square (FSLMS algorithm when the secondary path is time-varying. This observation implies that the SPSA-based MF controller can eliminate the need of the modeling of the secondary path for the ANC system.

  18. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

  19. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    simulated process and compared. The closing chapter describes some practical experiments, where the different control concepts and training methods are tested on the same practical process operating in very noisy environments. All tests confirm that neural networks also have the potential to be trained......The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...

  20. 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

  1. A hardware implementation of neural network with modified HANNIBAL architecture

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Bum youb; Chung, Duck Jin [Inha University, Inchon (Korea, Republic of)

    1996-03-01

    A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). 14 refs., 10 figs., 3 tabs.

  2. Multilayer Optical Learning Networks

    Science.gov (United States)

    Wagner, Kelvin; Psaltis, Demetri

    1987-08-01

    In this paper we present a new approach to learning in a multilayer optical neural network which is based on holographically interconnected nonlinear Fabry-Perot etalons. The network can learn the interconnections that form a distributed representation of a desired pattern transformation operation. The interconnections are formed in an adaptive and self aligning fashion, as volume holographic gratings in photorefractive crystals. Parallel arrays of globally space integrated inner products diffracted by the interconnecting hologram illuminate arrays of nonlinear Fabry-Perot etalons for fast thresholding of the transformed patterns. A phase conjugated reference wave interferes with a backwards propagating error signal to form holographic interference patterns which are time integrated in the volume of the photorefractive crystal in order to slowly modify and learn the appropriate self aligning interconnections. A holographic implementation of a single layer perceptron learning procedure is presented that can be extendept ,to a multilayer learning network through an optical implementation of the backward error propagation (BEP) algorithm.

  3. Neural Network and Letter Recognition.

    Science.gov (United States)

    Lee, Hue Yeon

    Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C -layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the 'Gabor' transform. Pattern dependent choice of center and wavelengths of 'Gabor' filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets. The correct recognition rate of the system increases with the number of training sets and eventually saturates at a certain value. Similar recognition rates are obtained for the above three different learning algorithms. The minimum error

  4. 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...

  5. 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.

  6. Common nature of learning between back-propagation and Hopfield-type neural networks for generalized matrix inversion with simplified models.

    Science.gov (United States)

    Zhang, Yunong; Guo, Dongsheng; Li, Zhan

    2013-04-01

    In this paper, two simple-structure neural networks based on the error back-propagation (BP) algorithm (i.e., BP-type neural networks, BPNNs) are proposed, developed, and investigated for online generalized matrix inversion. Specifically, the BPNN-L and BPNN-R models are proposed and investigated for the left and right generalized matrix inversion, respectively. In addition, for the same problem-solving task, two discrete-time Hopfield-type neural networks (HNNs) are developed and investigated in this paper. Similar to the classification of the presented BPNN-L and BPNN-R models, the presented HNN-L and HNN-R models correspond to the left and right generalized matrix inversion, respectively. Comparing the BPNN weight-updating formula with the HNN state-transition equation for the specific (i.e., left or right) generalized matrix inversion, we show that such two derived learning-expressions turn out to be the same (in mathematics), although the BP and Hopfield-type neural networks are evidently different from each other a great deal, in terms of network architecture, physical meaning, and training patterns. Numerical results with different illustrative examples further demonstrate the efficacy of the presented BPNNs and HNNs for online generalized matrix inversion and, more importantly, their common natures of learning.

  7. Neural-like growing networks

    Science.gov (United States)

    Yashchenko, Vitaliy A.

    2000-03-01

    On the basis of the analysis of scientific ideas reflecting the law in the structure and functioning the biological structures of a brain, and analysis and synthesis of knowledge, developed by various directions in Computer Science, also there were developed the bases of the theory of a new class neural-like growing networks, not having the analogue in world practice. In a base of neural-like growing networks the synthesis of knowledge developed by classical theories - semantic and neural of networks is. The first of them enable to form sense, as objects and connections between them in accordance with construction of the network. With thus each sense gets a separate a component of a network as top, connected to other tops. In common it quite corresponds to structure reflected in a brain, where each obvious concept is presented by certain structure and has designating symbol. Secondly, this network gets increased semantic clearness at the expense owing to formation not only connections between neural by elements, but also themselves of elements as such, i.e. here has a place not simply construction of a network by accommodation sense structures in environment neural of elements, and purely creation of most this environment, as of an equivalent of environment of memory. Thus neural-like growing networks are represented by the convenient apparatus for modeling of mechanisms of teleological thinking, as a fulfillment of certain psychophysiological of functions.

  8. Automated Grading of Gliomas using Deep Learning in Digital Pathology Images: A modular approach with ensemble of convolutional neural networks.

    Science.gov (United States)

    Ertosun, Mehmet Günhan; Rubin, Daniel L

    2015-01-01

    Brain glioma is the most common primary malignant brain tumors in adults with different pathologic subtypes: Lower Grade Glioma (LGG) Grade II, Lower Grade Glioma (LGG) Grade III, and Glioblastoma Multiforme (GBM) Grade IV. The survival and treatment options are highly dependent of this glioma grade. We propose a deep learning-based, modular classification pipeline for automated grading of gliomas using digital pathology images. Whole tissue digitized images of pathology slides obtained from The Cancer Genome Atlas (TCGA) were used to train our deep learning modules. Our modular pipeline provides diagnostic quality statistics, such as precision, sensitivity and specificity, of the individual deep learning modules, and (1) facilitates training given the limited data in this domain, (2) enables exploration of different deep learning structures for each module, (3) leads to developing less complex modules that are simpler to analyze, and (4) provides flexibility, permitting use of single modules within the framework or use of other modeling or machine learning applications, such as probabilistic graphical models or support vector machines. Our modular approach helps us meet the requirements of minimum accuracy levels that are demanded by the context of different decision points within a multi-class classification scheme. Convolutional Neural Networks are trained for each module for each sub-task with more than 90% classification accuracies on validation data set, and achieved classification accuracy of 96% for the task of GBM vs LGG classification, 71% for further identifying the grade of LGG into Grade II or Grade III on independent data set coming from new patients from the multi-institutional repository.

  9. Neural network optimization, components, and design selection

    Science.gov (United States)

    Weller, Scott W.

    1990-07-01

    Neural Networks are part of a revived technology which has received a lot of hype in recent years. As is apt to happen in any hyped technology, jargon and predictions make its assimilation and application difficult. Nevertheless, Neural Networks have found use in a number of areas, working on non-trivial and noncontrived problems. For example, one net has been trained to "read", translating English text into phoneme sequences. Other applications of Neural Networks include data base manipulation and the solving of muting and classification types of optimization problems. Neural Networks are constructed from neurons, which in electronics or software attempt to model but are not constrained by the real thing, i.e., neurons in our gray matter. Neurons are simple processing units connected to many other neurons over pathways which modify the incoming signals. A single synthetic neuron typically sums its weighted inputs, runs this sum through a non-linear function, and produces an output. In the brain, neurons are connected in a complex topology: in hardware/software the topology is typically much simpler, with neurons lying side by side, forming layers of neurons which connect to the layer of neurons which receive their outputs. This simplistic model is much easier to construct than the real thing, and yet can solve real problems. The information in a network, or its "memory", is completely contained in the weights on the connections from one neuron to another. Establishing these weights is called "training" the network. Some networks are trained by design -- once constructed no further learning takes place. Other types of networks require iterative training once wired up, but are not trainable once taught Still other types of networks can continue to learn after initial construction. The main benefit to using Neural Networks is their ability to work with conflicting or incomplete ("fuzzy") data sets. This ability and its usefulness will become evident in the following

  10. Parallelization of learning problems by artificial neural networks. Application in external radiotherapy; Parallelisation de problemes d'apprentissage par des reseaux neuronaux artificiels. Application en radiotherapie externe

    Energy Technology Data Exchange (ETDEWEB)

    Sauget, M

    2007-12-15

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

  11. Complex-valued Neural Networks

    Science.gov (United States)

    Hirose, Akira

    This paper reviews the features and applications of complex-valued neural networks (CVNNs). First we list the present application fields, and describe the advantages of the CVNNs in two application examples, namely, an adaptive plastic-landmine visualization system and an optical frequency-domain-multiplexed learning logic circuit. Then we briefly discuss the features of complex number itself to find that the phase rotation is the most significant concept, which is very useful in processing the information related to wave phenomena such as lightwave and electromagnetic wave. The CVNNs will also be an indispensable framework of the future microelectronic information-processing hardware where the quantum electron wave plays the principal role.

  12. Multilingual Text Detection with Nonlinear Neural Network

    Directory of Open Access Journals (Sweden)

    Lin Li

    2015-01-01

    Full Text Available Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work.

  13. Classification of behavior using unsupervised temporal neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Adair, K.L. [Florida State Univ., Tallahassee, FL (United States). Dept. of Computer Science; Argo, P. [Los Alamos National Lab., NM (United States)

    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.

  14. 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.

  15. Artificial neural network in cosmic landscape

    Science.gov (United States)

    Liu, Junyu

    2017-12-01

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

  16. Memristor-based neural networks

    Science.gov (United States)

    Thomas, Andy

    2013-03-01

    The synapse is a crucial element in biological neural networks, but a simple electronic equivalent has been absent. This complicates the development of hardware that imitates biological architectures in the nervous system. Now, the recent progress in the experimental realization of memristive devices has renewed interest in artificial neural networks. The resistance of a memristive system depends on its past states and exactly this functionality can be used to mimic the synaptic connections in a (human) brain. After a short introduction to memristors, we present and explain the relevant mechanisms in a biological neural network, such as long-term potentiation and spike time-dependent plasticity, and determine the minimal requirements for an artificial neural network. We review the implementations of these processes using basic electric circuits and more complex mechanisms that either imitate biological systems or could act as a model system for them.

  17. Pansharpening by Convolutional Neural Networks

    National Research Council Canada - National Science Library

    Masi, Giuseppe; Cozzolino, Davide; Verdoliva, Luisa; Scarpa, Giuseppe

    2016-01-01

    A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem...

  18. 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.

  19. Application of a deep-learning method to the forecast of daily solar flare occurrence using Convolution Neural Network

    Science.gov (United States)

    Shin, Seulki; Moon, Yong-Jae; Chu, Hyoungseok

    2017-08-01

    As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT 195Å, and 304Å from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the overfitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). Our model can immediately be applied to automatic forecasting service when image data are available.

  20. What are artificial neural networks?

    DEFF Research Database (Denmark)

    Krogh, Anders

    2008-01-01

    Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...

  1. Convolutional neural network based deep-learning architecture for prostate cancer detection on multiparametric magnetic resonance images

    Science.gov (United States)

    Tsehay, Yohannes K.; Lay, Nathan S.; Roth, Holger R.; Wang, Xiaosong; Kwak, Jin Tae; Turkbey, Baris I.; Pinto, Peter A.; Wood, Brad J.; Summers, Ronald M.

    2017-03-01

    Prostate cancer (PCa) is the second most common cause of cancer related deaths in men. Multiparametric MRI (mpMRI) is the most accurate imaging method for PCa detection; however, it requires the expertise of experienced radiologists leading to inconsistency across readers of varying experience. To increase inter-reader agreement and sensitivity, we developed a computer-aided detection (CAD) system that can automatically detect lesions on mpMRI that readers can use as a reference. We investigated a convolutional neural network based deep-learing (DCNN) architecture to find an improved solution for PCa detection on mpMRI. We adopted a network architecture from a state-of-the-art edge detector that takes an image as an input and produces an image probability map. Two-fold cross validation along with a receiver operating characteristic (ROC) analysis and free-response ROC (FROC) were used to determine our deep-learning based prostate-CAD's (CADDL) performance. The efficacy was compared to an existing prostate CAD system that is based on hand-crafted features, which was evaluated on the same test-set. CADDL had an 86% detection rate at 20% false-positive rate while the top-down learning CAD had 80% detection rate at the same false-positive rate, which translated to 94% and 85% detection rate at 10 false-positives per patient on the FROC. A CNN based CAD is able to detect cancerous lesions on mpMRI of the prostate with results comparable to an existing prostate-CAD showing potential for further development.

  2. Complex-Valued Neural Networks

    CERN Document Server

    Hirose, Akira

    2012-01-01

    This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...

  3. Neural network model to control an experimental chaotic pendulum

    NARCIS (Netherlands)

    Bakker, R; Schouten, JC; Takens, F; vandenBleek, CM

    1996-01-01

    A feedforward neural network was trained to predict the motion of an experimental, driven, and damped pendulum operating in a chaotic regime. The network learned the behavior of the pendulum from a time series of the pendulum's angle, the single measured variable. The validity of the neural

  4. Parameter estimation of an aeroelastic aircraft using neural networks

    Indian Academy of Sciences (India)

    e-mail: scr@iitk.ac.in. Abstract. Application of neural networks to the problem of aerodynamic modelling and parameter estimation for aeroelastic aircraft is addressed. A neural model capable of ... of the network in terms of the number of neurons in the hidden layer, the learning rate, the momentum rate etc. is not an exact ...

  5. Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.

    Science.gov (United States)

    Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu

    2017-10-01

    This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.

  6. Spiking modular neural networks: A neural network modeling approach for hydrological processes

    National Research Council Canada - National Science Library

    Kamban Parasuraman; Amin Elshorbagy; Sean K. Carey

    2006-01-01

    .... In this study, a novel neural network model called the spiking modular neural networks (SMNNs) is proposed. An SMNN consists of an input layer, a spiking layer, and an associator neural network layer...

  7. Memory-optimal neural network approximation

    Science.gov (United States)

    Bölcskei, Helmut; Grohs, Philipp; Kutyniok, Gitta; Petersen, Philipp

    2017-08-01

    We summarize the main results of a recent theory-developed by the authors-establishing fundamental lower bounds on the connectivity and memory requirements of deep neural networks as a function of the complexity of the function class to be approximated by the network. These bounds are shown to be achievable. Specifically, all function classes that are optimally approximated by a general class of representation systems-so-called affine systems-can be approximated by deep neural networks with minimal connectivity and memory requirements. Affine systems encompass a wealth of representation systems from applied harmonic analysis such as wavelets, shearlets, ridgelets, α-shearlets, and more generally α-molecules. This result elucidates a remarkable universality property of deep neural networks and shows that they achieve the optimum approximation properties of all affine systems combined. Finally, we present numerical experiments demonstrating that the standard stochastic gradient descent algorithm generates deep neural networks which provide close-to-optimal approximation rates at minimal connectivity. Moreover, stochastic gradient descent is found to actually learn approximations that are sparse in the representation system optimally sparsifying the function class the network is trained on.

  8. Wind Turbine Driving a PM Synchronous Generator Using Novel Recurrent Chebyshev Neural Network Control with the Ideal Learning Rate

    Directory of Open Access Journals (Sweden)

    Chih-Hong Lin

    2016-06-01

    Full Text Available A permanent magnet (PM synchronous generator system driven by wind turbine (WT, connected with smart grid via AC-DC converter and DC-AC converter, are controlled by the novel recurrent Chebyshev neural network (NN and amended particle swarm optimization (PSO to regulate output power and output voltage in two power converters in this study. Because a PM synchronous generator system driven by WT is an unknown non-linear and time-varying dynamic system, the on-line training novel recurrent Chebyshev NN control system is developed to regulate DC voltage of the AC-DC converter and AC voltage of the DC-AC converter connected with smart grid. Furthermore, the variable learning rate of the novel recurrent Chebyshev NN is regulated according to discrete-type Lyapunov function for improving the control performance and enhancing convergent speed. Finally, some experimental results are shown to verify the effectiveness of the proposed control method for a WT driving a PM synchronous generator system in smart grid.

  9. Variances handling method of clinical pathways based on T-S fuzzy neural networks with novel hybrid learning algorithm.

    Science.gov (United States)

    Du, Gang; Jiang, Zhibin; Diao, Xiaodi; Ye, Yan; Yao, Yang

    2012-06-01

    Clinical pathways' variances present complex, fuzzy, uncertain and high-risk characteristics. They could cause complicating diseases or even endanger patients' life if not handled effectively. In order to improve the accuracy and efficiency of variances handling by Takagi-Sugeno (T-S) fuzzy neural networks (FNNs), a new variances handling method for clinical pathways (CPs) is proposed in this study, which is based on T-S FNNs with novel hybrid learning algorithm. And the optimal structure and parameters can be achieved simultaneously by integrating the random cooperative decomposing particle swarm optimization algorithm (RCDPSO) and discrete binary version of PSO (DPSO) algorithm. Finally, a case study on liver poisoning of osteosarcoma preoperative chemotherapy CP is used to validate the proposed method. The result demonstrates that T-S FNNs based on the proposed algorithm achieves superior performances in efficiency, precision, and generalization ability to standard T-S FNNs, Mamdani FNNs and T-S FNNs based on other algorithms (CPSO and PSO) for variances handling of CPs.

  10. Ischemia Detection Using Supervised Learning for Hierarchical Neural Networks Based on Kohonen-Maps

    National Research Council Canada - National Science Library

    Vladutu, L

    2001-01-01

    .... The motivation for developing the Supervising Network - Self Organizing Map (sNet-SOM) model is to design computationally effective solutions for the particular problem of ischemia detection and other similar applications...

  11. ARTIFICIAL NEURAL NETWORK FOR MODELS OF HUMAN OPERATOR

    Directory of Open Access Journals (Sweden)

    Martin Ruzek

    2017-12-01

    Full Text Available This paper presents a new approach to mental functions modeling with the use of artificial neural networks. The artificial neural networks seems to be a promising method for the modeling of a human operator because the architecture of the ANN is directly inspired by the biological neuron. On the other hand, the classical paradigms of artificial neural networks are not suitable because they simplify too much the real processes in biological neural network. The search for a compromise between the complexity of biological neural network and the practical feasibility of the artificial network led to a new learning algorithm. This algorithm is based on the classical multilayered neural network; however, the learning rule is different. The neurons are updating their parameters in a way that is similar to real biological processes. The basic idea is that the neurons are competing for resources and the criterion to decide which neuron will survive is the usefulness of the neuron to the whole neural network. The neuron is not using "teacher" or any kind of superior system, the neuron receives only the information that is present in the biological system. The learning process can be seen as searching of some equilibrium point that is equal to a state with maximal importance of the neuron for the neural network. This position can change if the environment changes. The name of this type of learning, the homeostatic artificial neural network, originates from this idea, as it is similar to the process of homeostasis known in any living cell. The simulation results suggest that this type of learning can be useful also in other tasks of artificial learning and recognition.

  12. 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.

  13. Neural Network-Based Learning Kernel for Automatic Segmentation of Multiple Sclerosis Lesions on Magnetic Resonance Images

    Directory of Open Access Journals (Sweden)

    Khastavaneh H.

    2017-06-01

    Full Text Available Background: Multiple Sclerosis (MS is a degenerative disease of central nervous system. MS patients have some dead tissues in their brains called MS lesions. MRI is an imaging technique sensitive to soft tissues such as brain that shows MS lesions as hyper-intense or hypo-intense signals. Since manual segmentation of these lesions is a laborious and time consuming task, automatic segmentation is a need. Materials and Methods: In order to segment MS lesions, a method based on learning kernels has been proposed. The proposed method has three main steps namely; pre-processing, sub-region extraction and segmentation. The segmentation is performed by a kernel. This kernel is trained using a modified version of a special type of Artificial Neural Networks (ANN called Massive Training ANN (MTANN. The kernel incorporates surrounding pixel information as features for classification of middle pixel of kernel. The materials of this study include a part of MICCAI 2008 MS lesion segmentation grand challenge data-set. Results: Both qualitative and quantitative results show promising results. Similarity index of 70 percent in some cases is considered convincing. These results are obtained from information of only one MRI channel rather than multi-channel MRIs. Conclusion: This study shows the potential of surrounding pixel information to be incorporated in segmentation by learning kernels. The performance of proposed method will be improved using a special pre-processing pipeline and also a post-processing step for reducing false positives/negatives. An important advantage of proposed model is that it uses just FLAIR MRI that reduces computational time and brings comfort to patients.

  14. Neural Network-Based Learning Kernel for Automatic Segmentation of Multiple Sclerosis Lesions on Magnetic Resonance Images.

    Science.gov (United States)

    Khastavaneh, H; Ebrahimpour-Komleh, H

    2017-06-01

    Multiple Sclerosis (MS) is a degenerative disease of central nervous system. MS patients have some dead tissues in their brains called MS lesions. MRI is an imaging technique sensitive to soft tissues such as brain that shows MS lesions as hyper-intense or hypo-intense signals. Since manual segmentation of these lesions is a laborious and time consuming task, automatic segmentation is a need. In order to segment MS lesions, a method based on learning kernels has been proposed. The proposed method has three main steps namely; pre-processing, sub-region extraction and segmentation. The segmentation is performed by a kernel. This kernel is trained using a modified version of a special type of Artificial Neural Networks (ANN) called Massive Training ANN (MTANN). The kernel incorporates surrounding pixel information as features for classification of middle pixel of kernel. The materials of this study include a part of MICCAI 2008 MS lesion segmentation grand challenge data-set. Both qualitative and quantitative results show promising results. Similarity index of 70 percent in some cases is considered convincing. These results are obtained from information of only one MRI channel rather than multi-channel MRIs. This study shows the potential of surrounding pixel information to be incorporated in segmentation by learning kernels. The performance of proposed method will be improved using a special pre-processing pipeline and also a post-processing step for reducing false positives/negatives. An important advantage of proposed model is that it uses just FLAIR MRI that reduces computational time and brings comfort to patients.

  15. Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study.

    Science.gov (United States)

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

    2017-10-27

    Purpose To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent-enhanced computed tomography (CT). Materials and Methods This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A-B versus categories C-E were calculated. Results Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A-B from C-E was 0.92. Conclusion Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. (©) RSNA, 2017 Online

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

    Science.gov (United States)

    Zhen, Xin; Chen, Jiawei; Zhong, Zichun; Hrycushko, Brian; Zhou, Linghong; Jiang, Steve; Albuquerque, Kevin; Gu, Xuejun

    2017-11-01

    Better understanding of the dose-toxicity relationship is critical for safe dose escalation to improve local control in late-stage cervical cancer radiotherapy. In this study, we introduced a convolutional neural network (CNN) model to analyze rectum dose distribution and predict rectum toxicity. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively collected, including twelve toxicity patients and thirty non-toxicity patients. We adopted a transfer learning strategy to overcome the limited patient data issue. A 16-layers CNN developed by the visual geometry group (VGG-16) of the University of Oxford was pre-trained on a large-scale natural image database, ImageNet, and fine-tuned with patient rectum surface dose maps (RSDMs), which were accumulated EBRT  +  BT doses on the unfolded rectum surface. We used the adaptive synthetic sampling approach and the data augmentation method to address the two challenges, data imbalance and data scarcity. The gradient-weighted class activation maps (Grad-CAM) were also generated to highlight the discriminative regions on the RSDM along with the prediction model. We compare different CNN coefficients fine-tuning strategies, and compare the predictive performance using the traditional dose volume parameters, e.g. D 0.1/1/2cc, and the texture features extracted from the RSDM. Satisfactory prediction performance was achieved with the proposed scheme, and we found that the mean Grad-CAM over the toxicity patient group has geometric consistence of distribution with the statistical analysis result, which indicates possible rectum toxicity location. The evaluation results have demonstrated the feasibility of building a CNN-based rectum dose-toxicity prediction model with transfer learning for cervical cancer radiotherapy.

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

    Science.gov (United States)

    Zhen, Xin; Chen, Jiawei; Zhong, Zichun; Hrycushko, Brian; Zhou, Linghong; Jiang, Steve; Albuquerque, Kevin; Gu, Xuejun

    2017-10-12

    Better understanding of the dose-toxicity relationship is critical for safe dose escalation to improve local control in late-stage cervical cancer radiotherapy. In this study, we introduced a convolutional neural network (CNN) model to analyze rectum dose distribution and predict rectum toxicity. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively collected, including twelve toxicity patients and thirty non-toxicity patients. We adopted a transfer learning strategy to overcome the limited patient data issue. A 16-layers CNN developed by the visual geometry group (VGG-16) of the University of Oxford was pre-trained on a large-scale natural image database, ImageNet, and fine-tuned with patient rectum surface dose maps (RSDMs), which were accumulated EBRT  +  BT doses on the unfolded rectum surface. We used the adaptive synthetic sampling approach and the data augmentation method to address the two challenges, data imbalance and data scarcity. The gradient-weighted class activation maps (Grad-CAM) were also generated to highlight the discriminative regions on the RSDM along with the prediction model. We compare different CNN coefficients fine-tuning strategies, and compare the predictive performance using the traditional dose volume parameters, e.g. D 0.1/1/2cc, and the texture features extracted from the RSDM. Satisfactory prediction performance was achieved with the proposed scheme, and we found that the mean Grad-CAM over the toxicity patient group has geometric consistence of distribution with the statistical analysis result, which indicates possible rectum toxicity location. The evaluation results have demonstrated the feasibility of building a CNN-based rectum dose-toxicity prediction model with transfer learning for cervical cancer radiotherapy.

  18. Multigradient for Neural Networks for Equalizers

    Directory of Open Access Journals (Sweden)

    Chulhee Lee

    2003-06-01

    Full Text Available Recently, a new training algorithm, multigradient, has been published for neural networks and it is reported that the multigradient outperforms the backpropagation when neural networks are used as a classifier. When neural networks are used as an equalizer in communications, they can be viewed as a classifier. In this paper, we apply the multigradient algorithm to train the neural networks that are used as equalizers. Experiments show that the neural networks trained using the multigradient noticeably outperforms the neural networks trained by the backpropagation.

  19. 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.

  20. Multiprocessor Neural Network in Healthcare.

    Science.gov (United States)

    Godó, Zoltán Attila; Kiss, Gábor; Kocsis, Dénes

    2015-01-01

    A possible way of creating a multiprocessor artificial neural network is by the use of microcontrollers. The RISC processors' high performance and the large number of I/O ports mean they are greatly suitable for creating such a system. During our research, we wanted to see if it is possible to efficiently create interaction between the artifical neural network and the natural nervous system. To achieve as much analogy to the living nervous system as possible, we created a frequency-modulated analog connection between the units. Our system is connected to the living nervous system through 128 microelectrodes. Two-way communication is provided through A/D transformation, which is even capable of testing psychopharmacons. The microcontroller-based analog artificial neural network can play a great role in medical singal processing, such as ECG, EEG etc.

  1. An efficient neural network approach to dynamic robot motion planning.

    Science.gov (United States)

    Yang, S X; Meng, M

    2000-03-01

    In this paper, a biologically inspired neural network approach to real-time collision-free motion planning of mobile robots or robot manipulators in a nonstationary environment is proposed. Each neuron in the topologically organized neural network has only local connections, whose neural dynamics is characterized by a shunting equation. Thus the computational complexity linearly depends on the neural network size. The real-time robot motion is planned through the dynamic activity landscape of the neural network without any prior knowledge of the dynamic environment, without explicitly searching over the free workspace or the collision paths, and without any learning procedures. Therefore it is computationally efficient. The global stability of the neural network is guaranteed by qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency of the proposed approach are demonstrated through simulation studies.

  2. Geochemical characterization of oceanic basalts using artificial neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Das, P.; Iyer, S.D.

    method is specifically needed to identify the OFB as normal (N-MORB), enriched (E-MORB) and ocean island basalts (OIB). Artificial Neural Network (ANN) technique as a supervised Learning Vector Quantisation (LVQ) is applied to identify the inherent...

  3. Using artificial neural network approach for modelling rainfall–runoff ...

    Indian Academy of Sciences (India)

    driven techniques, the artificial neural .... inputs from the environment), one or more inter- mediate layers and an output layer (producing the ... three-layer learning network consisting of an input layer, a hidden layer and an output layer as illus-.

  4. Supervised Sequence Labelling with Recurrent Neural Networks

    CERN Document Server

    Graves, Alex

    2012-01-01

    Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools—robust to input noise and distortion, able to exploit long-range contextual information—that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary.    The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional...

  5. 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.

  6. Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments

    Science.gov (United States)

    Oubbati, Mohamed; Kord, Bahram; Koprinkova-Hristova, Petia; Palm, Günther

    2014-04-01

    The new tendency of artificial intelligence suggests that intelligence must be seen as a result of the interaction between brains, bodies and environments. This view implies that designing sophisticated behaviour requires a primary focus on how agents are functionally coupled to their environments. Under this perspective, we present early results with the application of reservoir computing as an efficient tool to understand how behaviour emerges from interaction. Specifically, we present reservoir computing models, that are inspired by imitation learning designs, to extract the essential components of behaviour that results from agent-environment interaction dynamics. Experimental results using a mobile robot are reported to validate the learning architectures.

  7. BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

    Science.gov (United States)

    Santara, Anirban; Mani, Kaustubh; Hatwar, Pranoot; Singh, Ankit; Garg, Ankur; Padia, Kirti; Mitra, Pabitra

    2017-09-01

    Deep learning based landcover classification algorithms have recently been proposed in literature. In hyperspectral images (HSI) they face the challenges of large dimensionality, spatial variability of spectral signatures and scarcity of labeled data. In this article we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs landcover classification. The architecture has fewer independent connection weights and thus requires lesser number of training data. The method is found to outperform the highest reported accuracies on popular hyperspectral image data sets.

  8. An Overview on Evaluation of E-Learning/Training Response Time Considering Artificial Neural Networks Modeling

    Science.gov (United States)

    Mustafa, Hassan M. H.; Tourkia, Fadhel Ben; Ramadan, Ramadan Mohamed

    2017-01-01

    The objective of this piece of research is to interpret and investigate systematically an observed brain functional phenomenon which is associated with proceeding of e-learning processes. More specifically, this work addresses an interesting and challenging educational issue concerned with dynamical evaluation of elearning performance considering…

  9. On Extending Neural Networks with Loss Ensembles for Text Classification

    OpenAIRE

    Hajiabadi, Hamideh; Molla-Aliod, Diego; Monsefi, Reza

    2017-01-01

    Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a neural network extended with an ensemble loss function for text classification. The weight of each weak loss function is tuned within the training phase through the gradient propagation optimization method of the neural network. The approach is evaluated on...

  10. Fuzzy logic and neural network technologies

    Science.gov (United States)

    Villarreal, James A.; Lea, Robert N.; Savely, Robert T.

    1992-01-01

    Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.

  11. 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.

  12. 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.

  13. Learning to read aloud: A neural network approach using sparse distributed memory

    Science.gov (United States)

    Joglekar, Umesh Dwarkanath

    1989-01-01

    An attempt to solve a problem of text-to-phoneme mapping is described which does not appear amenable to solution by use of standard algorithmic procedures. Experiments based on a model of distributed processing are also described. This model (sparse distributed memory (SDM)) can be used in an iterative supervised learning mode to solve the problem. Additional improvements aimed at obtaining better performance are suggested.

  14. Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations

    Science.gov (United States)

    Jani, Yashvant

    1992-01-01

    As part of the Research Institute for Computing and Information Systems (RICIS) activity, the reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Max satellite simulation. This activity is carried out in the software technology laboratory utilizing the Orbital Operations Simulator (OOS). This interim report provides the status of the project and outlines the future plans.

  15. Generalization performance of regularized neural network models

    DEFF Research Database (Denmark)

    Larsen, Jan; Hansen, Lars Kai

    1994-01-01

    Architecture optimization is a fundamental problem of neural network modeling. The optimal architecture is defined as the one which minimizes the generalization error. This paper addresses estimation of the generalization performance of regularized, complete neural network models. Regularization...

  16. voltage compensation using artificial neural network

    African Journals Online (AJOL)

    Offor Theophilos

    VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK: A CASE STUDY OF. RUMUOLA ... using artificial neural network (ANN) controller based dynamic voltage restorer (DVR). ... substation by simulating with sample of average voltage for Omerelu, Waterlines, Rumuola, Shell Industrial and Barracks.

  17. Plant Growth Models Using Artificial Neural Networks

    Science.gov (United States)

    Bubenheim, David

    1997-01-01

    In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.

  18. Segmentation of inner and outer bladder wall using deep-learning convolutional neural network in CT urography

    Science.gov (United States)

    Gordon, Marshall; Hadjiiski, Lubomir; Cha, Kenny; Chan, Heang-Ping; Samala, Ravi; Cohan, Richard H.; Caoili, Elaine M.

    2017-03-01

    We are developing a computerized system for detection of bladder cancer in CT urography. In this study, we used a deep-learning convolutional neural network (DL-CNN) to segment the bladder wall. This task is challenging due to differences in the wall between the contrast and non-contrast-filled regions, significant variations in appearance, size, and shape of the bladder among cases, overlap of the prostate with the bladder wall, and the wall being extremely thin compared to the overall size of the bladder. We trained a DL-CNN to estimate the likelihood that a given pixel would be inside the wall of the bladder using neighborhood information. A segmented bladder wall was then obtained using level sets with this likelihood map as a term in the level set energy formulation to obtain contours of the inner and outer bladder walls. The accuracy of the segmentation was evaluated by comparing the segmented wall outlines to hand outlines for a set of 79 training cases and 15 test cases using the average volume intersection % as the metric. For the training set, the inner wall achieved an average volume intersection of 90.0+/-8.7% and the outer wall achieved 93.7+/-3.9%. For the test set, the inner wall achieved an average volume intersection of 87.6+/-7.6% and the outer wall achieved 87.2+/-9.3%. The results show that the DL-CNN with level sets was effective in segmenting the inner and outer bladder walls.

  19. Optoelectronic Implementation of Neural Networks

    Indian Academy of Sciences (India)

    Home; Journals; Resonance – Journal of Science Education; Volume 3; Issue 9. Optoelectronic Implementation of Neural Networks - Use of Optics in Computing. R Ramachandran. General Article Volume 3 Issue 9 September 1998 pp 45-55. Fulltext. Click here to view fulltext PDF. Permanent link:

  20. Aphasia Classification Using Neural Networks

    DEFF Research Database (Denmark)

    Axer, H.; Jantzen, Jan; Berks, G.

    2000-01-01

    A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests...

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

    Science.gov (United States)

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

    2017-01-01

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

  2. Analysis of neural networks through base functions

    NARCIS (Netherlands)

    van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.

    Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more

  3. Simplified LQG Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1997-01-01

    A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce...

  4. Novel quantum inspired binary neural network algorithm

    Indian Academy of Sciences (India)

    In this paper, a quantum based binary neural network algorithm is proposed, named as novel quantum binary neural network algorithm (NQ-BNN). It forms a neural network structure by deciding weights and separability parameter in quantum based manner. Quantum computing concept represents solution probabilistically ...

  5. 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.

  6. Learning Pitch with STDP: A Computational Model of Place and Temporal Pitch Perception Using Spiking Neural Networks.

    Directory of Open Access Journals (Sweden)

    Nafise Erfanian Saeedi

    2016-04-01

    Full Text Available Pitch perception is important for understanding speech prosody, music perception, recognizing tones in tonal languages, and perceiving speech in noisy environments. The two principal pitch perception theories consider the place of maximum neural excitation along the auditory nerve and the temporal pattern of the auditory neurons' action potentials (spikes as pitch cues. This paper describes a biophysical mechanism by which fine-structure temporal information can be extracted from the spikes generated at the auditory periphery. Deriving meaningful pitch-related information from spike times requires neural structures specialized in capturing synchronous or correlated activity from amongst neural events. The emergence of such pitch-processing neural mechanisms is described through a computational model of auditory processing. Simulation results show that a correlation-based, unsupervised, spike-based form of Hebbian learning can explain the development of neural structures required for recognizing the pitch of simple and complex tones, with or without the fundamental frequency. The temporal code is robust to variations in the spectral shape of the signal and thus can explain the phenomenon of pitch constancy.

  7. A renaissance of neural networks in drug discovery.

    Science.gov (United States)

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

    2016-08-01

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

  8. Neural network controller for underwater work ROV. Suichu sagyoyo ROV no neural network controller

    Energy Technology Data Exchange (ETDEWEB)

    Yoshida, Y.; Kidoshi, H.; Arahata, M.; Shoji, K.; Takahashi, Y. (Ishikawajima-Harima Heavy Industries, Co. Ltd., Tokyo (Japan))

    1993-07-01

    The previous underwater work ROV (remotely operated vehicle) has been controlled manually because its dynamic properties are changeable underwater. Ishikawajima-Harima Heavy Industries (IHI) has applied a neural network to an adaptive controller for the ROV. This paper describes objectives of the research, design of control logic, and tank experiments on a model ROV. For the neural network, manual operation was used to provide the initial learning data for the neural network in order to initialize control parameters for optimization. The model ROV was designed to achieve and maintain constant depth in normal operation. As a consequence of the tank experiments, it was demonstrated that the controller can acquire skill of operators, can further improve the acquired skill of operators, and can construct an automatic control system autonomically even if any dynamic properties are not known. 6 refs., 8 figs.

  9. Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

    Directory of Open Access Journals (Sweden)

    C. Chen

    2017-05-01

    Full Text Available The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN. Our contributions are mainly in the following two aspects: 1 Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2 the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

  10. Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

    Science.gov (United States)

    Chen, C.; Gong, W.; Hu, Y.; Chen, Y.; Ding, Y.

    2017-05-01

    The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN). Our contributions are mainly in the following two aspects: 1) Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2) the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

  11. Ocean wave forecasting using recurrent neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Prabaharan, N.

    to the biological neurons, works on the input and output passing through a hidden layer. The ANN used here is a data- oriented modeling technique to find relations between input and output patterns by self learning and without any fixed mathematical form assumed... = 1/p ? Ep (2) Where, Ep = ? ? (Tk ?Ok)2 (3) p is the total number of training patterns; Tk is the actual output and Ok is the predicted output at kth output node. In the learning process of backpropagation neural network...

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

    Science.gov (United States)

    Bronfman, Zohar Z; Ginsburg, Simona; Jablonka, Eva

    2014-01-01

    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.

  13. Multiple neural network approaches to clinical expert systems

    Science.gov (United States)

    Stubbs, Derek F.

    1990-08-01

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

  14. Improved probabilistic neural networks with self-adaptive strategies for transformer fault diagnosis problem

    Directory of Open Access Journals (Sweden)

    Jiao-Hong Yi

    2016-01-01

    Full Text Available Probabilistic neural network has successfully solved all kinds of engineering problems in various fields since it is proposed. In probabilistic neural network, Spread has great influence on its performance, and probabilistic neural network will generate bad prediction results if it is improperly selected. It is difficult to select the optimal manually. In this article, a variant of probabilistic neural network with self-adaptive strategy, called self-adaptive probabilistic neural network, is proposed. In self-adaptive probabilistic neural network, Spread can be self-adaptively adjusted and selected and then the best selected Spread is used to guide the self-adaptive probabilistic neural network train and test. In addition, two simplified strategies are incorporated into the proposed self-adaptive probabilistic neural network with the aim of further improving its performance and then two versions of simplified self-adaptive probabilistic neural network (simplified self-adaptive probabilistic neural networks 1 and 2 are proposed. The variants of self-adaptive probabilistic neural networks are further applied to solve the transformer fault diagnosis problem. By comparing them with basic probabilistic neural network, and the traditional back propagation, extreme learning machine, general regression neural network, and self-adaptive extreme learning machine, the results have experimentally proven that self-adaptive probabilistic neural networks have a more accurate prediction and better generalization performance when addressing the transformer fault diagnosis problem.

  15. Tumor Diagnosis Using Backpropagation Neural Network Method

    Science.gov (United States)

    Ma, Lixing; Looney, Carl; Sukuta, Sydney; Bruch, Reinhard; Afanasyeva, Natalia

    1998-05-01

    For characterization of skin cancer, an artificial neural network (ANN) method has been developed to diagnose normal tissue, benign tumor and melanoma. The pattern recognition is based on a three-layer neural network fuzzy learning system. In this study, the input neuron data set is the Fourier Transform infrared (FT-IR)spectrum obtained by a new Fiberoptic Evanescent Wave Fourier Transform Infrared (FEW-FTIR) spectroscopy method in the range of 1480 to 1850 cm-1. Ten input features are extracted from the absorbency values in this region. A single hidden layer of neural nodes with sigmoids activation functions clusters the feature space into small subclasses and the output nodes are separated in different nonconvex classes to permit nonlinear discrimination of disease states. The output is classified as three classes: normal tissue, benign tumor and melanoma. The results obtained from the neural network pattern recognition are shown to be consistent with traditional medical diagnosis. Input features have also been extracted from the absorbency spectra using chemical factor analysis. These abstract features or factors are also used in the classification.

  16. 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.

  17. Forecasting Energy Commodity Prices Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Massimo Panella

    2012-01-01

    Full Text Available A new machine learning approach for price modeling is proposed. The use of neural networks as an advanced signal processing tool may be successfully used to model and forecast energy commodity prices, such as crude oil, coal, natural gas, and electricity prices. Energy commodities have shown explosive growth in the last decade. They have become a new asset class used also for investment purposes. This creates a huge demand for better modeling as what occurred in the stock markets in the 1970s. Their price behavior presents unique features causing complex dynamics whose prediction is regarded as a challenging task. The use of a Mixture of Gaussian neural network may provide significant improvements with respect to other well-known models. We propose a computationally efficient learning of this neural network using the maximum likelihood estimation approach to calibrate the parameters. The optimal model is identified using a hierarchical constructive procedure that progressively increases the model complexity. Extensive computer simulations validate the proposed approach and provide an accurate description of commodities prices dynamics.

  18. Dynamic properties of cellular neural networks

    Directory of Open Access Journals (Sweden)

    Angela Slavova

    1993-01-01

    Full Text Available Dynamic behavior of a new class of information-processing systems called Cellular Neural Networks is investigated. In this paper we introduce a small parameter in the state equation of a cellular neural network and we seek for periodic phenomena. New approach is used for proving stability of a cellular neural network by constructing Lyapunov's majorizing equations. This algorithm is helpful for finding a map from initial continuous state space of a cellular neural network into discrete output. A comparison between cellular neural networks and cellular automata is made.

  19. Is Artificial Neural Network Suitable for Damage Level Determination of Rc- Structures?

    OpenAIRE

    Baltacıoğlu, A. K.; Öztürk, B.; Civalek, Ö.; Akgöz, B.

    2010-01-01

    In the present study, an artificial neural network (ANN) application is introduced for estimation of damage level of reinforced concrete structures. Back-propagation learning algorithm is adopted. A typical neural network architecture is proposed and some conclusions are presented. Applicability of artificial neural network (ANN) for the assessment of earthquake related damage is investigated

  20. 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.

  1. Learning Networks for Lifelong Learning

    OpenAIRE

    Sloep, Peter

    2008-01-01

    Presentation in a seminar organized by Christopher Hoadley at Penn State University, October 2004.Contains general introduction into the Learning Network Programme and a demonstration of the Netlogo Simulation of a Learning Network.

  2. Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks.

    Science.gov (United States)

    Panda, Priyadarshini; Roy, Kaushik

    2017-01-01

    Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations.

  3. Neural Networks Methodology and Applications

    CERN Document Server

    Dreyfus, Gérard

    2005-01-01

    Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...

  4. Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms.

    Science.gov (United States)

    Li, Hui; Giger, Maryellen L; Huynh, Benjamin Q; Antropova, Natalia O

    2017-10-01

    To evaluate deep learning in the assessment of breast cancer risk in which convolutional neural networks (CNNs) with transfer learning are used to extract parenchymal characteristics directly from full-field digital mammographic (FFDM) images instead of using computerized radiographic texture analysis (RTA), 456 clinical FFDM cases were included: a "high-risk" BRCA1/2 gene-mutation carriers dataset (53 cases), a "high-risk" unilateral cancer patients dataset (75 cases), and a "low-risk dataset" (328 cases). Deep learning was compared to the use of features from RTA, as well as to a combination of both in the task of distinguishing between high- and low-risk subjects. Similar classification performances were obtained using CNN [area under the curve [Formula: see text]; standard error [Formula: see text

  5. The LILARTI neural network system

    Energy Technology Data Exchange (ETDEWEB)

    Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.

    1992-10-01

    The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.

  6. 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

  7. 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.

  8. 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.

  9. Character Recognition Using Genetically Trained Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

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

    1998-10-01

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

  10. Architecture Analysis of an FPGA-Based Hopfield Neural Network

    Directory of Open Access Journals (Sweden)

    Miguel Angelo de Abreu de Sousa

    2014-01-01

    Full Text Available Interconnections between electronic circuits and neural computation have been a strongly researched topic in the machine learning field in order to approach several practical requirements, including decreasing training and operation times in high performance applications and reducing cost, size, and energy consumption for autonomous or embedded developments. Field programmable gate array (FPGA hardware shows some inherent features typically associated with neural networks, such as, parallel processing, modular executions, and dynamic adaptation, and works on different types of FPGA-based neural networks were presented in recent years. This paper aims to address different aspects of architectural characteristics analysis on a Hopfield Neural Network implemented in FPGA, such as maximum operating frequency and chip-area occupancy according to the network capacity. Also, the FPGA implementation methodology, which does not employ multipliers in the architecture developed for the Hopfield neural model, is presented, in detail.

  11. Neural Network Control of Asymmetrical Multilevel Converters

    Directory of Open Access Journals (Sweden)

    Patrice WIRA

    2009-12-01

    Full Text Available This paper proposes a neural implementation of a harmonic eliminationstrategy (HES to control a Uniform Step Asymmetrical Multilevel Inverter(USAMI. The mapping between the modulation rate and the requiredswitching angles is learned and approximated with a Multi-Layer Perceptron(MLP neural network. After learning, appropriate switching angles can bedetermined with the neural network leading to a low-computational-costneural controller which is well suited for real-time applications. Thistechnique can be applied to multilevel inverters with any number of levels. Asan example, a nine-level inverter and an eleven-level inverter are consideredand the optimum switching angles are calculated on-line. Comparisons to thewell-known sinusoidal pulse-width modulation (SPWM have been carriedout in order to evaluate the performance of the proposed approach. Simulationresults demonstrate the technical advantages of the proposed neuralimplementation over the conventional method (SPWM in eliminatingharmonics while controlling a nine-level and eleven-level USAMI. Thisneural approach is applied for the supply of an asynchronous machine andresults show that it ensures a highest quality torque by efficiently cancelingthe harmonics generated by the inverters.

  12. Temporal-pattern learning in neural models

    CERN Document Server

    Genís, Carme Torras

    1985-01-01

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

  13. Radar Target Classification Using Neural Network and Median Filter

    OpenAIRE

    J. Kurty; Matousek, Z.

    2001-01-01

    The paper deals with Radar Target Classification based on the use of a neural network. A radar signal was acquired from the output of a J frequency band noncoherent radar. We applied the three layer feed forward neural network using the backpropagation learning algorithm. We defined classes of radar targets and designated each of them by its number. Our classification process resulted in the number of a radar target class, which the radar target belongs to.

  14. Radar Target Classification Using Neural Network and Median Filter

    Directory of Open Access Journals (Sweden)

    J. Kurty

    2001-09-01

    Full Text Available The paper deals with Radar Target Classification based on the use ofa neural network. A radar signal was acquired from the output of a Jfrequency band noncoherent radar. We applied the three layer feedforward neural network using the backpropagation learning algorithm. Wedefined classes of radar targets and designated each of them by itsnumber. Our classification process resulted in the number of a radartarget class, which the radar target belongs to.

  15. Neural Network Enhanced Structure Determination of Osteoporosis, Immune System, and Radiation Repair Proteins Project

    Data.gov (United States)

    National Aeronautics and Space Administration — The proposed innovation will utilize self learning neural network technology to determine the structure of osteoporosis, immune system disease, and excess radiation...

  16. Identifying Broadband Rotational Spectra with Neural Networks

    Science.gov (United States)

    Zaleski, Daniel P.; Prozument, Kirill

    2017-06-01

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

  17. Neural network processing of natural language: II. Towards a unified model of corticostriatal function in learning sentence comprehension and non-linguistic sequencing.

    Science.gov (United States)

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

    2009-01-01

    A central issue in cognitive neuroscience today concerns how distributed neural networks in the brain that are used in language learning and processing can be involved in non-linguistic cognitive sequence learning. This issue is informed by a wealth of functional neurophysiology studies of sentence comprehension, along with a number of recent studies that examined the brain processes involved in learning non-linguistic sequences, or artificial grammar learning (AGL). The current research attempts to reconcile these data with several current neurophysiologically based models of sentence processing, through the specification of a neural network model whose architecture is constrained by the known cortico-striato-thalamo-cortical (CSTC) neuroanatomy of the human language system. The challenge is to develop simulation models that take into account constraints both from neuranatomical connectivity, and from functional imaging data, and that can actually learn and perform the same kind of language and artificial syntax tasks. In our proposed model, structural cues encoded in a recurrent cortical network in BA47 activate a CSTC circuit to modulate the flow of lexical semantic information from BA45 to an integrated representation of meaning at the sentence level in BA44/6. During language acquisition, corticostriatal plasticity is employed to allow closed class structure to drive thematic role assignment. From the AGL perspective, repetitive internal structure in the AGL strings is encoded in BA47, and activates the CSTC circuit to predict the next element in the sequence. Simulation results from Caplan's [Caplan, D., Baker, C., & Dehaut, F. (1985). Syntactic determinants of sentence comprehension in aphasia. Cognition, 21, 117-175] test of syntactic comprehension, and from Gomez and Schvaneveldts' [Gomez, R. L., & Schvaneveldt, R. W. (1994). What is learned from artificial grammars?. Transfer tests of simple association. Journal of Experimental Psychology: Learning

  18. Practical neural network recipies in C++

    CERN Document Server

    Masters

    2014-01-01

    This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum

  19. Neural network modeling of emotion

    Science.gov (United States)

    Levine, Daniel S.

    2007-03-01

    This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.

  20. Neural associative memory with optimal Bayesian learning.

    Science.gov (United States)

    Knoblauch, Andreas

    2011-06-01

    Neural associative memories are perceptron-like single-layer networks with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous work optimized the memory capacity for various models of synaptic learning: linear Hopfield-type rules, the Willshaw model employing binary synapses, or the BCPNN rule of Lansner and Ekeberg, for example. Here I show that all of these previous models are limit cases of a general optimal model where synaptic learning is determined by probabilistic Bayesian considerations. Asymptotically, for large networks and very sparse neuron activity, the Bayesian model becomes identical to an inhibitory implementation of the Willshaw and BCPNN-type models. For less sparse patterns, the Bayesian model becomes identical to Hopfield-type networks employing the covariance rule. For intermediate sparseness or finite networks, the optimal Bayesian learning rule differs from the previous models and can significantly improve memory performance. I also provide a unified analytical framework to determine memory capacity at a given output noise level that links approaches based on mutual information, Hamming distance, and signal-to-noise ratio.

  1. A SOLUTION TO THE DOUBLE DUMMY CONTRACT BRIDGE PROBLEM INFLUENCED BY SUPERVISED LEARNING MODULE ADAPTED BY ARTIFICIAL NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    M. Dharmalingam

    2014-10-01

    Full Text Available Contract Bridge is an intellectual game which motivates multiple skills and application of prior experience and knowledge, as no player knows accurately what moves other players are capable of making. The Bridge is a game played in the presence of imperfect information, yet its strategies must be well formulated, since the outcome at any intermediate stage is solely based on the choices made during the immediately preceding phase. In this paper, we train an Artificial Neural Network architecture using sample deals and use it to estimate the number of tricks to be taken by one pair of bridge players, which is the main challenge in the Double Dummy Bridge Problem. We focus on Back Propagation Neural Network Architecture with Back Propagation Algorithm with Sigmoidal transfer functions. We used two approaches namely, High – Card Point Count System and Distribution Point Method during the bidding phase of Contract Bridge. We experimented with two sigmoidal transfer functions namely, Log Sigmoid transfer function and the Hyperbolic Tangent Sigmoid function. Results reveal that the later performs better giving lower mean squared error on the output.

  2. MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION

    Directory of Open Access Journals (Sweden)

    Artur Popko

    2013-06-01

    Full Text Available Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.

  3. Granular neural networks, pattern recognition and bioinformatics

    CERN Document Server

    Pal, Sankar K; Ganivada, Avatharam

    2017-01-01

    This book provides a uniform framework describing how fuzzy rough granular neural network technologies can be formulated and used in building efficient pattern recognition and mining models. It also discusses the formation of granules in the notion of both fuzzy and rough sets. Judicious integration in forming fuzzy-rough information granules based on lower approximate regions enables the network to determine the exactness in class shape as well as to handle the uncertainties arising from overlapping regions, resulting in efficient and speedy learning with enhanced performance. Layered network and self-organizing analysis maps, which have a strong potential in big data, are considered as basic modules,. The book is structured according to the major phases of a pattern recognition system (e.g., classification, clustering, and feature selection) with a balanced mixture of theory, algorithm, and application. It covers the latest findings as well as directions for future research, particularly highlighting bioinf...

  4. On-line backpropagation in two-layered neural networks

    NARCIS (Netherlands)

    Riegler, Peter; Biehl, Michael

    1995-01-01

    We present an exact analysis of learning a rule by on-line gradient descent in a two-layered neural network with adjustable hidden-to-output weights (backpropagation of error). Results are compared with the training of networks having the same architecture but fixed weights in the second layer.

  5. Bach in 2014: Music Composition with Recurrent Neural Network

    OpenAIRE

    Liu, I-Ting; Ramakrishnan, Bhiksha

    2014-01-01

    We propose a framework for computer music composition that uses resilient propagation (RProp) and long short term memory (LSTM) recurrent neural network. In this paper, we show that LSTM network learns the structure and characteristics of music pieces properly by demonstrating its ability to recreate music. We also show that predicting existing music using RProp outperforms Back propagation through time (BPTT).

  6. Defect detection on videos using neural network

    Directory of Open Access Journals (Sweden)

    Sizyakin Roman

    2017-01-01

    Full Text Available In this paper, we consider a method for defects detection in a video sequence, which consists of three main steps; frame compensation, preprocessing by a detector, which is base on the ranking of pixel values, and the classification of all pixels having anomalous values using convolutional neural networks. The effectiveness of the proposed method shown in comparison with the known techniques on several frames of the video sequence with damaged in natural conditions. The analysis of the obtained results indicates the high efficiency of the proposed method. The additional use of machine learning as postprocessing significantly reduce the likelihood of false alarm.

  7. Predicting the survival of diabetes using neural network

    Science.gov (United States)

    Mamuda, Mamman; Sathasivam, Saratha

    2017-08-01

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

  8. Neural network training as a dissipative process.

    Science.gov (United States)

    Gori, Marco; Maggini, Marco; Rossi, Alessandro

    2016-09-01

    This paper analyzes the practical issues and reports some results on a theory in which learning is modeled as a continuous temporal process driven by laws describing the interactions of intelligent agents with their own environment. The classic regularization framework is paired with the idea of temporal manifolds by introducing the principle of least cognitive action, which is inspired by the related principle of mechanics. The introduction of the counterparts of the kinetic and potential energy leads to an interpretation of learning as a dissipative process. As an example, we apply the theory to supervised learning in neural networks and show that the corresponding Euler-Lagrange differential equations can be connected to the classic gradient descent algorithm on the supervised pairs. We give preliminary experiments to confirm the soundness of the theory. Copyright © 2016 Elsevier Ltd. All rights reserved.

  9. Satellite image analysis using neural networks

    Science.gov (United States)

    Sheldon, Roger A.

    1990-01-01

    The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.

  10. RBF neural network based H∞ H∞ H∞ synchronization for ...

    Indian Academy of Sciences (India)

    Based on this neural network and linear matrix inequality (LMI) formulation, the RBFNNHS controller and the learning laws are presented to reduce the effect of disturbance to an H ∞ norm constraint. It is shown that finding the RBFNNHS controller and the learning laws can be transformed into the LMI problem and solved ...

  11. Pragmatic Bootstrapping: A Neural Network Model of Vocabulary Acquisition

    Science.gov (United States)

    Caza, Gregory A.; Knott, Alistair

    2012-01-01

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

  12. Classical Conditioning with Pulsed Integrated Neural Networks: Circuits and System

    DEFF Research Database (Denmark)

    Lehmann, Torsten

    1998-01-01

    In this paper we investigate on-chip learning for pulsed, integrated neural networks. We discuss the implementational problems the technology imposes on learning systems and we find that abiologically inspired approach using simple circuit structures is most likely to bring success. We develop a ...... chip to solve simple classical conditioning tasks, thus verifying the design methodologies put forward in the paper....

  13. Preparing for knowledge extraction in modular neural networks

    NARCIS (Netherlands)

    Spaanenburg, Lambert; Slump, Cornelis H.; Venema, Rienk; van der Zwaag, B.J.

    Neural networks learn knowledge from data. For a monolithic structure, this knowledge can be easily used but not isolated. The many degrees of freedom while learning make knowledge extraction a computationally intensive process as the representation is not unique. Where existing knowledge is

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

    Energy Technology Data Exchange (ETDEWEB)

    Ortiz R, J. M. [Escuela Politecnica Superior, Departamento de Electrotecnia y Electronica, Avda. Menendez Pidal s/n, Cordoba (Spain); Martinez B, M. R.; Vega C, H. R. [Universidad Autonoma de Zacatecas, Unidad Academica de Estudios Nucleares, Calle Cipres No. 10, Fracc. La Penuela, 98068 Zacatecas (Mexico); Gallego D, E.; Lorente F, A. [Universidad Politecnica de Madrid, Departamento de Ingenieria Nuclear, ETSI Industriales, C. Jose Gutierrez Abascal 2, 28006 Madrid (Spain); Mendez V, R.; Los Arcos M, J. M.; Guerrero A, J. E., E-mail: morvymm@yahoo.com.m [CIEMAT, Laboratorio de Metrologia de Radiaciones Ionizantes, Avda. Complutense 22, 28040 Madrid (Spain)

    2011-02-15

    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)

  15. Research on the Application of Artificial Neural Networks in Tender Offer for Construction Projects

    Science.gov (United States)

    Minli, Zhang; Shanshan, Qiao

    The BP model in artificial neural network is used in this paper. Various factors that affect the tender offer is identified and these factors as the input nodes of network to conduct iterated operation in the network is applied in this paper. Through taking advantage of the self-learning function of network, this paper constantly modifies the weight matrix to achieve the objective error of the network error to achieve the function of predicting offer. As a software support tool, MATLAB is used in artificial neural network, the neural network toolbox helps to reduce the workload of writing code greatly and make the application of neural network more widely.

  16. Pediatric Nutritional Requirements Determination with Neural Networks

    OpenAIRE

    Karlık, Bekir; Ece, Aydın

    1998-01-01

    To calculate daily nutritional requirements of children, a computer program has been developed based upon neural network. Three parameters, daily protein, energy and water requirements, were calculated through trained artificial neural networks using a database of 312 children The results were compared with those of calculated from dietary requirements tables of World Health Organisation. No significant difference was found between two calculations. In conclusion, a simple neural network may ...

  17. Adaptive optimization and control using neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.

    1993-10-22

    Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.

  18. Bayesian regularization of neural networks.

    Science.gov (United States)

    Burden, Frank; Winkler, Dave

    2008-01-01

    Bayesian regularized artificial neural networks (BRANNs) are more robust than standard back-propagation nets and can reduce or eliminate the need for lengthy cross-validation. Bayesian regularization is a mathematical process that converts a nonlinear regression into a "well-posed" statistical problem in the manner of a ridge regression. The advantage of BRANNs is that the models are robust and the validation process, which scales as O(N2) in normal regression methods, such as back propagation, is unnecessary. These networks provide solutions to a number of problems that arise in QSAR modeling, such as choice of model, robustness of model, choice of validation set, size of validation effort, and optimization of network architecture. They are difficult to overtrain, since evidence procedures provide an objective Bayesian criterion for stopping training. They are also difficult to overfit, because the BRANN calculates and trains on a number of effective network parameters or weights, effectively turning off those that are not relevant. This effective number is usually considerably smaller than the number of weights in a standard fully connected back-propagation neural net. Automatic relevance determination (ARD) of the input variables can be used with BRANNs, and this allows the network to "estimate" the importance of each input. The ARD method ensures that irrelevant or highly correlated indices used in the modeling are neglected as well as showing which are the most important variables for modeling the activity data. This chapter outlines the equations that define the BRANN method plus a flowchart for producing a BRANN-QSAR model. Some results of the use of BRANNs on a number of data sets are illustrated and compared with other linear and nonlinear models.

  19. Neural networks for nuclear spectroscopy

    Energy Technology Data Exchange (ETDEWEB)

    Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States)] [and others

    1995-12-31

    In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.

  20. Neural network based system for equipment surveillance

    Science.gov (United States)

    Vilim, R.B.; Gross, K.C.; Wegerich, S.W.

    1998-04-28

    A method and system are disclosed for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process. 33 figs.

  1. Pansharpening by Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Giuseppe Masi

    2016-07-01

    Full Text Available A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.

  2. Optimization with Potts Neural Networks

    Science.gov (United States)

    Söderberg, Bo

    The Potts Neural Network approach to non-binary discrete optimization problems is described. It applies to problems that can be described as a set of elementary `multiple choice' options. Instead of the conventional binary (Ising) neurons, mean field Potts neurons, having several available states, are used to describe the elementary degrees of freedom of such problems. The dynamics consists of iterating the mean field equations with annealing until convergence. Due to its deterministic character, the method is quite fast. When applied to problems of Graph Partition and scheduling types, it produces very good solutions also for problems of considerable size.

  3. Optical implementation of neural networks

    Science.gov (United States)

    Yu, Francis T. S.; Guo, Ruyan

    2002-12-01

    An adaptive optical neuro-computing (ONC) using inexpensive pocket size liquid crystal televisions (LCTVs) had been developed by the graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8×8=64 neurons, it can be easily extended to 16×20=320 neurons. The major advantages of this LCTV architecture as compared with other reported ONCs, are low cost and the flexibility to operate. To test the performance, several neural net models are used. These models are Interpattern Association, Hetero-association and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.

  4. Precipitation Nowcast using Deep Recurrent Neural Network

    Science.gov (United States)

    Akbari Asanjan, A.; Yang, T.; Gao, X.; Hsu, K. L.; Sorooshian, S.

    2016-12-01

    An accurate precipitation nowcast (0-6 hours) with a fine temporal and spatial resolution has always been an important prerequisite for flood warning, streamflow prediction and risk management. Most of the popular approaches used for forecasting precipitation can be categorized into two groups. One type of precipitation forecast relies on numerical modeling of the physical dynamics of atmosphere and another is based on empirical and statistical regression models derived by local hydrologists or meteorologists. Given the recent advances in artificial intelligence, in this study a powerful Deep Recurrent Neural Network, termed as Long Short-Term Memory (LSTM) model, is creatively used to extract the patterns and forecast the spatial and temporal variability of Cloud Top Brightness Temperature (CTBT) observed from GOES satellite. Then, a 0-6 hours precipitation nowcast is produced using a Precipitation Estimation from Remote Sensing Information using Artificial Neural Network (PERSIANN) algorithm, in which the CTBT nowcast is used as the PERSIANN algorithm's raw inputs. Two case studies over the continental U.S. have been conducted that demonstrate the improvement of proposed approach as compared to a classical Feed Forward Neural Network and a couple simple regression models. The advantages and disadvantages of the proposed method are summarized with regard to its capability of pattern recognition through time, handling of vanishing gradient during model learning, and working with sparse data. The studies show that the LSTM model performs better than other methods, and it is able to learn the temporal evolution of the precipitation events through over 1000 time lags. The uniqueness of PERSIANN's algorithm enables an alternative precipitation nowcast approach as demonstrated in this study, in which the CTBT prediction is produced and used as the inputs for generating precipitation nowcast.

  5. Three dimensional living neural networks

    Science.gov (United States)

    Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.

    2015-08-01

    We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.

  6. The Laplacian spectrum of neural networks

    Science.gov (United States)

    de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.

    2014-01-01

    The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286

  7. Based on Soft Competition ART Neural Network Ensemble and Its Application to the Fault Diagnosis of Bearing

    National Research Council Canada - National Science Library

    Dan Yang; Hailin Mu; Zengbing Xu; Zhigang Wang; Cancan Yi; Changming Liu

    2017-01-01

    ...) neural network and ensemble technique. The method consists of three stages. Firstly, the improved ART neural network is comprised of the soft competition technique based on fuzzy competitive learning (FCL...

  8. UAV Trajectory Modeling Using Neural Networks

    Science.gov (United States)

    Xue, Min

    2017-01-01

    Large amount of small Unmanned Aerial Vehicles (sUAVs) are projected to operate in the near future. Potential sUAV applications include, but not limited to, search and rescue, inspection and surveillance, aerial photography and video, precision agriculture, and parcel delivery. sUAVs are expected to operate in the uncontrolled Class G airspace, which is at or below 500 feet above ground level (AGL), where many static and dynamic constraints exist, such as ground properties and terrains, restricted areas, various winds, manned helicopters, and conflict avoidance among sUAVs. How to enable safe, efficient, and massive sUAV operations at the low altitude airspace remains a great challenge. NASA's Unmanned aircraft system Traffic Management (UTM) research initiative works on establishing infrastructure and developing policies, requirement, and rules to enable safe and efficient sUAVs' operations. To achieve this goal, it is important to gain insights of future UTM traffic operations through simulations, where the accurate trajectory model plays an extremely important role. On the other hand, like what happens in current aviation development, trajectory modeling should also serve as the foundation for any advanced concepts and tools in UTM. Accurate models of sUAV dynamics and control systems are very important considering the requirement of the meter level precision in UTM operations. The vehicle dynamics are relatively easy to derive and model, however, vehicle control systems remain unknown as they are usually kept by manufactures as a part of intellectual properties. That brings challenges to trajectory modeling for sUAVs. How to model the vehicle's trajectories with unknown control system? This work proposes to use a neural network to model a vehicle's trajectory. The neural network is first trained to learn the vehicle's responses at numerous conditions. Once being fully trained, given current vehicle states, winds, and desired future trajectory, the neural

  9. Deep Neural Networks for Czech Multi-label Document Classification

    OpenAIRE

    Lenc, Ladislav; Král, Pavel

    2017-01-01

    This paper is focused on automatic multi-label document classification of Czech text documents. The current approaches usually use some pre-processing which can have negative impact (loss of information, additional implementation work, etc). Therefore, we would like to omit it and use deep neural networks that learn from simple features. This choice was motivated by their successful usage in many other machine learning fields. Two different networks are compared: the first one is a standard m...

  10. Neuronmaster: an integrated tool for applications in neural networks

    Science.gov (United States)

    Rivas-Echeverria, Francklin; Colina-Morles, Eliezer; Sole, Solazver; Perez-Mendez, Anna; Bravo-Bravo, Cesar; Bravo-Bravo, Victor

    2001-03-01

    This work presents the design of an integral environment for the suitable development of neural networks applications. The integrated environment contemplates the following features: A data processing module which encompasses statistical data analysis techniques for variables selection reduction, a variety of learning algorithms, code generator for different computer languages to enable network implementation, a learning sessions planning module and database connectivity facilities via ODBC, RPC, and API.

  11. 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.

  12. Neural networks with discontinuous/impact activations

    CERN Document Server

    Akhmet, Marat

    2014-01-01

    This book presents as its main subject new models in mathematical neuroscience. A wide range of neural networks models with discontinuities are discussed, including impulsive differential equations, differential equations with piecewise constant arguments, and models of mixed type. These models involve discontinuities, which are natural because huge velocities and short distances are usually observed in devices modeling the networks. A discussion of the models, appropriate for the proposed applications, is also provided. This book also: Explores questions related to the biological underpinning for models of neural networks\\ Considers neural networks modeling using differential equations with impulsive and piecewise constant argument discontinuities Provides all necessary mathematical basics for application to the theory of neural networks Neural Networks with Discontinuous/Impact Activations is an ideal book for researchers and professionals in the field of engineering mathematics that have an interest in app...

  13. Hindcasting of storm waves using neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Rao, S.; Mandal, S.

    of any exogenous input requirement makes the network attractive. A neural network is an information processing system modeled on the structure of the human brain. Its merit is the ability to deal with fuzzy information whose interrelation is ambiguous...

  14. Quantum Entanglement in Neural Network States

    Science.gov (United States)

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

    2017-04-01

    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 results uncover the

  15. 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

  16. General asymmetric neutral networks and structure design by genetic algorithms: A learning rule for temporal patterns

    Energy Technology Data Exchange (ETDEWEB)

    Bornholdt, S. [Heidelberg Univ., (Germany). Inst., fuer Theoretische Physik; Graudenz, D. [Lawrence Berkeley Lab., CA (United States)

    1993-07-01

    A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback.

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

    Science.gov (United States)

    Li, Hong; Ding, Xue

    2017-03-01

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

  18. Drift chamber tracking with neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Lindsey, C.S.; Denby, B.; Haggerty, H.

    1992-10-01

    We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.

  19. Neural network optimization, components, and design selection

    Science.gov (United States)

    Weller, Scott W.

    1991-01-01

    Neural Networks are part of a revived technology which has received a lot of hype in recent years. As is apt to happen in any hyped technology, jargon and predictions make its assimilation and application difficult. Nevertheless, Neural Networks have found use in a number of areas, working on non-trivial and non-contrived problems. For example, one net has been trained to "read", translating English text into phoneme sequences. Other applications of Neural Networks include data base manipulation and the solving of routing and classification types of optimization problems. It was their use in optimization that got me involved with Neural Networks. As it turned out, "optimization" used in this context was somewhat misleading, because while some network configurations could indeed solve certain kinds of optimization problems, the configuring or "training" of a Neural Network itself is an optimization problem, and most of the literature which talked about Neural Nets and optimization in the same breath did not speak to my goal of using Neural Nets to help solve lens optimization problems. I did eventually apply Neural Network to lens optimization, and I will touch on those results. The application of Neural Nets to the problem of lens selection was much more successful, and those results will dominate this paper.

  20. A Convolutional Neural Network Neutrino Event Classifier

    CERN Document Server

    Aurisano, A; Rocco, D; Himmel, A; Messier, M D; Niner, E; Pawloski, G; Psihas, F; Sousa, A; Vahle, P

    2016-01-01

    Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

  1. Inferring low-dimensional microstructure representations using convolutional neural networks

    Science.gov (United States)

    Lubbers, Nicholas; Lookman, Turab; Barros, Kipton

    2017-11-01

    We apply recent advances in machine learning and computer vision to a central problem in materials informatics: the statistical representation of microstructural images. We use activations in a pretrained convolutional neural network to provide a high-dimensional characterization of a set of synthetic microstructural images. Next, we use manifold learning to obtain a low-dimensional embedding of this statistical characterization. We show that the low-dimensional embedding extracts the parameters used to generate the images. According to a variety of metrics, the convolutional neural network method yields dramatically better embeddings than the analogous method derived from two-point correlations alone.

  2. 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.

  3. Radiation Behavior of Analog Neural Network Chip

    Science.gov (United States)

    Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.

    1996-01-01

    A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.

  4. Neural network approach to parton distributions fitting

    CERN Document Server

    Piccione, Andrea; Forte, Stefano; Latorre, Jose I.; Rojo, Joan; Piccione, Andrea; Rojo, Joan

    2006-01-01

    We will show an application of neural networks to extract information on the structure of hadrons. A Monte Carlo over experimental data is performed to correctly reproduce data errors and correlations. A neural network is then trained on each Monte Carlo replica via a genetic algorithm. Results on the proton and deuteron structure functions, and on the nonsinglet parton distribution will be shown.

  5. Medical image analysis with artificial neural networks.

    Science.gov (United States)

    Jiang, J; Trundle, P; Ren, J

    2010-12-01

    Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. Copyright © 2010 Elsevier Ltd. All rights reserved.

  6. Hidden neural networks: application to speech recognition

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1998-01-01

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...

  7. Genetic Algorithm Optimized Neural Networks Ensemble as ...

    African Journals Online (AJOL)

    Improvements in neural network calibration models by a novel approach using neural network ensemble (NNE) for the simultaneous spectrophotometric multicomponent analysis are suggested, with a study on the estimation of the components of an antihypertensive combination, namely, atenolol and losartan potassium.

  8. Neural Networks for Non-linear Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1994-01-01

    This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....

  9. Application of Neural Networks for Energy Reconstruction

    CERN Document Server

    Damgov, Jordan

    2002-01-01

    The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.

  10. Neural Network to Solve Concave Games

    OpenAIRE

    Zixin Liu; Nengfa Wang

    2014-01-01

    The issue on neural network method to solve concave games is concerned. Combined with variational inequality, Ky Fan inequality, and projection equation, concave games are transformed into a neural network model. On the basis of the Lyapunov stable theory, some stability results are also given. Finally, two classic games’ simulation results are given to illustrate the theoretical results.

  11. Recognizing changing seasonal patterns using neural networks

    NARCIS (Netherlands)

    Ph.H.B.F. Franses (Philip Hans); G. Draisma (Gerrit)

    1997-01-01

    textabstractIn this paper we propose a graphical method based on an artificial neural network model to investigate how and when seasonal patterns in macroeconomic time series change over time. Neural networks are useful since the hidden layer units may become activated only in certain seasons or

  12. Initialization of multilayer forecasting artifical neural networks

    OpenAIRE

    Bochkarev, Vladimir V.; Maslennikova, Yulia S.

    2014-01-01

    In this paper, a new method was developed for initialising artificial neural networks predicting dynamics of time series. Initial weighting coefficients were determined for neurons analogously to the case of a linear prediction filter. Moreover, to improve the accuracy of the initialization method for a multilayer neural network, some variants of decomposition of the transformation matrix corresponding to the linear prediction filter were suggested. The efficiency of the proposed neural netwo...

  13. 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.

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

    Science.gov (United States)

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

    2017-06-01

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

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

    Science.gov (United States)

    Yen, John

    1991-01-01

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

  16. Multi-Layer and Recursive Neural Networks for Metagenomic Classification.

    Science.gov (United States)

    Ditzler, Gregory; Polikar, Robi; Rosen, Gail

    2015-09-01

    Recent advances in machine learning, specifically in deep learning with neural networks, has made a profound impact on fields such as natural language processing, image classification, and language modeling; however, feasibility and potential benefits of the approaches to metagenomic data analysis has been largely under-explored. Deep learning exploits many layers of learning nonlinear feature representations, typically in an unsupervised fashion, and recent results have shown outstanding generalization performance on previously unseen data. Furthermore, some deep learning methods can also represent the structure in a data set. Consequently, deep learning and neural networks may prove to be an appropriate approach for metagenomic data. To determine whether such approaches are indeed appropriate for metagenomics, we experiment with two deep learning methods: i) a deep belief network, and ii) a recursive neural network, the latter of which provides a tree representing the structure of the data. We compare these approaches to the standard multi-layer perceptron, which has been well-established in the machine learning community as a powerful prediction algorithm, though its presence is largely missing in metagenomics literature. We find that traditional neural networks can be quite powerful classifiers on metagenomic data compared to baseline methods, such as random forests. On the other hand, while the deep learning approaches did not result in improvements to the classification accuracy, they do provide the ability to learn hierarchical representations of a data set that standard classification methods do not allow. Our goal in this effort is not to determine the best algorithm in terms accuracy-as that depends on the specific application-but rather to highlight the benefits and drawbacks of each of the approach we discuss and provide insight on how they can be improved for predictive metagenomic analysis.

  17. Reformulated radial basis neural networks trained by gradient descent.

    Science.gov (United States)

    Karayiannis, N B

    1999-01-01

    This paper presents an axiomatic approach for constructing radial basis function (RBF) neural networks. This approach results in a broad variety of admissible RBF models, including those employing Gaussian RBF's. The form of the RBF's is determined by a generator function. New RBF models can be developed according to the proposed approach by selecting generator functions other than exponential ones, which lead to Gaussian RBF's. This paper also proposes a supervised learning algorithm based on gradient descent for training reformulated RBF neural networks constructed using the proposed approach. A sensitivity analysis of the proposed algorithm relates the properties of RBF's with the convergence of gradient descent learning. Experiments involving a variety of reformulated RBF networks generated by linear and exponential generator functions indicate that gradient descent learning is simple, easily implementable, and produces RBF networks that perform considerably better than conventional RBF models trained by existing algorithms.

  18. Neural Based Orthogonal Data Fitting The EXIN Neural Networks

    CERN Document Server

    Cirrincione, Giansalvo

    2008-01-01

    Written by three leaders in the field of neural based algorithms, Neural Based Orthogonal Data Fitting proposes several neural networks, all endowed with a complete theory which not only explains their behavior, but also compares them with the existing neural and traditional algorithms. The algorithms are studied from different points of view, including: as a differential geometry problem, as a dynamic problem, as a stochastic problem, and as a numerical problem. All algorithms have also been analyzed on real time problems (large dimensional data matrices) and have shown accurate solutions. Wh

  19. Analysis of the experimental positron lifetime spectra by neural networks

    Directory of Open Access Journals (Sweden)

    Avdić Senada

    2003-01-01

    Full Text Available 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 [Pžzsitetal, 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 decomposi-tion 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.

  20. Learning Networks for Lifelong Learning

    NARCIS (Netherlands)

    Koper, Rob

    2004-01-01

    Presentation in a seminar organized by Christopher Hoadley at Penn State University, October 2004.Contains general introduction into the Learning Network Programme and a demonstration of the Netlogo Simulation of a Learning Network.

  1. Collision avoidance using neural networks

    Science.gov (United States)

    Sugathan, Shilpa; Sowmya Shree, B. V.; Warrier, Mithila R.; Vidhyapathi, C. M.

    2017-11-01

    Now a days, accidents on roads are caused due to the negligence of drivers and pedestrians or due to unexpected obstacles that come into the vehicle’s path. In this paper, a model (robot) is developed to assist drivers for a smooth travel without accidents. It reacts to the real time obstacles on the four critical sides of the vehicle and takes necessary action. The sensor used for detecting the obstacle was an IR proximity sensor. A single layer perceptron neural network is used to train and test all possible combinations of sensors result by using Matlab (offline). A microcontroller (ARM Cortex-M3 LPC1768) is used to control the vehicle through the output data which is received from Matlab via serial communication. Hence, the vehicle becomes capable of reacting to any combination of real time obstacles.

  2. Implementation of a smartphone as a wireless gyroscope platform for quantifying reduced arm swing in hemiplegie gait with machine learning classification by multilayer perceptron neural network.

    Science.gov (United States)

    LeMoyne, Robert; Mastroianni, Timothy

    2016-08-01

    Natural gait consists of synchronous and rhythmic patterns for both the lower and upper limb. People with hemiplegia can experience reduced arm swing, which can negatively impact the quality of gait. Wearable and wireless sensors, such as through a smartphone, have demonstrated the ability to quantify various features of gait. With a software application the smartphone (iPhone) can function as a wireless gyroscope platform capable of conveying a gyroscope signal recording as an email attachment by wireless connectivity to the Internet. The gyroscope signal recordings of the affected hemiplegic arm with reduced arm swing arm and the unaffected arm are post-processed into a feature set for machine learning. Using a multilayer perceptron neural network a considerable degree of classification accuracy is attained to distinguish between the affected hemiplegic arm with reduced arm swing arm and the unaffected arm.

  3. A comparative analysis of the effects of instructional design factors on student success in e-learning: multiple-regression versus neural networks

    Directory of Open Access Journals (Sweden)

    Halil Ibrahim Cebeci

    2009-12-01

    Full Text Available This study explores the relationship between the student performance and instructional design. The research was conducted at the E-Learning School at a university in Turkey. A list of design factors that had potential influence on student success was created through a review of the literature and interviews with relevant experts. From this, the five most import design factors were chosen. The experts scored 25 university courses on the extent to which they demonstrated the chosen design factors. Multiple-regression and supervised artificial neural network (ANN models were used to examine the relationship between student grade point averages and the scores on the five design factors. The results indicated that there is no statistical difference between the two models. Both models identified the use of examples and applications as the most influential factor. The ANN model provided more information and was used to predict the course-specific factor values required for a desired level of success.

  4. Computer image analysis in obtaining characteristics of images: greenhouse tomatoes in the process of generating learning sets of artificial neural networks

    Science.gov (United States)

    Zaborowicz, M.; Przybył, J.; Koszela, K.; Boniecki, P.; Mueller, W.; Raba, B.; Lewicki, A.; Przybył, K.

    2014-04-01

    The aim of the project was to make the software which on the basis on image of greenhouse tomato allows for the extraction of its characteristics. Data gathered during the image analysis and processing were used to build learning sets of artificial neural networks. Program enables to process pictures in jpeg format, acquisition of statistical information of the picture and export them to an external file. Produced software is intended to batch analyze collected research material and obtained information saved as a csv file. Program allows for analysis of 33 independent parameters implicitly to describe tested image. The application is dedicated to processing and image analysis of greenhouse tomatoes. The program can be used for analysis of other fruits and vegetables of a spherical shape.

  5. Tampa Electric Neural Network Sootblowing

    Energy Technology Data Exchange (ETDEWEB)

    Mark A. Rhode

    2003-12-31

    Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat

  6. Tampa Electric Neural Network Sootblowing

    Energy Technology Data Exchange (ETDEWEB)

    Mark A. Rhode

    2004-09-30

    Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate

  7. Tampa Electric Neural Network Sootblowing

    Energy Technology Data Exchange (ETDEWEB)

    Mark A. Rhode

    2004-03-31

    Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing co-funding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate

  8. Optimization of multilayer neural network parameters for speaker recognition

    Science.gov (United States)

    Tovarek, Jaromir; Partila, Pavol; Rozhon, Jan; Voznak, Miroslav; Skapa, Jan; Uhrin, Dominik; Chmelikova, Zdenka

    2016-05-01

    This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.

  9. Estimation of concrete compressive strength using artificial neural network

    Directory of Open Access Journals (Sweden)

    Kostić Srđan

    2015-01-01

    Full Text Available In present paper, concrete compressive strength is evaluated using back propagation feed-forward artificial neural network. Training of neural network is performed using Levenberg-Marquardt learning algorithm for four architectures of artificial neural networks, one, three, eight and twelve nodes in a hidden layer in order to avoid the occurrence of overfitting. Training, validation and testing of neural network is conducted for 75 concrete samples with distinct w/c ratio and amount of superplasticizer of melamine type. These specimens were exposed to different number of freeze/thaw cycles and their compressive strength was determined after 7, 20 and 32 days. The obtained results indicate that neural network with one hidden layer and twelve hidden nodes gives reasonable prediction accuracy in comparison to experimental results (R=0.965, MSE=0.005. These results of the performed analysis are further confirmed by calculating the standard statistical errors: the chosen architecture of neural network shows the smallest value of mean absolute percentage error (MAPE=, variance absolute relative error (VARE and median absolute error (MEDAE, and the highest value of variance accounted for (VAF.

  10. Classifying epilepsy diseases using artificial neural networks and genetic algorithm.

    Science.gov (United States)

    Koçer, Sabri; Canal, M Rahmi

    2011-08-01

    In this study, FFT analysis is applied to the EEG signals of the normal and patient subjects and the obtained FFT coefficients are used as inputs in Artificial Neural Network (ANN). The differences shown by the non-stationary random signals such as EEG signals in cases of health and sickness (epilepsy) were evaluated and tried to be analyzed under computer-supported conditions by using artificial neural networks. Multi-Layer Perceptron (MLP) architecture is used Levenberg-Marquardt (LM), Quickprop (QP), Delta-bar delta (DBD), Momentum and Conjugate gradient (CG) learning algorithms, and the best performance was tried to be attained by ensuring the optimization with the use of genetic algorithms of the weights, learning rates, neuron numbers of hidden layer in the training process. This study shows that the artificial neural network increases the classification performance using genetic algorithm.

  11. Analysis of convergence performance of neural networks ranking algorithm.

    Science.gov (United States)

    Zhang, Yongquan; Cao, Feilong

    2012-10-01

    The ranking problem is to learn a real-valued function which gives rise to a ranking over an instance space, which has gained much attention in machine learning in recent years. This article gives analysis of the convergence performance of neural networks ranking algorithm by means of the given samples and approximation property of neural networks. The upper bounds of convergence rate provided by our results can be considerably tight and independent of the dimension of input space when the target function satisfies some smooth condition. The obtained results imply that neural networks are able to adapt to ranking function in the instance space. Hence the obtained results are able to circumvent the curse of dimensionality on some smooth condition. Crown Copyright © 2012. Published by Elsevier Ltd. All rights reserved.

  12. 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.

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

    Science.gov (United States)

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

    1991-01-01

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

  14. Neural networks art: solving problems with multiple solutions and new teaching algorithm.

    Science.gov (United States)

    Dmitrienko, V D; Zakovorotnyi, A Yu; Leonov, S Yu; Khavina, I P

    2014-01-01

    A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input.

  15. Learning Processes to Predict the Hourly Global, Direct, and Diffuse Solar Irradiance from Daily Global Radiation with Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Hanae Loutfi

    2017-01-01

    Full Text Available This paper presents three different topologies of feed forward neural network (FFNN models for generating global, direct, and diffuse hourly solar irradiance in the city of Fez (Morocco. Results from this analysis are crucial for the conception of any solar energy system. Especially, for the concentrating ones, as direct component is seldom measured. For the three models, the main input was the daily global irradiation with other radiometric and meteorological parameters. Three years of hourly data were available for this study. For each solar component’s prediction, different combinations of inputs as well as different numbers of hidden neurons were considered. To evaluate these models, the regression coefficient (R2 and normalized root mean square error (nRMSE were used. The test of these models over unseen data showed a good accuracy and proved their generalization capability (nRMSE = 13.1%, 9.5%, and 8.05% and R = 0.98, 0.98, and 0.99 for hourly global, hourly direct, and daily direct radiation, respectively. Different comparison analyses confirmed that (FFNN models surpass other methods of estimation. As such, the proposed models showed a good ability to generate different solar components from daily global radiation which is registered in most radiometric stations.

  16. An architecture for designing fuzzy logic controllers using neural networks

    Science.gov (United States)

    Berenji, Hamid R.

    1991-01-01

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

  17. A cultured human neural network operates a robotic actuator.

    Science.gov (United States)

    Pizzi, R M R; Rossetti, D; Cino, G; Marino, D; A L Vescovi; Baer, W

    2009-02-01

    The development of bio-electronic prostheses, hybrid human-electronics devices and bionic robots has been the aim of many researchers. Although neurophysiologic processes have been widely investigated and bio-electronics has developed rapidly, the dynamics of a biological neuronal network that receive sensory inputs, store and control information is not yet understood. Toward this end, we have taken an interdisciplinary approach to study the learning and response of biological neural networks to complex stimulation patterns. This paper describes the design, execution, and results of several experiments performed in order to investigate the behavior of complex interconnected structures found in biological neural networks. The experimental design consisted of biological human neurons stimulated by parallel signal patterns intended to simulate complex perceptions. The response patterns were analyzed with an innovative artificial neural network (ANN), called ITSOM (Inductive Tracing Self Organizing Map). This system allowed us to decode the complex neural responses from a mixture of different stimulations and learned memory patterns inherent in the cell colonies. In the experiment described in this work, neurons derived from human neural stem cells were connected to a robotic actuator through the ANN analyzer to demonstrate our ability to produce useful control from simulated perceptions stimulating the cells. Preliminary results showed that in vitro human neuron colonies can learn to reply selectively to different stimulation patterns and that response signals can effectively be decoded to operate a minirobot. Lastly the fascinating performance of the hybrid system is evaluated quantitatively and potential future work is discussed.

  18. Sea level forecasts using neural networks

    Science.gov (United States)

    Röske, Frank

    1997-03-01

    In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the

  19. Modular representation of layered neural networks.

    Science.gov (United States)

    Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

    2018-01-01

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

  20. Research of The Deeper Neural Networks

    Directory of Open Access Journals (Sweden)

    Xiao You Rong

    2016-01-01

    Full Text Available Neural networks (NNs have powerful computational abilities and could be used in a variety of applications; however, training these networks is still a difficult problem. With different network structures, many neural models have been constructed. In this report, a deeper neural networks (DNNs architecture is proposed. The training algorithm of deeper neural network insides searching the global optimal point in the actual error surface. Before the training algorithm is designed, the error surface of the deeper neural network is analyzed from simple to complicated, and the features of the error surface is obtained. Based on these characters, the initialization method and training algorithm of DNNs is designed. For the initialization, a block-uniform design method is proposed which separates the error surface into some blocks and finds the optimal block using the uniform design method. For the training algorithm, the improved gradient-descent method is proposed which adds a penalty term into the cost function of the old gradient descent method. This algorithm makes the network have a great approximating ability and keeps the network state stable. All of these improve the practicality of the neural network.

  1. Neural network topology design for nonlinear control

    Science.gov (United States)

    Haecker, Jens; Rudolph, Stephan

    2001-03-01

    Neural networks, especially in nonlinear system identification and control applications, are typically considered to be black-boxes which are difficult to analyze and understand mathematically. Due to this reason, an in- depth mathematical analysis offering insight into the different neural network transformation layers based on a theoretical transformation scheme is desired, but up to now neither available nor known. In previous works it has been shown how proven engineering methods such as dimensional analysis and the Laplace transform may be used to construct a neural controller topology for time-invariant systems. Using the knowledge of neural correspondences of these two classical methods, the internal nodes of the network could also be successfully interpreted after training. As further extension to these works, the paper describes the latest of a theoretical interpretation framework describing the neural network transformation sequences in nonlinear system identification and control. This can be achieved By incorporation of the method of exact input-output linearization in the above mentioned two transform sequences of dimensional analysis and the Laplace transformation. Based on these three theoretical considerations neural network topologies may be designed in special situations by pure translation in the sense of a structural compilation of the known classical solutions into their correspondent neural topology. Based on known exemplary results, the paper synthesizes the proposed approach into the visionary goals of a structural compiler for neural networks. This structural compiler for neural networks is intended to automatically convert classical control formulations into their equivalent neural network structure based on the principles of equivalence between formula and operator, and operator and structure which are discussed in detail in this work.

  2. Neural-network-based fuzzy logic decision systems

    Science.gov (United States)

    Kulkarni, Arun D.; Giridhar, G. B.; Coca, Praveen

    1994-10-01

    During the last few years there has been a large and energetic upswing in research efforts aimed at synthesizing fuzzy logic with neural networks. This combination of neural networks and fuzzy logic seems natural because the two approaches generally attack the design of `intelligent' system from quite different angles. Neural networks provide algorithms for learning, classification, and optimization whereas fuzzy logic often deals with issues such as reasoning in a high (semantic or linguistic) level. Consequently the two technologies complement each other. In this paper, we combine neural networks with fuzzy logic techniques. We propose an artificial neural network (ANN) model for a fuzzy logic decision system. The model consists of six layers. The first three layers map the input variables to fuzzy set membership functions. The last three layers implement the decision rules. The model learns the decision rules using a supervised gradient descent procedure. As an illustration we considered two examples. The first example deals with pixel classification in multispectral satellite images. In our second example we used the fuzzy decision system to analyze data from magnetic resonance imaging (MRI) scans for tissue classification.

  3. 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.

  4. Using Artificial Neural Networks for ECG Signals Denoising

    Directory of Open Access Journals (Sweden)

    Zoltán Germán-Salló

    2010-12-01

    Full Text Available The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1th sample from n previous samples To train and adjust the network weights, the backpropagation (BP algorithm was used. In this paper, prediction of ECG signals (as time series using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.

  5. Brain tumor segmentation with Deep Neural Networks.

    Science.gov (United States)

    Havaei, Mohammad; Davy, Axel; Warde-Farley, David; Biard, Antoine; Courville, Aaron; Bengio, Yoshua; Pal, Chris; Jodoin, Pierre-Marc; Larochelle, Hugo

    2017-01-01

    In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster. Copyright © 2016 Elsevier B.V. All rights reserved.

  6. The role of cue information in the outcome-density effect: evidence from neural network simulations and a causal learning experiment

    Science.gov (United States)

    Musca, Serban C.; Vadillo, Miguel A.; Blanco, Fernando; Matute, Helena

    2010-06-01

    Although normatively irrelevant to the relationship between a cue and an outcome, outcome density (i.e. its base-rate probability) affects people's estimation of causality. By what process causality is incorrectly estimated is of importance to an integrative theory of causal learning. A potential explanation may be that this happens because outcome density induces a judgement bias. An alternative explanation is explored here, following which the incorrect estimation of causality is grounded in the processing of cue-outcome information during learning. A first neural network simulation shows that, in the absence of a deep processing of cue information, cue-outcome relationships are acquired but causality is correctly estimated. The second simulation shows how an incorrect estimation of causality may emerge from the active processing of both cue and outcome information. In an experiment inspired by the simulations, the role of a deep processing of cue information was put to test. In addition to an outcome density manipulation, a shallow cue manipulation was introduced: cue information was either still displayed (concurrent) or no longer displayed (delayed) when outcome information was given. Behavioural and simulation results agree: the outcome-density effect was maximal in the concurrent condition. The results are discussed with respect to the extant explanations of the outcome-density effect within the causal learning framework.

  7. A COMPARATIVE ANALYSIS OF WEB INFORMATION EXTRACTION TECHNIQUES DEEP LEARNING vs. NAÏVE BAYES vs. BACK PROPAGATION NEURAL NETWORKS IN WEB DOCUMENT EXTRACTION

    Directory of Open Access Journals (Sweden)

    J. Sharmila

    2016-01-01

    Full Text Available Web mining related exploration is getting the chance to be more essential these days in view of the reason that a lot of information is overseen through the web. Web utilization is expanding in an uncontrolled way. A particular framework is required for controlling such extensive measure of information in the web space. Web mining is ordered into three noteworthy divisions: Web content mining, web usage mining and web structure mining. Tak-Lam Wong has proposed a web content mining methodology in the exploration with the aid of Bayesian Networks (BN. In their methodology, they were learning on separating the web data and characteristic revelation in view of the Bayesian approach. Roused from their investigation, we mean to propose a web content mining methodology, in view of a Deep Learning Algorithm. The Deep Learning Algorithm gives the interest over BN on the basis that BN is not considered in any learning architecture planning like to propose system. The main objective of this investigation is web document extraction utilizing different grouping algorithm and investigation. This work extricates the data from the web URL. This work shows three classification algorithms, Deep Learning Algorithm, Bayesian Algorithm and BPNN Algorithm. Deep Learning is a capable arrangement of strategies for learning in neural system which is connected like computer vision, speech recognition, and natural language processing and biometrics framework. Deep Learning is one of the simple classification technique and which is utilized for subset of extensive field furthermore Deep Learning has less time for classification. Naive Bayes classifiers are a group of basic probabilistic classifiers in view of applying Bayes hypothesis with concrete independence assumptions between the features. At that point the BPNN algorithm is utilized for classification. Initially training and testing dataset contains more URL. We extract the content presently from the dataset. The

  8. Quantum Measurements: From Bayes Rule to Neural Networks

    DEFF Research Database (Denmark)

    Greplova, Eliska

    2017-01-01

    Quantum technologies are becoming more and more introduced into the devices that we use in the daily life, such as quantum dot based television screens or quantum cryptographic channels for encoding financial transactions. Given the limits of the silicon computer chips, it will in the near future...... learning techniques such as artificial neural networks....

  9. Prediction of tides using back-propagation neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    of tides. This neural network model predicts the time series data of hourly tides directly while using an efficient learning process called quickprop based on a previous set of data. Hourly tidal data measured at Gopalpur port - east coast of India was used...

  10. Cognition: Differential-geometrical view on neural networks

    Directory of Open Access Journals (Sweden)

    S. A. Buffalov

    1999-01-01

    Full Text Available A neural network taken as a model of a trainable system appears to be nothing but a dynamical system evolving on a tangent bundle with changeable metrics. In other words to learn means to change metrics of a definite manifold.

  11. A Constructive Neural-Network Approach to Modeling Psychological Development

    Science.gov (United States)

    Shultz, Thomas R.

    2012-01-01

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

  12. Bilingual Lexical Interactions in an Unsupervised Neural Network Model

    Science.gov (United States)

    Zhao, Xiaowei; Li, Ping

    2010-01-01

    In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…

  13. Does Artificial Neural Network Support Connectivism's Assumptions?

    Science.gov (United States)

    AlDahdouh, Alaa A.

    2017-01-01

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

  14. Neural network based system for script identification in Indian ...

    Indian Academy of Sciences (India)

    R. Narasimhan (Krishtel eMaging) 1461 1996 Oct 15 13:05:22

    environments. The system developed includes a feature extractor and a modular neural network. The feature extractor consists of two stages. In the first stage ... environments is script/language identification (Muthusamy et al 1994; Hochberg et al 1997). ... In order to take advantage of the learning and generalization abilities ...

  15. Bayesian and neural networks for preliminary ship design

    DEFF Research Database (Denmark)

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

    2001-01-01

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

  16. Estimation of Conditional Quantile using Neural Networks

    DEFF Research Database (Denmark)

    Kulczycki, P.; Schiøler, Henrik

    1999-01-01

    The problem of estimating conditional quantiles using neural networks is investigated here. A basic structure is developed using the methodology of kernel estimation, and a theory guaranteeing con-sistency on a mild set of assumptions is provided. The constructed structure constitutes a basis...... for the design of a variety of different neural networks, some of which are considered in detail. The task of estimating conditional quantiles is related to Bayes point estimation whereby a broad range of applications within engineering, economics and management can be suggested. Numerical results illustrating...... the capabilities of the elaborated neural network are also given....

  17. Vectorized algorithms for spiking neural network simulation.

    Science.gov (United States)

    Brette, Romain; Goodman, Dan F M

    2011-06-01

    High-level languages (Matlab, Python) are popular in neuroscience because they are flexible and accelerate development. However, for simulating spiking neural networks, the cost of interpretation is a bottleneck. We describe a set of algorithms to simulate large spiking neural networks efficiently with high-level languages using vector-based operations. These algorithms constitute the core of Brian, a spiking neural network simulator written in the Python language. Vectorized simulation makes it possible to combine the flexibility of high-level languages with the computational efficiency usually associated with compiled languages.

  18. Neural Plasticity in Speech Acquisition and Learning

    Science.gov (United States)

    Zhang, Yang; Wang, Yue

    2007-01-01

    Neural plasticity in speech acquisition and learning is concerned with the timeline trajectory and the mechanisms of experience-driven changes in the neural circuits that support or disrupt linguistic function. In this selective review, we discuss the role of phonetic learning in language acquisition, the "critical period" of learning, the agents…

  19. Fluctuating Arctic Sea ice thickness changes estimated by an in situ learned and empirically forced neural network model

    Science.gov (United States)

    Belchansky, G.I.; Douglas, D.C.; Platonov, N.G.

    2008-01-01

    Sea ice thickness (SIT) is a key parameter of scientific interest because understanding the natural spatiotemporal variability of ice thickness is critical for improving global climate models. In this paper, changes in Arctic SIT during 1982-2003 are examined using a neural network (NN) algorithm trained with in situ submarine ice draft and surface drilling data. For each month of the study period, the NN individually estimated SIT of each ice-covered pixel (25-km resolution) based on seven geophysical parameters (four shortwave and longwave radiative fluxes, surface air temperature, ice drift velocity, and ice divergence/convergence) that were cumulatively summed at each monthly position along the pixel's previous 3-yr drift track (or less if the ice was <3 yr old). Average January SIT increased during 1982-88 in most regions of the Arctic (+7.6 ?? 0.9 cm yr-1), decreased through 1996 Arctic-wide (-6.1 ?? 1.2 cm yr-1), then modestly increased through 2003 mostly in the central Arctic (+2.1 ?? 0.6 cm yr-1). Net ice volume change in the Arctic Ocean from 1982 to 2003 was negligible, indicating that cumulative ice growth had largely replaced the estimated 45 000 km3 of ice lost by cumulative export. Above 65??N, total annual ice volume and interannual volume changes were correlated with the Arctic Oscillation (AO) at decadal and annual time scales, respectively. Late-summer ice thickness and total volume varied proportionally until the mid-1990s, but volume did not increase commensurate with the thickening during 1996-2002. The authors speculate that decoupling of the ice thickness-volume relationship resulted from two opposing mechanisms with different latitudinal expressions: a recent quasi-decadal shift in atmospheric circulation patterns associated with the AO's neutral state facilitated ice thickening at high latitudes while anomalously warm thermal forcing thinned and melted the ice cap at its periphery. ?? 2008 American Meteorological Society.

  20. Enhancing Hohlraum Design with Artificial Neural Networks

    Science.gov (United States)

    Peterson, J. L.; Berzak Hopkins, L. F.; Humbird, K. D.; Brandon, S. T.; Field, J. E.; Langer, S. H.; Nora, R. C.; Spears, B. K.

    2017-10-01

    A primary goal of hohlraum design is to efficiently convert available laser power and energy to capsule drive, compression and ultimately fusion neutron yield. However, a major challenge of this multi-dimensional optimization problem is the relative computational expense of hohlraum simulations. In this work, we explore overcoming this obstacle with the use of artificial neural networks built off ensembles of hohlraum simulations. These machine learning systems emulate the behavior of full simulations in a fraction of the time, thereby enabling the rapid exploration of design parameters. We will demonstrate this technology with a search for modifications to existing high-yield designs that can maximize neutron production within NIF's current laser power and energy constraints. This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344. LLNL-ABS-734401.

  1. Neural networks in support of manned space

    Science.gov (United States)

    Werbos, Paul J.

    1989-01-01

    Many lobbyists in Washington have argued that artificial intelligence (AI) is an alternative to manned space activity. In actuality, this is the opposite of the truth, especially as regards artificial neural networks (ANNs), that form of AI which has the greatest hope of mimicking human abilities in learning, ability to interface with sensors and actuators, flexibility and balanced judgement. ANNs and their relation to expert systems (the more traditional form of AI), and the limitations of both technologies are briefly reviewed. A Few highlights of recent work on ANNs, including an NSF-sponsored workshop on ANNs for control applications are given. Current thinking on ANNs for use in certain key areas (the National Aerospace Plane, teleoperation, the control of large structures, fault diagnostics, and docking) which may be crucial to the long term future of man in space is discussed.

  2. Neural Network for Estimating Conditional Distribution

    DEFF Research Database (Denmark)

    Schiøler, Henrik; Kulczycki, P.

    Neural networks for estimating conditional distributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency is proved from a mild set of assumptions. A number of applications within...... statistcs, decision theory and signal processing are suggested, and a numerical example illustrating the capabilities of the elaborated network is given...

  3. 1991 IEEE International Joint Conference on Neural Networks, Singapore, Nov. 18-21, 1991, Proceedings. Vols. 1-3

    Energy Technology Data Exchange (ETDEWEB)

    1991-01-01

    The present conference the application of neural networks to associative memories, neurorecognition, hybrid systems, supervised and unsupervised learning, image processing, neurophysiology, sensation and perception, electrical neurocomputers, optimization, robotics, machine vision, sensorimotor control systems, and neurodynamics. Attention is given to such topics as optimal associative mappings in recurrent networks, self-improving associative neural network models, fuzzy activation functions, adaptive pattern recognition with sparse associative networks, efficient question-answering in a hybrid system, the use of abstractions by neural networks, remote-sensing pattern classification, speech recognition with guided propagation, inverse-step competitive learning, and rotational quadratic function neural networks. Also discussed are electrical load forecasting, evolutionarily stable and unstable strategies, the capacity of recurrent networks, neural net vs control theory, perceptrons for image recognition, storage capacity of bidirectional associative memories, associative random optimization for control, automatic synthesis of digital neural architectures, self-learning robot vision, and the associative dynamics of chaotic neural networks.

  4. 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.

  5. Neural networks within multi-core optic fibers

    Science.gov (United States)

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

    2016-07-01

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

  6. An interpretation of neural networks as inference engines with application to transformer failure diagnosis

    Energy Technology Data Exchange (ETDEWEB)

    Castro, Adriana R. Garcez; Miranda, Vladimiro [Instituto de Engenharia de Sistemas e Computadores do Porto, INESC Porto (Portugal)

    2005-12-01

    An artificial neural network concept has been developed for transformer fault diagnosis using dissolved gas-in-oil analysis (DGA). A new methodology for mapping the neural network into a rule-based inference system is described. This mapping makes explicit the knowledge implicitly captured by the neural network during the learning stage, by transforming it into a Fuzzy Inference System. Some studies are reported, illustrating the good results obtained. (author)

  7. A Simple Shallow Convolutional Neural Network for Accurate Handwritten Digit Classification

    OpenAIRE

    Golovko, V.; Mikhno, E.; Brichk, A.

    2016-01-01

    At present the deep neural network is the hottest topic in the domain of machine learning and can accomplish a deep hierarchical representation of the input data. Due to deep architecture the large convolutional neural networks can reach very small test error rates below 0.4% using the MNIST database. In this work we have shown, that high accuracy can be achieved using reduced shallow convolutional neural network without adding distortions for digits. The main contribu...

  8. 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...

  9. Comparison of breast DCE-MRI contrast time points for predicting response to neoadjuvant chemotherapy using deep convolutional neural network features with transfer learning

    Science.gov (United States)

    Huynh, Benjamin Q.; Antropova, Natasha; Giger, Maryellen L.

    2017-03-01

    DCE-MRI datasets have a temporal aspect to them, resulting in multiple regions of interest (ROIs) per subject, based on contrast time points. It is unclear how the different contrast time points vary in terms of usefulness for computer-aided diagnosis tasks in conjunction with deep learning methods. We thus sought to compare the different DCE-MRI contrast time points with regard to how well their extracted features predict response to neoadjuvant chemotherapy within a deep convolutional neural network. Our dataset consisted of 561 ROIs from 64 subjects. Each subject was categorized as a non-responder or responder, determined by recurrence-free survival. First, features were extracted from each ROI using a convolutional neural network (CNN) pre-trained on non-medical images. Linear discriminant analysis classifiers were then trained on varying subsets of these features, based on their contrast time points of origin. Leave-one-out cross validation (by subject) was used to assess performance in the task of estimating probability of response to therapy, with area under the ROC curve (AUC) as the metric. The classifier trained on features from strictly the pre-contrast time point performed the best, with an AUC of 0.85 (SD = 0.033). The remaining classifiers resulted in AUCs ranging from 0.71 (SD = 0.028) to 0.82 (SD = 0.027). Overall, we found the pre-contrast time point to be the most effective at predicting response to therapy and that including additional contrast time points moderately reduces variance.

  10. Neural network for prediction of superheater fireside corrosion

    Energy Technology Data Exchange (ETDEWEB)

    Makkonen, P. [Foster Wheeler Energia Oy, Karhula R and D Center, Karhula (Finland)

    1998-12-31

    Superheater corrosion causes vast annual losses to the power companies. If the corrosion could be reliably predicted, new power plants could be designed accordingly, and knowledge of fuel selection and determination of process conditions could be utilized to minimize superheater corrosion. If relations between inputs and the output are poorly known, conventional models depending on corrosion theories will fail. A prediction model based on a neural network is capable of learning from errors and improving its performance as the amount of data increases. The neural network developed during this study predicts superheater corrosion with 80 % accuracy at early stage of the project. (orig.) 10 refs.

  11. 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.

  12. INTEGRATING ARTIFICIAL NEURAL NETWORKS FOR DEVELOPING TELEMEDICINE SOLUTION

    Directory of Open Access Journals (Sweden)

    Mihaela GHEORGHE

    2015-06-01

    Full Text Available Artificial intelligence is assuming an increasing important role in the telemedicine field, especially neural networks with their ability to achieve meaning from large sets of data characterized by lacking exactness and accuracy. These can be used for assisting physicians or other clinical staff in the process of taking decisions under uncertainty. Thus, machine learning methods which are specific to this technology are offering an approach for prediction based on pattern classification. This paper aims to present the importance of neural networks in detecting trends and extracting patterns which can be used within telemedicine domains, particularly for taking medical diagnosis decisions.

  13. 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

  14. [Medical use of artificial neural networks].

    Science.gov (United States)

    Molnár, B; Papik, K; Schaefer, R; Dombóvári, Z; Fehér, J; Tulassay, Z

    1998-01-04

    The main aim of the research in medical diagnostics is to develop more exact, cost-effective and handsome systems, procedures and methods for supporting the clinicians. In their paper the authors introduce a new method that recently came into the focus referred to as artificial neural networks. Based on the literature of the past 5-6 years they give a brief review--highlighting the most important ones--showing the idea behind neural networks, what they are used for in the medical field. The definition, structure and operation of neural networks are discussed. In the application part they collect examples in order to give an insight in the neural network application research. It is emphasised that in the near future basically new diagnostic equipment can be developed based on this new technology in the field of ECG, EEG and macroscopic and microscopic image analysis systems.

  15. Application of neural networks in coastal engineering

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    methods. That is why it is becoming popular in various fields including coastal engineering. Waves and tides will play important roles in coastal erosion or accretion. This paper briefly describes the back-propagation neural networks and its application...

  16. Additive Feed Forward Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1999-01-01

    This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...

  17. Blood glucose prediction using neural network

    Science.gov (United States)

    Soh, Chit Siang; Zhang, Xiqin; Chen, Jianhong; Raveendran, P.; Soh, Phey Hong; Yeo, Joon Hock

    2008-02-01

    We used neural network for blood glucose level determination in this study. The data set used in this study was collected using a non-invasive blood glucose monitoring system with six laser diodes, each laser diode operating at distinct near infrared wavelength between 1500nm and 1800nm. The neural network is specifically used to determine blood glucose level of one individual who participated in an oral glucose tolerance test (OGTT) session. Partial least squares regression is also used for blood glucose level determination for the purpose of comparison with the neural network model. The neural network model performs better in the prediction of blood glucose level as compared with the partial least squares model.

  18. Using Neural Networks in Diagnosing Breast Cancer

    National Research Council Canada - National Science Library

    Fogel, David

    1997-01-01

    .... In the current study, evolutionary programming is used to train neural networks and linear discriminant models to detect breast cancer in suspicious and microcalcifications using radiographic features and patient age...

  19. Neural Networks in Mobile Robot Motion

    Directory of Open Access Journals (Sweden)

    Danica Janglová

    2004-03-01

    Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the “free” space using ultrasound range finder data. The second neural network “finds” a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.

  20. Isolated Speech Recognition Using Artificial Neural Networks

    National Research Council Canada - National Science Library

    Polur, Prasad

    2001-01-01

    .... A small size vocabulary containing the words YES and NO is chosen. Spectral features using cepstral analysis are extracted per frame and imported to a feedforward neural network which uses a backpropagation with momentum training algorithm...