WorldWideScience

Sample records for boolean neural network

  1. Boolean Factor Analysis by Attractor Neural Network

    Czech Academy of Sciences Publication Activity Database

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

    2007-01-01

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

  2. Neural Network Boolean Factor Analysis and Applications

    Czech Academy of Sciences Publication Activity Database

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

    -: WSEAS Press, 2007 - (Katehakis, M.; And ina, D.; Mastorakis, M.), s. 30-35. (Electrical and Computer Engineering Series). ISBN 978-960-6766-21-3. [CIMMACS'07. WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics. Tenerife (ES), 14.12.2007-16.12.2007] R&D Projects: GA MŠk 1M0567; GA AV ČR 1ET100300414; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : Hopfield neural network * boolean factor analysis * unsupervised learning * dimension reduction * data mining Subject RIV: BB - Applied Statistics, Operational Research

  3. IMS Algorithm for Learning Representations in Boolean Neural Networks

    OpenAIRE

    Biswas, Nripendra N; Murthy, TVMK; Chandrasekhar, M.

    1991-01-01

    A new algorithm for learning representations in Boolean neural networks, where the inputs and outputs are binary bits, is presented. The algorithm has become feasible because of a newly discovered theorem which states that any non-linearly separable Boolean function can be expressed as a convergent series of linearly separable functions connected by the logical OR (+) and the logical INHIBIT (-) operators. The formation of the series is carried out by many important properties exhibited by th...

  4. Binary higher order neural networks for realizing Boolean functions.

    Science.gov (United States)

    Zhang, Chao; Yang, Jie; Wu, Wei

    2011-05-01

    In order to more efficiently realize Boolean functions by using neural networks, we propose a binary product-unit neural network (BPUNN) and a binary π-ς neural network (BPSNN). The network weights can be determined by one-step training. It is shown that the addition " σ," the multiplication " π," and two kinds of special weighting operations in BPUNN and BPSNN can implement the logical operators " ∨," " ∧," and " ¬" on Boolean algebra 〈Z(2),∨,∧,¬,0,1〉 (Z(2)={0,1}), respectively. The proposed two neural networks enjoy the following advantages over the existing networks: 1) for a complete truth table of N variables with both truth and false assignments, the corresponding Boolean function can be realized by accordingly choosing a BPUNN or a BPSNN such that at most 2(N-1) hidden nodes are needed, while O(2(N)), precisely 2(N) or at most 2(N), hidden nodes are needed by existing networks; 2) a new network BPUPS based on a collaboration of BPUNN and BPSNN can be defined to deal with incomplete truth tables, while the existing networks can only deal with complete truth tables; and 3) the values of the weights are all simply -1 or 1, while the weights of all the existing networks are real numbers. Supporting numerical experiments are provided as well. Finally, we present the risk bounds of BPUNN, BPSNN, and BPUPS, and then analyze their probably approximately correct learnability. PMID:21427020

  5. Comparison of Two Neural Networks Approaches to Boolean Matrix Factorization

    Czech Academy of Sciences Publication Activity Database

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

    Los Alamitos: IEEE Computer Society, 2009 - (Snášel, V.; Pokorný, J.; Pichappan, P.; El-Qawasmeh, E.), s. 316-321 ISBN 978-1-4244-4614-8. [NDT 2009. International Conference on Networked Digital Technologies /1./. Ostrava (CZ), 29.07.2009-31.07.2009] R&D Projects: GA ČR GA205/09/1079; GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : data mining * artificial inteligence * neural networks * multivariate statistics * Boolean factor analysis * Hopfield-like neural networks * feed forward neural network Subject RIV: BB - Applied Statistics, Operational Research

  6. Neural Network Based Boolean Factor Analysis of Parliament Voting

    Czech Academy of Sciences Publication Activity Database

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

    Heidelberg : Springer, 2006 - (Rizzi, A.; Vichi, M.), s. 861-868 ISBN 3-7908-1708-2. [COMPSTAT 2006. Symposium /17./. Rome (IN), 28.08.2006-01.09.2006] R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Grant ostatní: RFBR(RU) 05-07-90049 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * neural networks * social networks Subject RIV: BB - Applied Statistics, Operational Research

  7. Learning and Unlearning in Hopfield-Like Neural Network Performing Boolean Factor Analysis

    Czech Academy of Sciences Publication Activity Database

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

    Berlin : Springer, 2010 - (Koronacki, J.; Ras, Z.; Wierzchon, S.; Kacprzyk, J.), s. 501-518 ISBN 978-3-642-05176-0. - (Studies in Computational Intelligence. 262) Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * Hopfield-like neural network * spurious attractors * statistics * bingy data Subject RIV: IN - Informatics, Computer Science

  8. Application of Neural Network Boolean Factor Analysis Procedure to Automatic Conference Papers Categorization

    Czech Academy of Sciences Publication Activity Database

    Húsek, Dušan; Frolov, A. A.; Polyakov, P.Y.; Řezanková, H.; Snášel, V.

    Lisabon : Instituto Nacional de Estatística, 2008 - (Gomes, M.; Pinto Martins, J.; Silva, J.), s. 3739-3742 ISBN 978-972-673-992-0. [ISI 2007. Session of the International Statistical Institute /56./. Lisboa (PT), 22.08.2007-29.08.2007] R&D Projects: GA AV ČR 1ET100300414 Grant ostatní: RFBR(RU) 05-07-90049 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * document classification * automatic concepts search * unsupervised learning * neural network Subject RIV: BB - Applied Statistics, Operational Research

  9. Neural Network Based Boolean Factor Analysis: Efficient Tool for Automated Topics Search.

    Czech Academy of Sciences Publication Activity Database

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

    Amman: Applied Science Private University, 2006 - (Issa, G.; El-Qawasmeh, E.; Raho, G.), s. 321-327 ISBN 9957-8592-0-X. [CSIT 2006. International Multiconference on Computer Science and Information Technology /4./. Amman (JO), 05.04.2006-07.04.2006] R&D Projects: GA AV ČR 1ET100300419 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * neural networks * associative memory * clustering * web searching * semantic web * information retrieval * document indexing * document classification * document processing * data mining * machine learning Subject RIV: BB - Applied Statistics, Operational Research

  10. Attractor Neural Network Combined with Likelihood Maximization Algorithm for Boolean Factor Analysis

    Czech Academy of Sciences Publication Activity Database

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

    Vol. 1. Berlin: Springer, 2012 - (Wang, J.; Yen, G.; Polycarpou, M.), s. 1-10. (Lecture Notes in Computer Science. 7367). ISBN 978-3-642-31345-5. ISSN 0302-9743. [ISNN 2012. International Symposium on Neural Networks /9./. Shenyang (CN), 11.07.2012-14.07.2012] R&D Projects: GA ČR GAP202/10/0262 Grant ostatní: GA MŠk(CZ) ED1.1.00/02.0070 Institutional research plan: CEZ:AV0Z10300504 Keywords : Associative Neural Network * Likelihood Maximization * Boolean Factor Analysis * Binary Matrix factorization * Noise XOR Mixing * Plato Problem * Information Gain * Bars problem * Data Mining * Dimension Reduction * Hebbian Learning * Anti-Hebbian Learning Subject RIV: IN - Informatics, Computer Science

  11. Decisional Processes with Boolean Neural Network: the Emergence of Mental Schemes

    CERN Document Server

    Barnabei, Graziano; Conversano, Ciro; Lensi, Elena

    2010-01-01

    Human decisional processes result from the employment of selected quantities of relevant information, generally synthesized from environmental incoming data and stored memories. Their main goal is the production of an appropriate and adaptive response to a cognitive or behavioral task. Different strategies of response production can be adopted, among which haphazard trials, formation of mental schemes and heuristics. In this paper, we propose a model of Boolean neural network that incorporates these strategies by recurring to global optimization strategies during the learning session. The model characterizes as well the passage from an unstructured/chaotic attractor neural network typical of data-driven processes to a faster one, forward-only and representative of schema-driven processes. Moreover, a simplified version of the Iowa Gambling Task (IGT) is introduced in order to test the model. Our results match with experimental data and point out some relevant knowledge coming from psychological domain.

  12. Decisional Processes with Boolean Neural Network: The Emergence of Mental Schemes

    International Nuclear Information System (INIS)

    Human decisional processes result from the employment of selected quantities of relevant information, generally synthesized from environmental incoming data and stored memories. Their main goal is the production of an appropriate and adaptive response to a cognitive or behavioral task. Different strategies of response production can be adopted, among which haphazard trials, formation of mental schemes and heuristics. In this paper, we propose a model of Boolean neural network that incorporates these strategies by recurring to global optimization strategies during the learning session. The model characterizes as well the passage from an unstructured/chaotic attractor neural network typical of data-driven processes to a faster one, forward-only and representative of schema-driven processes. Moreover, a simplified version of the Iowa Gambling Task (IGT) is introduced in order to test the model. Our results match with experimental data and point out some relevant knowledge coming from psychological domain. (authors)

  13. Random Boolean Networks

    OpenAIRE

    Drossel, Barbara

    2007-01-01

    This review explains in a self-contained way the properties of random Boolean networks and their attractors, with a special focus on critical networks. Using small example networks, analytical calculations, phenomenological arguments, and problems to solve, the basic concepts are introduced and important results concerning phase diagrams, numbers of relevant nodes and attractor properties are derived.

  14. Robust Template Decomposition without Weight Restriction for Cellular Neural Networks Implementing Arbitrary Boolean Functions Using Support Vector Classifiers

    Directory of Open Access Journals (Sweden)

    Yih-Lon Lin

    2013-01-01

    Full Text Available If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

  15. Origin and Elimination of Two Global Spurious Attractors in Hopfield-Like Neural Network Performing Boolean Factor Analysis

    Czech Academy of Sciences Publication Activity Database

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

    2010-01-01

    Roč. 73, č. 7-9 (2010), s. 1394-1404. ISSN 0925-2312 R&D Projects: GA ČR GA205/09/1079; GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * Hopfield neural Network * unsupervised learning * dimension reduction * data mining Subject RIV: IN - Informatics, Computer Science Impact factor: 1.429, year: 2010

  16. Comparison of Neural Network Boolean Factor Analysis Method with Some Other Dimension Reduction Methods on Bars Problem

    Czech Academy of Sciences Publication Activity Database

    Húsek, Dušan; Moravec, P.; Snášel, V.; Frolov, A.; Řezanková, H.; Polyakov, P.Y.

    Berlin : Springer, 2007 - (Ghosh, A.; De, R.), s. 235-243 ISBN 978-3-540-77045-9. - (Lecture Notes in Computer Science. 4815). [PReMI 2007. International Conference /2./. Kolkata (IN), 18.12.2007-22.12.2007] R&D Projects: GA MŠk(CZ) 1M0567; GA AV ČR 1ET100300419 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * neural network * dimension reduction * cluster analysis Subject RIV: BB - Applied Statistics, Operational Research

  17. Boolean networks as modelling framework

    Directory of Open Access Journals (Sweden)

    Florian eGreil

    2012-08-01

    Full Text Available In a network, the components of a given system are represented as nodes, the interactions are abstracted as links between the nodes. Boolean networks refer to a class of dynamics on networks, in fact it is the simplest possible dynamics where each node has a value 0 or 1. This allows to investigate extensively the dynamics both analytically and by numerical experiments. The present article focuses on the theoretical concept of relevant components and the immediate application in plant biology, references for more in-depths treatment of the mathematical details are also given.

  18. Boolean networks with reliable dynamics

    CERN Document Server

    Peixoto, Tiago P

    2009-01-01

    We investigated the properties of Boolean networks that follow a given reliable trajectory in state space. A reliable trajectory is defined as a sequence of states which is independent of the order in which the nodes are updated. We explored numerically the topology, the update functions, and the state space structure of these networks, which we constructed using a minimum number of links and the simplest update functions. We found that the clustering coefficient is larger than in random networks, and that the probability distribution of three-node motifs is similar to that found in gene regulation networks. Among the update functions, only a subset of all possible functions occur, and they can be classified according to their probability. More homogeneous functions occur more often, leading to a dominance of canalyzing functions. Finally, we studied the entire state space of the networks. We observed that with increasing systems size, fixed points become more dominant, moving the networks close to the frozen...

  19. Forced synchronization of autonomous dynamical Boolean networks

    International Nuclear Information System (INIS)

    We present the design of an autonomous time-delay Boolean network realized with readily available electronic components. Through simulations and experiments that account for the detailed nonlinear response of each circuit element, we demonstrate that a network with five Boolean nodes displays complex behavior. Furthermore, we show that the dynamics of two identical networks display near-instantaneous synchronization to a periodic state when forced by a common periodic Boolean signal. A theoretical analysis of the network reveals the conditions under which complex behavior is expected in an individual network and the occurrence of synchronization in the forced networks. This research will enable future experiments on autonomous time-delay networks using readily available electronic components with dynamics on a slow enough time-scale so that inexpensive data collection systems can faithfully record the dynamics

  20. Forced synchronization of autonomous dynamical Boolean networks

    Energy Technology Data Exchange (ETDEWEB)

    Rivera-Durón, R. R., E-mail: roberto.rivera@ipicyt.edu.mx; Campos-Cantón, E., E-mail: eric.campos@ipicyt.edu.mx [División de Matemáticas Aplicadas, Instituto Potosino de Investigación Científica y Tecnológica A. C., Camino a la Presa San José 2055, Col. Lomas 4 Sección, C.P. 78216, San Luis Potosí, S.L.P. (Mexico); Campos-Cantón, I. [Facultad de Ciencias, Universidad Autónoma de San Luis Potosí, Álvaro Obregón 64, C.P. 78000, San Luis Potosí, S.L.P. (Mexico); Gauthier, Daniel J. [Department of Physics and Center for Nonlinear and Complex Systems, Duke University, Box 90305, Durham, North Carolina 27708 (United States)

    2015-08-15

    We present the design of an autonomous time-delay Boolean network realized with readily available electronic components. Through simulations and experiments that account for the detailed nonlinear response of each circuit element, we demonstrate that a network with five Boolean nodes displays complex behavior. Furthermore, we show that the dynamics of two identical networks display near-instantaneous synchronization to a periodic state when forced by a common periodic Boolean signal. A theoretical analysis of the network reveals the conditions under which complex behavior is expected in an individual network and the occurrence of synchronization in the forced networks. This research will enable future experiments on autonomous time-delay networks using readily available electronic components with dynamics on a slow enough time-scale so that inexpensive data collection systems can faithfully record the dynamics.

  1. Boolean network robotics: a proof of concept

    CERN Document Server

    Roli, Andrea; Pinciroli, Carlo; Birattari, Mauro

    2011-01-01

    Dynamical systems theory and complexity science provide powerful tools for analysing artificial agents and robots. Furthermore, they have been recently proposed also as a source of design principles and guidelines. Boolean networks are a prominent example of complex dynamical systems and they have been shown to effectively capture important phenomena in gene regulation. From an engineering perspective, these models are very compelling, because they can exhibit rich and complex behaviours, in spite of the compactness of their description. In this paper, we propose the use of Boolean networks for controlling robots' behaviour. The network is designed by means of an automatic procedure based on stochastic local search techniques. We show that this approach makes it possible to design a network which enables the robot to accomplish a task that requires the capability of navigating the space using a light stimulus, as well as the formation and use of an internal memory.

  2. Effect of memory in non-Markovian Boolean networks

    CERN Document Server

    Ebadi, Haleh; Ausloos, Marcel; Jafari, GholamReza

    2016-01-01

    One successful model of interacting biological systems is the Boolean network. The dynamics of a Boolean network, controlled with Boolean functions, is usually considered to be a Markovian (memory-less) process. However, both self organizing features of biological phenomena and their intelligent nature should raise some doubt about ignoring the history of their time evolution. Here, we extend the Boolean network Markovian approach: we involve the effect of memory on the dynamics. This can be explored by modifying Boolean functions into non-Markovian functions, for example, by investigating the usual non-Markovian threshold function, - one of the most applied Boolean functions. By applying the non-Markovian threshold function on the dynamical process of a cell cycle network, we discover a power law memory with a more robust dynamics than the Markovian dynamics.

  3. Solving the Satisfiability Problem Through Boolean Networks

    OpenAIRE

    Roli, Andrea; Milano, Michela

    2011-01-01

    In this paper we present a new approach to solve the satisfiability problem (SAT), based on boolean networks (BN). We define a mapping between a SAT instance and a BN, and we solve SAT problem by simulating the BN dynamics. We prove that BN fixed points correspond to the SAT solutions. The mapping presented allows to develop a new class of algorithms to solve SAT. Moreover, this new approach suggests new ways to combine symbolic and connectionist computation and provides a general framework f...

  4. Solving the Satisfiability Problem Through Boolean Networks

    CERN Document Server

    Roli, Andrea

    2011-01-01

    In this paper we present a new approach to solve the satisfiability problem (SAT), based on boolean networks (BN). We define a mapping between a SAT instance and a BN, and we solve SAT problem by simulating the BN dynamics. We prove that BN fixed points correspond to the SAT solutions. The mapping presented allows to develop a new class of algorithms to solve SAT. Moreover, this new approach suggests new ways to combine symbolic and connectionist computation and provides a general framework for local search algorithms.

  5. Representations of Boolean Functions by Perceptron Networks

    Czech Academy of Sciences Publication Activity Database

    Kůrková, Věra

    Prague : Institute of Computer Science AS CR, 2014 - (Kůrková, V.; Bajer, L.; Peška, L.; Vojtáš, R.; Holeňa, M.; Nehéz, M.), s. 68-70 ISBN 978-80-87136-19-5. [ITAT 2014. European Conference on Information Technologies - Applications and Theory /14./. Demänovská dolina (SK), 25.09.2014-29.09.2014] R&D Projects: GA MŠk(CZ) LD13002 Institutional support: RVO:67985807 Keywords : perceptron networks * model complexity * Boolean functions Subject RIV: IN - Informatics, Computer Science

  6. ON REDUCED SCALAR EQUATIONS FOR SYNCHRONOUS BOOLEAN NETWORKS

    OpenAIRE

    Ali Muhammad Ali Rushdi; Adnan Ahmad Alsogati

    2013-01-01

    A total description of a synchronous Boolean network is typically achieved by a matrix recurrence relation. A simpler alternative is to use a scalar equation which is a possibly nonlinear equation that involves two or more instances of a single scalar variable and some Boolean operator(s). Further simplification is possible in terms of a linear reduced scalar equation which is the simplest two-term scalar equation that includes no Boolean operators and equates the value of a scalar variable a...

  7. Evolution of a designless nanoparticle network into reconfigurable Boolean logic

    Science.gov (United States)

    Bose, S. K.; Lawrence, C. P.; Liu, Z.; Makarenko, K. S.; van Damme, R. M. J.; Broersma, H. J.; van der Wiel, W. G.

    2015-12-01

    Natural computers exploit the emergent properties and massive parallelism of interconnected networks of locally active components. Evolution has resulted in systems that compute quickly and that use energy efficiently, utilizing whatever physical properties are exploitable. Man-made computers, on the other hand, are based on circuits of functional units that follow given design rules. Hence, potentially exploitable physical processes, such as capacitive crosstalk, to solve a problem are left out. Until now, designless nanoscale networks of inanimate matter that exhibit robust computational functionality had not been realized. Here we artificially evolve the electrical properties of a disordered nanomaterials system (by optimizing the values of control voltages using a genetic algorithm) to perform computational tasks reconfigurably. We exploit the rich behaviour that emerges from interconnected metal nanoparticles, which act as strongly nonlinear single-electron transistors, and find that this nanoscale architecture can be configured in situ into any Boolean logic gate. This universal, reconfigurable gate would require about ten transistors in a conventional circuit. Our system meets the criteria for the physical realization of (cellular) neural networks: universality (arbitrary Boolean functions), compactness, robustness and evolvability, which implies scalability to perform more advanced tasks. Our evolutionary approach works around device-to-device variations and the accompanying uncertainties in performance. Moreover, it bears a great potential for more energy-efficient computation, and for solving problems that are very hard to tackle in conventional architectures.

  8. Evolution of a designless nanoparticle network into reconfigurable Boolean logic.

    Science.gov (United States)

    Bose, S K; Lawrence, C P; Liu, Z; Makarenko, K S; van Damme, R M J; Broersma, H J; van der Wiel, W G

    2015-12-01

    Natural computers exploit the emergent properties and massive parallelism of interconnected networks of locally active components. Evolution has resulted in systems that compute quickly and that use energy efficiently, utilizing whatever physical properties are exploitable. Man-made computers, on the other hand, are based on circuits of functional units that follow given design rules. Hence, potentially exploitable physical processes, such as capacitive crosstalk, to solve a problem are left out. Until now, designless nanoscale networks of inanimate matter that exhibit robust computational functionality had not been realized. Here we artificially evolve the electrical properties of a disordered nanomaterials system (by optimizing the values of control voltages using a genetic algorithm) to perform computational tasks reconfigurably. We exploit the rich behaviour that emerges from interconnected metal nanoparticles, which act as strongly nonlinear single-electron transistors, and find that this nanoscale architecture can be configured in situ into any Boolean logic gate. This universal, reconfigurable gate would require about ten transistors in a conventional circuit. Our system meets the criteria for the physical realization of (cellular) neural networks: universality (arbitrary Boolean functions), compactness, robustness and evolvability, which implies scalability to perform more advanced tasks. Our evolutionary approach works around device-to-device variations and the accompanying uncertainties in performance. Moreover, it bears a great potential for more energy-efficient computation, and for solving problems that are very hard to tackle in conventional architectures. PMID:26389658

  9. Consistent stabilizability of switched Boolean networks.

    Science.gov (United States)

    Li, Haitao; Wang, Yuzhen

    2013-10-01

    This paper investigates the consistent stabilizability of switched Boolean networks (SBNs) by using the semi-tensor product method, and presents a number of new results. First, an algebraic expression of SBNs is obtained by the semi-tensor product, based on which the consistent stabilizability is then studied for SBNs and some necessary and sufficient conditions are presented for the design of free-form and state-feedback switching signals, respectively. Finally, the consistent stabilizability of SBNs with state constraints is considered and some necessary and sufficient conditions are proposed. The study of illustrative examples shows that the new results obtained in this paper are very effective in designing switching signals for the consistent stabilizability of SBNs. PMID:23787170

  10. Boolean network model predicts knockout mutant phenotypes of fission yeast.

    Directory of Open Access Journals (Sweden)

    Maria I Davidich

    Full Text Available BOOLEAN NETWORKS (OR: networks of switches are extremely simple mathematical models of biochemical signaling networks. Under certain circumstances, Boolean networks, despite their simplicity, are capable of predicting dynamical activation patterns of gene regulatory networks in living cells. For example, the temporal sequence of cell cycle activation patterns in yeasts S. pombe and S. cerevisiae are faithfully reproduced by Boolean network models. An interesting question is whether this simple model class could also predict a more complex cellular phenomenology as, for example, the cell cycle dynamics under various knockout mutants instead of the wild type dynamics, only. Here we show that a Boolean network model for the cell cycle control network of yeast S. pombe correctly predicts viability of a large number of known mutants. So far this had been left to the more detailed differential equation models of the biochemical kinetics of the yeast cell cycle network and was commonly thought to be out of reach for models as simplistic as Boolean networks. The new results support our vision that Boolean networks may complement other mathematical models in systems biology to a larger extent than expected so far, and may fill a gap where simplicity of the model and a preference for an overall dynamical blueprint of cellular regulation, instead of biochemical details, are in the focus.

  11. Measuring Mutual Information in Random Boolean Networks

    CERN Document Server

    Luque, B; Luque, Bartolo; Ferrera, Antonio

    1999-01-01

    During the last few years an area of active research in the field of complex systems is that of their information storing and processing abilities. Common opinion has it that the most interesting beaviour of these systems is found ``at the edge of chaos'', which would seem to suggest that complex systems may have inherently non-trivial information proccesing abilities in the vicinity of sharp phase transitions. A comprenhensive, quantitative understanding of why this is the case is however still lacking. Indeed, even ``experimental'' (i.e., often numerical) evidence that this is so has been questioned for a number of systems. In this paper we will investigate, both numerically and analitically, the behavior of Random Boolean Networks (RBN's) as they undergo their order-disorder phase transition. We will use a simple mean field approximation to treat the problem, and without lack of generality we will concentrate on a particular value for the connectivity of the system. In spite of the simplicity of our argume...

  12. Enhancing Boolean networks with fuzzy operators and edge tuning

    OpenAIRE

    Poret, Arnaud; Monteiro Sousa, Claudio; Boissel, Jean-Pierre

    2014-01-01

    Quantitative modeling in systems biology can be difficult due to the scarcity of quantitative details about biological phenomenons, especially at the subcellular scale. An alternative to escape this difficulty is qualitative modeling since it requires few to no quantitative information. Among the qualitative modeling approaches, the Boolean network formalism is one of the most popular. However, Boolean models allow variables to be valued at only true or false, which can appear too simplistic ...

  13. The Influence of Canalization on the Robustness of Boolean Networks

    CERN Document Server

    Kadelka, Claus; Laubenbacher, Reinhard

    2016-01-01

    Time- and state-discrete dynamical systems are frequently used to model molecular networks. This paper provides a collection of mathematical and computational tools for the study of robustness in Boolean network models. The focus is on networks governed by $k$-canalizing functions, a recently introduced class of Boolean functions that contains the well-studied class of nested canalizing functions. The activities and sensitivity of a function quantify the impact of input changes on the function output. This paper generalizes the latter concept to $c$-sensitivity and provides formulas for the activities and $c$-sensitivity of general $k$-canalizing functions as well as canalizing functions with more precisely defined structure. A popular measure for the robustness of a network, the Derrida value, can be expressed as a weighted sum of the $c$-sensitivities of the governing canalizing functions, and can also be calculated for a stochastic extension of Boolean networks. These findings provide a computationally eff...

  14. Classes of feedforward neural networks and their circuit complexity

    OpenAIRE

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

    1992-01-01

    This paper aims to place neural networks in the context of boolean circuit complexity. We define appropriate classes of feedforward neural networks with specified fan-in, accuracy of computation and depth and using techniques of communication complexity proceed to show that the classes fit into a well-studied hierarchy of boolean circuits. Results cover both classes of sigmoid activation function networks and linear threshold networks. This provides a much needed theoretical basis for the stu...

  15. Neural Networks

    International Nuclear Information System (INIS)

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

  16. ON REDUCED SCALAR EQUATIONS FOR SYNCHRONOUS BOOLEAN NETWORKS

    Directory of Open Access Journals (Sweden)

    Ali Muhammad Ali Rushdi

    2013-01-01

    Full Text Available A total description of a synchronous Boolean network is typically achieved by a matrix recurrence relation. A simpler alternative is to use a scalar equation which is a possibly nonlinear equation that involves two or more instances of a single scalar variable and some Boolean operator(s. Further simplification is possible in terms of a linear reduced scalar equation which is the simplest two-term scalar equation that includes no Boolean operators and equates the value of a scalar variable at a latter instance t2 to its value at an earlier instance t1. This equation remains valid when the times t1 and t2 are both augmented by any integral multiple of the underlying time period. In other words, there are infinitely many versions of a reduced scalar equation, any of which is useful for deducing information about the cyclic behavior of the network. However, to obtain correct information about the transient behavior of the network, one must find the true reduced scalar equation for which instances t1 and t2 are minimal. This study investigates the nature, derivation and utilization of reduced scalar equations. It relies on Boolean-algebraic manipulations for the derivation of such equations and suggests that this derivation can be facilitated by seeking certain orthogonality relations among certain successive (albeit not necessarily consecutive instances of the same scalar variable. We demonstrate, contrary to previously published assumptions or assertions, that there is typically no common reduced scalar equation for all the scalar variables. Each variable usually satisfies its own distinct reduced scalar equation. We also demonstrate that the derivation of a reduced scalar equation is achieved not only by proving it but also by disproving an immediately preceding version of it when such a version might exist. We also demonstrate that, despite the useful insight supplied by the reduced scalar equations, they do not provide a total solution like the

  17. Optimal Computation of Symmetric Boolean Functions in Collocated Networks

    CERN Document Server

    Kowshik, Hemant

    2011-01-01

    We consider collocated wireless sensor networks, where each node has a Boolean measurement and the goal is to compute a given Boolean function of these measurements. We first consider the worst case setting and study optimal block computation strategies for computing symmetric Boolean functions. We study three classes of functions: threshold functions, delta functions and interval functions. We provide exactly optimal strategies for the first two classes, and a scaling law order-optimal strategy with optimal preconstant for interval functions. We also extend the results to the case of integer measurements and certain integer-valued functions. We use lower bounds from communication complexity theory, and provide an achievable scheme using information theoretic tools. Next, we consider the case where nodes measurements are random and drawn from independent Bernoulli distributions. We address the problem of optimal function computation so as to minimize the expected total number of bits that are transmitted. In ...

  18. Boolean network representation of contagion dynamics during a financial crisis

    Science.gov (United States)

    Caetano, Marco Antonio Leonel; Yoneyama, Takashi

    2015-01-01

    This work presents a network model for representation of the evolution of certain patterns of economic behavior. More specifically, after representing the agents as points in a space in which each dimension associated to a relevant economic variable, their relative "motions" that can be either stationary or discordant, are coded into a boolean network. Patterns with stationary averages indicate the maintenance of status quo, whereas discordant patterns represent aggregation of new agent into the cluster or departure from the former policies. The changing patterns can be embedded into a network representation, particularly using the concept of autocatalytic boolean networks. As a case study, the economic tendencies of the BRIC countries + Argentina were studied. Although Argentina is not included in the cluster formed by BRIC countries, it tends to follow the BRIC members because of strong commercial ties.

  19. Algorithms for Finding Small Attractors in Boolean Networks

    Directory of Open Access Journals (Sweden)

    Hayashida Morihiro

    2007-01-01

    Full Text Available A Boolean network is a model used to study the interactions between different genes in genetic regulatory networks. In this paper, we present several algorithms using gene ordering and feedback vertex sets to identify singleton attractors and small attractors in Boolean networks. We analyze the average case time complexities of some of the proposed algorithms. For instance, it is shown that the outdegree-based ordering algorithm for finding singleton attractors works in time for , which is much faster than the naive time algorithm, where is the number of genes and is the maximum indegree. We performed extensive computational experiments on these algorithms, which resulted in good agreement with theoretical results. In contrast, we give a simple and complete proof for showing that finding an attractor with the shortest period is NP-hard.

  20. Neural networks

    Czech Academy of Sciences Publication Activity Database

    Vajda, Igor; Grim, Jiří

    Oxford : Eolss Publishers-UNESCO, 2008 - (Parra-Luna, F.), s. 224-248 ISBN 978-1-84826-654-4. - (Encyclopedia of Life Support Systems. Volume III) R&D Projects: GA ČR GA102/07/1594 Institutional research plan: CEZ:AV0Z10750506 Keywords : neural networks * probabilistic approach Subject RIV: BD - Theory of Information http://library.utia.cas.cz/separaty/2008/SI/vajda-systems science and cybernetics .pdf

  1. The value of less connected agents in Boolean networks

    Science.gov (United States)

    Epstein, Daniel; Bazzan, Ana L. C.

    2013-11-01

    In multiagent systems, agents often face binary decisions where one seeks to take either the minority or the majority side. Examples are minority and congestion games in general, i.e., situations that require coordination among the agents in order to depict efficient decisions. In minority games such as the El Farol Bar Problem, previous works have shown that agents may reach appropriate levels of coordination, mostly by looking at the history of past decisions. Not many works consider any kind of structure of the social network, i.e., how agents are connected. Moreover, when structure is indeed considered, it assumes some kind of random network with a given, fixed connectivity degree. The present paper departs from the conventional approach in some ways. First, it considers more realistic network topologies, based on preferential attachments. This is especially useful in social networks. Second, the formalism of random Boolean networks is used to help agents to make decisions given their attachments (for example acquaintances). This is coupled with a reinforcement learning mechanism that allows agents to select strategies that are locally and globally efficient. Third, we use agent-based modeling and simulation, a microscopic approach, which allows us to draw conclusions about individuals and/or classes of individuals. Finally, for the sake of illustration we use two different scenarios, namely the El Farol Bar Problem and a binary route choice scenario. With this approach we target systems that adapt dynamically to changes in the environment, including other adaptive decision-makers. Our results using preferential attachments and random Boolean networks are threefold. First we show that an efficient equilibrium can be achieved, provided agents do experimentation. Second, microscopic analysis show that influential agents tend to consider few inputs in their Boolean functions. Third, we have also conducted measurements related to network clustering and centrality

  2. Self-organized networks of competing boolean agents

    Science.gov (United States)

    Paczuski; Bassler; Corral

    2000-04-01

    A model of Boolean agents competing in a market is presented where each agent bases his action on information obtained from a small group of other agents. The agents play a competitive game that rewards those in the minority. After a long time interval, the poorest player's strategy is changed randomly, and the process is repeated. Eventually the network evolves to a stationary but intermittent state where random mutation of the worst strategy can change the behavior of the entire network, often causing a switch in the dynamics between attractors of vastly different lengths. PMID:11019043

  3. Chaos synchronization of two stochastically coupled random Boolean networks

    Energy Technology Data Exchange (ETDEWEB)

    Hung, Y.-C. [Department of Physics, National Sun Yat-sen University, Kaohsiung, Taiwan (China) and Nonlinear Science Group, Department of Physics, National Kaohsiung Normal University, Kaohsiung, Taiwan (China)]. E-mail: d9123801@student.nsysu.edu.tw; Ho, M.-C. [Nonlinear Science Group, Department of Physics, National Kaohsiung Normal University, Kaohsiung, Taiwan (China)]. E-mail: t1603@nknucc.nknu.edu.tw; Lih, J.-S. [Department of Physics and Geoscience, National Pingtung University of Education, Pingtung, Taiwan (China); Nonlinear Science Group, Department of Physics, National Kaohsiung Normal University, Kaohsiung, Taiwan (China); Jiang, I-M. [Department of Physics, National Sun Yat-sen University, Kaohsiung, Taiwan (China); Nonlinear Science Group, Department of Physics, National Kaohsiung Normal University, Kaohsiung, Taiwan (China)

    2006-07-24

    In this Letter, we study the chaos synchronization of two stochastically coupled random Boolean networks (RBNs). Instead of using the 'site-by-site and all-to-all' coupling, the coupling mechanism we consider here is that: the nth cell in a network is linked by an arbitrarily chosen cell in the other network with probability {rho}, and it possesses no links with probability 1-{rho}. The mechanism is useful to investigate the coevolution of biological species via horizontal genetic exchange. We show that the density evolution of networks can be described by two deterministic coupled polynomial maps. The complete synchronization occurs when the coupling parameter exceeds a critical value. Moreover, the reverse bifurcations in inhomogeneous condition are observed and under our discussion.

  4. Harmonic Analysis of Boolean Networks: Determinative Power and Perturbations

    CERN Document Server

    Heckel, Reinhard; Bossert, Martin

    2011-01-01

    Consider a large Boolean network with a feed forward structure. Given a probability distribution for the inputs, can one find-possibly small-collections of input nodes that determine the states of most other nodes in the network? To identify these nodes, a notion that quantifies the determinative power of an input over states in the network is needed. We argue that the mutual information (MI) between a subset of the inputs X = {X_1, ..., X_n} of node i and the function f_i(X)$ associated with node i quantifies the determinative power of this subset of inputs over node i. To study the relation of determinative power to sensitivity to perturbations, we relate the MI to measures of perturbations, such as the influence of a variable, in terms of inequalities. The result shows that, maybe surprisingly, an input that has large influence does not necessarily have large determinative power. The main tool for the analysis is Fourier analysis of Boolean functions. Whether a function is sensitive to perturbations or not...

  5. Evolution and Controllability of Cancer Networks: A Boolean Perspective.

    Science.gov (United States)

    Srihari, Sriganesh; Raman, Venkatesh; Leong, Hon Wai; Ragan, Mark A

    2014-01-01

    Cancer forms a robust system capable of maintaining stable functioning (cell sustenance and proliferation) despite perturbations. Cancer progresses as stages over time typically with increasing aggressiveness and worsening prognosis. Characterizing these stages and identifying the genes driving transitions between them is critical to understand cancer progression and to develop effective anti-cancer therapies. In this work, we propose a novel model for the `cancer system' as a Boolean state space in which a Boolean network, built from protein-interaction and gene-expression data from different stages of cancer, transits between Boolean satisfiability states by "editing" interactions and "flipping" genes. Edits reflect rewiring of the PPI network while flipping of genes reflect activation or silencing of genes between stages. We formulate a minimization problem min flip to identify these genes driving the transitions. The application of our model (called BoolSpace) on three case studies-pancreatic and breast tumours in human and post spinal-cord injury (SCI) in rats-reveals valuable insights into the phenomenon of cancer progression: (i) interactions involved in core cell-cycle and DNA-damage repair pathways are significantly rewired in tumours, indicating significant impact to key genome-stabilizing mechanisms; (ii) several of the genes flipped are serine/threonine kinases which act as biological switches, reflecting cellular switching mechanisms between stages; and (iii) different sets of genes are flipped during the initial and final stages indicating a pattern to tumour progression. Based on these results, we hypothesize that robustness of cancer partly stems from "passing of the baton" between genes at different stages-genes from different biological processes and/or cellular components are involved in different stages of tumour progression thereby allowing tumour cells to evade targeted therapy, and therefore an effective therapy should target a "cover set" of

  6. Damage spreading in spatial and small-world random boolean networks

    Energy Technology Data Exchange (ETDEWEB)

    Lu, Qiming [Los Alamos National Laboratory; Teuscher, Christof [Los Alamos National Laboratory

    2008-01-01

    Random Boolean Networks (RBNs) are often used as generic models for certain dynamics of complex systems, ranging from social networks, neural networks, to gene or protein interaction networks. Traditionally, RBNs are interconnected randomly and without considering any spatial arrangement of the links and nodes. However, most real-world networks are spatially extended and arranged with regular, small-world, or other non-random connections. Here we explore the RBN network topology between extreme local connections, random small-world, and random networks, and study the damage spreading with small perturbations. We find that spatially local connections change the scaling of the relevant component at very low connectivities ({bar K} << 1) and that the critical connectivity of stability K{sub s} changes compared to random networks. At higher {bar K}, this scaling remains unchanged. We also show that the relevant component of spatially local networks scales with a power-law as the system size N increases, but with a different exponent for local and small-world networks. The scaling behaviors are obtained by finite-size scaling. We further investigate the wiring cost of the networks. From an engineering perspective, our new findings provide the key trade-offs between damage spreading (robustness), the network wiring cost, and the network's communication characteristics.

  7. Simulating Quantitative Cellular Responses Using Asynchronous Threshold Boolean Network Ensembles

    Directory of Open Access Journals (Sweden)

    Shah Imran

    2011-07-01

    Full Text Available Abstract Background With increasing knowledge about the potential mechanisms underlying cellular functions, it is becoming feasible to predict the response of biological systems to genetic and environmental perturbations. Due to the lack of homogeneity in living tissues it is difficult to estimate the physiological effect of chemicals, including potential toxicity. Here we investigate a biologically motivated model for estimating tissue level responses by aggregating the behavior of a cell population. We assume that the molecular state of individual cells is independently governed by discrete non-deterministic signaling mechanisms. This results in noisy but highly reproducible aggregate level responses that are consistent with experimental data. Results We developed an asynchronous threshold Boolean network simulation algorithm to model signal transduction in a single cell, and then used an ensemble of these models to estimate the aggregate response across a cell population. Using published data, we derived a putative crosstalk network involving growth factors and cytokines - i.e., Epidermal Growth Factor, Insulin, Insulin like Growth Factor Type 1, and Tumor Necrosis Factor α - to describe early signaling events in cell proliferation signal transduction. Reproducibility of the modeling technique across ensembles of Boolean networks representing cell populations is investigated. Furthermore, we compare our simulation results to experimental observations of hepatocytes reported in the literature. Conclusion A systematic analysis of the results following differential stimulation of this model by growth factors and cytokines suggests that: (a using Boolean network ensembles with asynchronous updating provides biologically plausible noisy individual cellular responses with reproducible mean behavior for large cell populations, and (b with sufficient data our model can estimate the response to different concentrations of extracellular ligands. Our

  8. Multilayer neural networks with extensively many hidden units.

    Science.gov (United States)

    Rosen-Zvi, M; Engel, A; Kanter, I

    2001-08-13

    The information processing abilities of a multilayer neural network with a number of hidden units scaling as the input dimension are studied using statistical mechanics methods. The mapping from the input layer to the hidden units is performed by general symmetric Boolean functions, whereas the hidden layer is connected to the output by either discrete or continuous couplings. Introducing an overlap in the space of Boolean functions as order parameter, the storage capacity is found to scale with the logarithm of the number of implementable Boolean functions. The generalization behavior is smooth for continuous couplings and shows a discontinuous transition to perfect generalization for discrete ones. PMID:11497920

  9. Multilayer Neural Networks with Extensively Many Hidden Units

    International Nuclear Information System (INIS)

    The information processing abilities of a multilayer neural network with a number of hidden units scaling as the input dimension are studied using statistical mechanics methods. The mapping from the input layer to the hidden units is performed by general symmetric Boolean functions, whereas the hidden layer is connected to the output by either discrete or continuous couplings. Introducing an overlap in the space of Boolean functions as order parameter, the storage capacity is found to scale with the logarithm of the number of implementable Boolean functions. The generalization behavior is smooth for continuous couplings and shows a discontinuous transition to perfect generalization for discrete ones

  10. On analog implementations of discrete neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Beiu, V.; Moore, K.R.

    1998-12-01

    The paper will show that in order to obtain minimum size neural networks (i.e., size-optimal) for implementing any Boolean function, the nonlinear activation function of the neutrons has to be the identity function. The authors shall shortly present many results dealing with the approximation capabilities of neural networks, and detail several bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions they will show that implementing Boolean functions can be done using neurons having an identity nonlinear function. It follows that size-optimal solutions can be obtained only using analog circuitry. Conclusions, and several comments on the required precision are ending the paper.

  11. Holographic neural networks

    OpenAIRE

    Manger, R

    1998-01-01

    Holographic neural networks are a new and promising type of artificial neural networks. This article gives an overview of the holographic neural technology and its possibilities. The theoretical principles of holographic networks are first reviewed. Then, some other papers are presented, where holographic networks have been applied or experimentally evaluated. A case study dealing with currency exchange rate prediction is described in more detail.

  12. A SAT-based algorithm for finding attractors in synchronous Boolean networks.

    Science.gov (United States)

    Dubrova, Elena; Teslenko, Maxim

    2011-01-01

    This paper addresses the problem of finding attractors in synchronous Boolean networks. The existing Boolean decision diagram-based algorithms have limited capacity due to the excessive memory requirements of decision diagrams. The simulation-based algorithms can be applied to larger networks, however, they are incomplete. We present an algorithm, which uses a SAT-based bounded model checking to find all attractors in a Boolean network. The efficiency of the presented algorithm is evaluated by analyzing seven networks models of real biological processes, as well as 150,000 randomly generated Boolean networks of sizes between 100 and 7,000. The results show that our approach has a potential to handle an order of magnitude larger models than currently possible. PMID:21778527

  13. Modeling integrated cellular machinery using hybrid Petri-Boolean networks.

    Directory of Open Access Journals (Sweden)

    Natalie Berestovsky

    Full Text Available The behavior and phenotypic changes of cells are governed by a cellular circuitry that represents a set of biochemical reactions. Based on biological functions, this circuitry is divided into three types of networks, each encoding for a major biological process: signal transduction, transcription regulation, and metabolism. This division has generally enabled taming computational complexity dealing with the entire system, allowed for using modeling techniques that are specific to each of the components, and achieved separation of the different time scales at which reactions in each of the three networks occur. Nonetheless, with this division comes loss of information and power needed to elucidate certain cellular phenomena. Within the cell, these three types of networks work in tandem, and each produces signals and/or substances that are used by the others to process information and operate normally. Therefore, computational techniques for modeling integrated cellular machinery are needed. In this work, we propose an integrated hybrid model (IHM that combines Petri nets and Boolean networks to model integrated cellular networks. Coupled with a stochastic simulation mechanism, the model simulates the dynamics of the integrated network, and can be perturbed to generate testable hypotheses. Our model is qualitative and is mostly built upon knowledge from the literature and requires fine-tuning of very few parameters. We validated our model on two systems: the transcriptional regulation of glucose metabolism in human cells, and cellular osmoregulation in S. cerevisiae. The model produced results that are in very good agreement with experimental data, and produces valid hypotheses. The abstract nature of our model and the ease of its construction makes it a very good candidate for modeling integrated networks from qualitative data. The results it produces can guide the practitioner to zoom into components and interconnections and investigate them

  14. Dynamical modeling of the cholesterol regulatory pathway with Boolean networks

    Directory of Open Access Journals (Sweden)

    Corcos Laurent

    2008-11-01

    Full Text Available Abstract Background Qualitative dynamics of small gene regulatory networks have been studied in quite some details both with synchronous and asynchronous analysis. However, both methods have their drawbacks: synchronous analysis leads to spurious attractors and asynchronous analysis lacks computational efficiency, which is a problem to simulate large networks. We addressed this question through the analysis of a major biosynthesis pathway. Indeed the cholesterol synthesis pathway plays a pivotal role in dislypidemia and, ultimately, in cancer through intermediates such as mevalonate, farnesyl pyrophosphate and geranyl geranyl pyrophosphate, but no dynamic model of this pathway has been proposed until now. Results We set up a computational framework to dynamically analyze large biological networks. This framework associates a classical and computationally efficient synchronous Boolean analysis with a newly introduced method based on Markov chains, which identifies spurious cycles among the results of the synchronous simulation. Based on this method, we present here the results of the analysis of the cholesterol biosynthesis pathway and its physiological regulation by the Sterol Response Element Binding Proteins (SREBPs, as well as the modeling of the action of statins, inhibitor drugs, on this pathway. The in silico experiments show the blockade of the cholesterol endogenous synthesis by statins and its regulation by SREPBs, in full agreement with the known biochemical features of the pathway. Conclusion We believe that the method described here to identify spurious cycles opens new routes to compute large and biologically relevant models, thanks to the computational efficiency of synchronous simulation. Furthermore, to the best of our knowledge, we present here the first dynamic systems biology model of the human cholesterol pathway and several of its key regulatory control elements, hoping it would provide a good basis to perform in silico

  15. Characterizing short-term stability for Boolean networks over any distribution of transfer functions

    Science.gov (United States)

    Seshadhri, C.; Smith, Andrew M.; Vorobeychik, Yevgeniy; Mayo, Jackson R.; Armstrong, Robert C.

    2016-07-01

    We present a characterization of short-term stability of Kauffman's N K (random) Boolean networks under arbitrary distributions of transfer functions. Given such a Boolean network where each transfer function is drawn from the same distribution, we present a formula that determines whether short-term chaos (damage spreading) will happen. Our main technical tool which enables the formal proof of this formula is the Fourier analysis of Boolean functions, which describes such functions as multilinear polynomials over the inputs. Numerical simulations on mixtures of threshold functions and nested canalyzing functions demonstrate the formula's correctness.

  16. Boolean modeling of neural systems with point-process inputs and outputs.

    Science.gov (United States)

    Marmarelis, Vasilis Z; Zanos, Theodoros P; Courellis, Spiros H; Berger, Theodore W

    2006-01-01

    This paper presents a novel modeling approach for neural systems with point-process inputs and outputs (binary time-series of 0's and 1's) that utilizes Boolean operators of modulo-2 multiplication and addition, corresponding to the logical AND and OR operations respectively. The form of the employed mathematical model is akin to a "Boolean-Volterra" model that contains the product terms of all relevant input lags in a hierarchical order, where terms of order higher than first represent nonlinear interactions among the various lagged values of each input point-process or among lagged values of various inputs (if multiple inputs exist) as they reflect on the output. The coefficients of this Boolean model are also binary variables that indicate the presence or absence of the respective term in each specific model/system. Simulations are used to explore the properties of such models and the feasibility of accurate estimation of such models from short data-records in the presence of noise (i.e. spurious spikes). The results demonstrate the feasibility of obtaining reliable estimates of such models, even in the presence of considerable noise in the input and/or output, thus making the proposed approach an attractive candidate for modeling neural systems in a practical context. PMID:17946091

  17. SAT-based Distributed Reactive Control Protocol Synthesis for Boolean Networks

    OpenAIRE

    Sahin, Yunus Emre; Ozay, Necmiye

    2016-01-01

    This paper considers the synthesis of distributed reactive control protocols for a Boolean network in a distributed manner. We start with a directed acyclic graph representing a network of Boolean subsystems and a global contract, given as an assumption-guarantee pair. Assumption captures the environment behavior, and guarantee is the requirements to be satisfied by the system. Local assumption-guarantee contracts, together with local control protocols ensuring these local contracts, are comp...

  18. Propagation of external regulation and asynchronous dynamics in random Boolean networks

    OpenAIRE

    Mahmoudi, Hamed; Pagnani, Andrea; Weigt, Martin; Zecchina, Riccardo

    2007-01-01

    Boolean Networks and their dynamics are of great interest as abstract modeling schemes in various disciplines, ranging from biology to computer science. Whereas parallel update schemes have been studied extensively in past years, the level of understanding of asynchronous updates schemes is still very poor. In this paper we study the propagation of external information given by regulatory input variables into a random Boolean network. We compute both analytically and numerically the time evol...

  19. Neural Networks, Game Theory and Time Series Generation

    OpenAIRE

    Metzler, Richard

    2002-01-01

    This dissertation highlights connections between the fields of neural networks, game theory and time series generation. The concept of antipredictability is explained, and the properties of time series that are antipredictable for several prototypical prediction algorithms (neural networks, Boolean funtions etc.) are studied. The Minority Game provides a framework in which antipredictability arises naturally. Several variations of the MG are introduced and compared, including extensions to mo...

  20. Polynomial-Time Algorithm for Controllability Test of a Class of Boolean Biological Networks

    Directory of Open Access Journals (Sweden)

    Koichi Kobayashi

    2010-01-01

    Full Text Available In recent years, Boolean-network-model-based approaches to dynamical analysis of complex biological networks such as gene regulatory networks have been extensively studied. One of the fundamental problems in control theory of such networks is the problem of determining whether a given substance quantity can be arbitrarily controlled by operating the other substance quantities, which we call the controllability problem. This paper proposes a polynomial-time algorithm for solving this problem. Although the algorithm is based on a sufficient condition for controllability, it is easily computable for a wider class of large-scale biological networks compared with the existing approaches. A key to this success in our approach is to give up computing Boolean operations in a rigorous way and to exploit an adjacency matrix of a directed graph induced by a Boolean network. By applying the proposed approach to a neurotransmitter signaling pathway, it is shown that it is effective.

  1. Chaotic diagonal recurrent neural network

    Institute of Scientific and Technical Information of China (English)

    Wang Xing-Yuan; Zhang Yi

    2012-01-01

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

  2. Chaotic diagonal recurrent neural network

    International Nuclear Information System (INIS)

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

  3. Relative stability of network states in Boolean network models of gene regulation in development.

    Science.gov (United States)

    Zhou, Joseph Xu; Samal, Areejit; d'Hérouël, Aymeric Fouquier; Price, Nathan D; Huang, Sui

    2016-01-01

    Progress in cell type reprogramming has revived the interest in Waddington's concept of the epigenetic landscape. Recently researchers developed the quasi-potential theory to represent the Waddington's landscape. The Quasi-potential U(x), derived from interactions in the gene regulatory network (GRN) of a cell, quantifies the relative stability of network states, which determine the effort required for state transitions in a multi-stable dynamical system. However, quasi-potential landscapes, originally developed for continuous systems, are not suitable for discrete-valued networks which are important tools to study complex systems. In this paper, we provide a framework to quantify the landscape for discrete Boolean networks (BNs). We apply our framework to study pancreas cell differentiation where an ensemble of BN models is considered based on the structure of a minimal GRN for pancreas development. We impose biologically motivated structural constraints (corresponding to specific type of Boolean functions) and dynamical constraints (corresponding to stable attractor states) to limit the space of BN models for pancreas development. In addition, we enforce a novel functional constraint corresponding to the relative ordering of attractor states in BN models to restrict the space of BN models to the biological relevant class. We find that BNs with canalyzing/sign-compatible Boolean functions best capture the dynamics of pancreas cell differentiation. This framework can also determine the genes' influence on cell state transitions, and thus can facilitate the rational design of cell reprogramming protocols. PMID:26965665

  4. Autonomous Modeling, Statistical Complexity and Semi-annealed Treatment of Boolean Networks

    Science.gov (United States)

    Gong, Xinwei

    This dissertation presents three studies on Boolean networks. Boolean networks are a class of mathematical systems consisting of interacting elements with binary state variables. Each element is a node with a Boolean logic gate, and the presence of interactions between any two nodes is represented by directed links. Boolean networks that implement the logic structures of real systems are studied as coarse-grained models of the real systems. Large random Boolean networks are studied with mean field approximations and used to provide a baseline of possible behaviors of large real systems. This dissertation presents one study of the former type, concerning the stable oscillation of a yeast cell-cycle oscillator, and two studies of the latter type, respectively concerning the statistical complexity of large random Boolean networks and an extension of traditional mean field techniques that accounts for the presence of short loops. In the cell-cycle oscillator study, a novel autonomous update scheme is introduced to study the stability of oscillations in small networks. A motif that corrects pulse-growing perturbations and a motif that grows pulses are identified. A combination of the two motifs is capable of sustaining stable oscillations. Examining a Boolean model of the yeast cell-cycle oscillator using an autonomous update scheme yields evidence that it is endowed with such a combination. Random Boolean networks are classified as ordered, critical or disordered based on their response to small perturbations. In the second study, random Boolean networks are taken as prototypical cases for the evaluation of two measures of complexity based on a criterion for optimal statistical prediction. One measure, defined for homogeneous systems, does not distinguish between the static spatial inhomogeneity in the ordered phase and the dynamical inhomogeneity in the disordered phase. A modification in which complexities of individual nodes are calculated yields vanishing

  5. Implementing size-optimal discrete neural networks require analog circuitry

    Energy Technology Data Exchange (ETDEWEB)

    Beiu, V.

    1998-12-01

    This paper starts by overviewing results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions the authors show that implementing Boolean functions can be done using neurons having an identity transfer function. Because in this case the size of the network is minimized, it follows that size-optimal solutions for implementing Boolean functions can be obtained using analog circuitry. Conclusions and several comments on the required precision are ending the paper.

  6. Neural Networks: Implementations and Applications

    OpenAIRE

    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

  7. Evolution of neural networks

    OpenAIRE

    Uršič, Aleš

    2012-01-01

    The goal of this work is construction of an artificial life model and simulation of organisms in an environment with food. Organisms survive if they find food successfuly. With evolution and learning organisms develop a neural network which enables that. First neural networks and their history are introduced with the basic concepts like a neuron model, a network, transfer functions, topologies and learning. I describe the backpropagation learning on multilayer feed forward network and dem...

  8. Mapping Complex Networks: Exploring Boolean Modeling of Signal Transduction Pathways

    OpenAIRE

    Bhardwaj, Gaurav; Wells, Christine P.; Albert, Reka; van Rossum, Damian B.; Patterson, Randen L

    2009-01-01

    In this study, we explored the utility of a descriptive and predictive bionetwork model for phospholipase C-coupled calcium signaling pathways, built with non-kinetic experimental information. Boolean models generated from these data yield oscillatory activity patterns for both the endoplasmic reticulum resident inositol-1,4,5-trisphosphate receptor (IP3R) and the plasma-membrane resident canonical transient receptor potential channel 3 (TRPC3). These results are specific as randomization of ...

  9. 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...

  10. Neural networks for aircraft control

    Science.gov (United States)

    Linse, Dennis

    1990-01-01

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

  11. 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....

  12. 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…

  13. Analysis and control of Boolean networks a semi-tensor product approach

    CERN Document Server

    Cheng, Daizhan; Li, Zhiqiang

    2010-01-01

    This book presents a new approach to the investigation of Boolean control networks, using the semi-tensor product (STP), which can express a logical function as a conventional discrete-time linear system. This makes it possible to analyze basic control problems.

  14. Reverse engineering Boolean networks: from Bernoulli mixture models to rule based systems.

    Directory of Open Access Journals (Sweden)

    Mehreen Saeed

    Full Text Available A Boolean network is a graphical model for representing and analyzing the behavior of gene regulatory networks (GRN. In this context, the accurate and efficient reconstruction of a Boolean network is essential for understanding the gene regulation mechanism and the complex relations that exist therein. In this paper we introduce an elegant and efficient algorithm for the reverse engineering of Boolean networks from a time series of multivariate binary data corresponding to gene expression data. We call our method ReBMM, i.e., reverse engineering based on Bernoulli mixture models. The time complexity of most of the existing reverse engineering techniques is quite high and depends upon the indegree of a node in the network. Due to the high complexity of these methods, they can only be applied to sparsely connected networks of small sizes. ReBMM has a time complexity factor, which is independent of the indegree of a node and is quadratic in the number of nodes in the network, a big improvement over other techniques and yet there is little or no compromise in accuracy. We have tested ReBMM on a number of artificial datasets along with simulated data derived from a plant signaling network. We also used this method to reconstruct a network from real experimental observations of microarray data of the yeast cell cycle. Our method provides a natural framework for generating rules from a probabilistic model. It is simple, intuitive and illustrates excellent empirical results.

  15. Recurrent Neural Network Regularization

    OpenAIRE

    Zaremba, Wojciech; Sutskever, Ilya; Vinyals, Oriol

    2014-01-01

    We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.

  16. Deep Sequential Neural Network

    OpenAIRE

    Denoyer, Ludovic; Gallinari, Patrick

    2014-01-01

    Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. Instead of c...

  17. The Future of Neural Networks

    OpenAIRE

    Lakra, Sachin; T. V. Prasad; G. Ramakrishna

    2012-01-01

    The paper describes some recent developments in neural networks and discusses the applicability of neural networks in the development of a machine that mimics the human brain. The paper mentions a new architecture, the pulsed neural network that is being considered as the next generation of neural networks. The paper also explores the use of memristors in the development of a brain-like computer called the MoNETA. A new model, multi/infinite dimensional neural networks, are a recent developme...

  18. Neural Networks in Data Mining

    OpenAIRE

    Priyanka Gaur

    2012-01-01

    The application of neural networks in the data mining is very wide. Although neural networks may have complex structure, long training time, and uneasily understandable representation of results, neural networks have high acceptance ability for noisy data and high accuracy and are preferable in data mining. In this paper the data mining based on neural networks is researched in detail, and the key technology and ways to achieve the data mining based on neural networks are also researched.

  19. Neural networks and graph theory

    Institute of Scientific and Technical Information of China (English)

    许进; 保铮

    2002-01-01

    The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.

  20. Introduction to neural networks

    International Nuclear Information System (INIS)

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

  1. New Measure of Boolean Factor Analysis Quality

    Czech Academy of Sciences Publication Activity Database

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

    Vol. 1. Heidelberg: Springer, 2011 - (Dobnikar, A.; Lotrič, U.; Šter, B.), s. 100-109. (Lecture Notes in Computer Science. 6593). ISBN 978-3-642-20281-0. ISSN 0302-9743. [ICANNGA'2011. International Conference /10./. Ljubljana (SI), 14.04.2011-16.04.2011] R&D Projects: GA ČR GAP202/10/0262; GA ČR GA205/09/1079 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * information gain * expectation-maximization * associative memory * neural network application * Boolean matrix factorization * bars problem * Hopfield neural network Subject RIV: IN - Informatics, Computer Science

  2. From Boolean Network Model to Continuous Model Helps in Design of Functional Circuits

    OpenAIRE

    Bin Shao; Xiang Liu; Dongliang Zhang; Jiayi Wu; Qi Ouyang

    2015-01-01

    Computational circuit design with desired functions in a living cell is a challenging task in synthetic biology. To achieve this task, numerous methods that either focus on small scale networks or use evolutionary algorithms have been developed. Here, we propose a two-step approach to facilitate the design of functional circuits. In the first step, the search space of possible topologies for target functions is reduced by reverse engineering using a Boolean network model. In the second step, ...

  3. Neural Network Nonlinear Factor Analysis of High Dimensional Binary Signal

    Czech Academy of Sciences Publication Activity Database

    Húsek, Dušan; Řezanková, H.; Snášel, Václav; Frolov, A. A.; Polyakov, P.Y.

    IEEE, 2005 - (Chbeir, R.; Dipanda, A.; Vétongnon, K.), s. 86-89 ISBN 2-9525435-0. [IEEE SITIS 2005. International Conference on Signal & Image Technology and Internet Based Systems /1./. Yaoundé (CM), 27.11.2005-01.12.2005] R&D Projects: GA MŠk 1M0567; GA MŠk 1M0554 Keywords : neural networks * associative memory * Boolean factor analysis * text mining Subject RIV: BA - General Mathematics

  4. Neural Network Analysis of Russian Parliament Voting Patterns

    Czech Academy of Sciences Publication Activity Database

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

    Amman: Applied Science Private University, 2006 - (Issa, G.; El-Qawasmeh, E.; Raho, G.), s. 328-334 ISBN 9957-8592-0-X. [CSIT 2006. International Multiconference on Computer Science and Information Technology /4./. Amman (JO), 05.04.2006-07.04.2006] R&D Projects: GA AV ČR 1ET100300414; GA ČR GA201/05/0079 Grant ostatní: RFBR(RU) 05-07-90049 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural networks * associative memory * recurrent neural network * Boolean factor analysis * clustering * data mining Subject RIV: BB - Applied Statistics, Operational Research

  5. Features Extraction by Hopfield-Like Neural Network

    Czech Academy of Sciences Publication Activity Database

    Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Řezanková, H.; Snášel, Václav; Polyakov, P.Y.

    Malaga : Dpt. de Ingeneria de Sistemas y Automatica, 2003 - (Fernandez de Canete, J.; Tsaptsinos, D.), s. 383-390 ISBN 84-930984-1-8. [EANN'03. International Conference on Engineering Applications of Neural Networks. Malaga (ES), 08.09.2003-10.09.2003] R&D Projects: GA AV ČR IAA2030801; GA ČR GA201/01/1192 Grant ostatní: BARRANDE(XE) 203-030-2 Institutional research plan: AV0Z1030915 Keywords : Boolean factorization * recurrent neural network * single-step approximation Subject RIV: BB - Applied Statistics, Operational Research

  6. 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. PMID:24808287

  7. Exploring phospholipase C-coupled Ca(2+) signalling networks using Boolean modelling.

    Science.gov (United States)

    Bhardwaj, G; Wells, C P; Albert, R; van Rossum, D B; Patterson, R L

    2011-05-01

    In this study, the authors explored the utility of a descriptive and predictive bionetwork model for phospholipase C-coupled calcium signalling pathways, built with non-kinetic experimental information. Boolean models generated from these data yield oscillatory activity patterns for both the endoplasmic reticulum resident inositol-1,4,5-trisphosphate receptor (IP(3)R) and the plasma-membrane resident canonical transient receptor potential channel 3 (TRPC3). These results are specific as randomisation of the Boolean operators ablates oscillatory pattern formation. Furthermore, knock-out simulations of the IP(3)R, TRPC3 and multiple other proteins recapitulate experimentally derived results. The potential of this approach can be observed by its ability to predict previously undescribed cellular phenotypes using in vitro experimental data. Indeed, our cellular analysis of the developmental and calcium-regulatory protein, DANGER1a, confirms the counter-intuitive predictions from our Boolean models in two highly relevant cellular models. Based on these results, the authors theorise that with sufficient legacy knowledge and/or computational biology predictions, Boolean networks can provide a robust method for predictive modelling of any biological system. [Includes supplementary material]. PMID:21639591

  8. Rule Extraction:Using Neural Networks or for Neural Networks?

    Institute of Scientific and Technical Information of China (English)

    Zhi-Hua Zhou

    2004-01-01

    In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.

  9. 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....

  10. Investigating Boolean Matrix Factorization

    Czech Academy of Sciences Publication Activity Database

    Snášel, V.; Platoš, J.; Krömer, P.; Húsek, Dušan; Neruda, Roman; Frolov, A. A.

    - : ACM, 2008 - (Ding, C.; Li, T.; Zhu, S.), s. 18-25 ISBN 978-1-60558-307-5. [DMMT'08. Workshop in Conjunction with SIGKDD 2008 /14./. Las Vegas (US), 24.08.2008-24.08.2008] Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * nonnegative matrix factorization * neural networks * information retrieval * data mining * binary data Subject RIV: BB - Applied Statistics, Operational Research http://users.cs.fiu.edu/~taoli/kdd08-workshop/DMMT08-Proceedings.pdf

  11. 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. .

  12. Detecting small attractors of large Boolean networks by function-reduction-based strategy.

    Science.gov (United States)

    Zheng, Qiben; Shen, Liangzhong; Shang, Xuequn; Liu, Wenbin

    2016-04-01

    Boolean networks (BNs) are widely used to model gene regulatory networks and to design therapeutic intervention strategies to affect the long-term behaviour of systems. A central aim of Boolean-network analysis is to find attractors that correspond to various cellular states, such as cell types or the stage of cell differentiation. This problem is NP-hard and various algorithms have been used to tackle it with considerable success. The idea is that a singleton attractor corresponds to n consistent subsequences in the truth table. To find these subsequences, the authors gradually reduce the entire truth table of Boolean functions by extending a partial gene activity profile (GAP). Not only does this process delete inconsistent subsequences in truth tables, it also directly determines values for some nodes not extended, which means it can abandon the partial GAPs that cannot lead to an attractor as early as possible. The results of simulation show that the proposed algorithm can detect small attractors with length p = 4 in BNs of up to 200 nodes with average indegree K = 2. PMID:26997659

  13. Neural Networks and Micromechanics

    Science.gov (United States)

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

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

  14. Generalized Adaptive Artificial Neural Networks

    Science.gov (United States)

    Tawel, Raoul

    1993-01-01

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

  15. Coevolution of Information Processing and Topology in Hierarchical Adaptive Random Boolean Networks

    CERN Document Server

    Gorski, Piotr J; Holyst, Janusz A

    2015-01-01

    Random Boolean networks (RBNs) are frequently employed for modelling complex systems driven by information processing, e.g. for gene regulatory networks (GRNs). Here we propose a hierarchical adaptive RBN (HARBN) as a system consisting of distinct adaptive RBNs - subnetworks - connected by a set of permanent interlinks. Information measures and internal subnetworks topology of HARBN coevolve and reach steady-states that are specific for a given network structure. We investigate mean node information, mean edge information as well as a mean node degree as functions of model parameters and demonstrate HARBN's ability to describe complex hierarchical systems.

  16. Boolean modeling of neural systems with point-process inputs and outputs. Part I: theory and simulations.

    Science.gov (United States)

    Marmarelis, Vasilis Z; Zanos, Theodoros P; Berger, Theodore W

    2009-08-01

    This paper presents a new modeling approach for neural systems with point-process (spike) inputs and outputs that utilizes Boolean operators (i.e. modulo 2 multiplication and addition that correspond to the logical AND and OR operations respectively, as well as the AND_NOT logical operation representing inhibitory effects). The form of the employed mathematical models is akin to a "Boolean-Volterra" model that contains the product terms of all relevant input lags in a hierarchical order, where terms of order higher than first represent nonlinear interactions among the various lagged values of each input point-process or among lagged values of various inputs (if multiple inputs exist) as they reflect on the output. The coefficients of this Boolean-Volterra model are also binary variables that indicate the presence or absence of the respective term in each specific model/system. Simulations are used to explore the properties of such models and the feasibility of their accurate estimation from short data-records in the presence of noise (i.e. spurious spikes). The results demonstrate the feasibility of obtaining reliable estimates of such models, with excitatory and inhibitory terms, in the presence of considerable noise (spurious spikes) in the outputs and/or the inputs in a computationally efficient manner. A pilot application of this approach to an actual neural system is presented in the companion paper (Part II). PMID:19517238

  17. Random Boolean Networks and Attractors of their Intersecting Circuits

    OpenAIRE

    Demongeot, Jacques; Elena, Adrien; Noual, Mathilde; Sené, Sylvain

    2011-01-01

    International audience The multi-scale strategy in studying biological regulatory networks analysis is based on two level of analysis. The first level is structural and consists in examining the architecture of the interaction graph underlying the network and the second level is functional and analyse the regulatory properties of the network. We apply this dual approach to the "immunetworks" involved in the control of the immune system. As a result, we show that the small number of attract...

  18. Satisfiability of logic programming based on radial basis function neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hamadneh, Nawaf; Sathasivam, Saratha; Tilahun, Surafel Luleseged; Choon, Ong Hong [School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Malaysia)

    2014-07-10

    In this paper, we propose a new technique to test the Satisfiability of propositional logic programming and quantified Boolean formula problem in radial basis function neural networks. For this purpose, we built radial basis function neural networks to represent the proportional logic which has exactly three variables in each clause. We used the Prey-predator algorithm to calculate the output weights of the neural networks, while the K-means clustering algorithm is used to determine the hidden parameters (the centers and the widths). Mean of the sum squared error function is used to measure the activity of the two algorithms. We applied the developed technique with the recurrent radial basis function neural networks to represent the quantified Boolean formulas. The new technique can be applied to solve many applications such as electronic circuits and NP-complete problems.

  19. Dynamical modeling of the cholesterol regulatory pathway with Boolean networks

    OpenAIRE

    Corcos Laurent; Kervizic Gwenael

    2008-01-01

    Abstract Background Qualitative dynamics of small gene regulatory networks have been studied in quite some details both with synchronous and asynchronous analysis. However, both methods have their drawbacks: synchronous analysis leads to spurious attractors and asynchronous analysis lacks computational efficiency, which is a problem to simulate large networks. We addressed this question through the analysis of a major biosynthesis pathway. Indeed the cholesterol synthesis pathway plays a pivo...

  20. Algorithms and Complexity Analyses for Control of Singleton Attractors in Boolean Networks

    Directory of Open Access Journals (Sweden)

    Wai-Ki Ching

    2008-09-01

    Full Text Available A Boolean network (BN is a mathematical model of genetic networks. We propose several algorithms for control of singleton attractors in BN. We theoretically estimate the average-case time complexities of the proposed algorithms, and confirm them by computer experiments. The results suggest the importance of gene ordering. Especially, setting internal nodes ahead yields shorter computational time than setting external nodes ahead in various types of algorithms. We also present a heuristic algorithm which does not look for the optimal solution but for the solution whose computational time is shorter than that of the exact algorithms.

  1. New Neural Network Based Approach Helps to Discover Hidden Russian Parliament Voting Patterns

    Czech Academy of Sciences Publication Activity Database

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

    Madison : Omnipress, 2006, s. 6518-6523. [IJCNN 2006. International Joint Conference on Neural Networks. Vancouver (CA), 16.07.2006-21.07.2006] R&D Projects: GA MŠk(CZ) 1M0567; GA AV ČR 1ET100300414; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : Hopfield like neural network * Boolean factor analysis * Ljapunov function Subject RIV: BB - Applied Statistics, Operational Research

  2. Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Kapil Nahar

    2012-12-01

    Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.

  3. Implementing Neural Networks Efficiently

    OpenAIRE

    Collobert, Ronan; Kavukcuoglu, Koray; Farabet, Clément; Montavon, Grégoire; Orr, Geneviève; Müller, K.-R.

    2012-01-01

    Neural networks and machine learning algorithms in general require a flexible environment where new algorithm prototypes and experiments can be set up as quickly as possible with best possible computational performance. To that end, we provide a new framework called Torch7, that is especially suited to achieve both of these competing goals. Torch7 is a versatile numeric computing framework and machine learning library that extends a very lightweight and powerful programming language Lua. Its ...

  4. 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.

  5. Neural networks for triggering

    International Nuclear Information System (INIS)

    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

  6. Dynamic recurrent neural networks

    OpenAIRE

    Pearlmutter, Barak A

    1990-01-01

    We survey learning algorithms for recurrent neural networks with hidden units and attempt to put the various techniques into a common framework. We discuss fixpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non-fixpoint algorithms, namely backpropagation through time, Elman's history cutoff nets, and Jordan's output feedback architecture. Forward propagation, an online technique that uses adjoint equations, is also discussed. In many cases...

  7. Complementing ODE-Based System Analysis Using Boolean Networks Derived from an Euler-Like Transformation.

    Directory of Open Access Journals (Sweden)

    Claudia Stötzel

    Full Text Available In this paper, we present a systematic transition scheme for a large class of ordinary differential equations (ODEs into Boolean networks. Our transition scheme can be applied to any system of ODEs whose right hand sides can be written as sums and products of monotone functions. It performs an Euler-like step which uses the signs of the right hand sides to obtain the Boolean update functions for every variable of the corresponding discrete model. The discrete model can, on one hand, be considered as another representation of the biological system or, alternatively, it can be used to further the analysis of the original ODE model. Since the generic transformation method does not guarantee any property conservation, a subsequent validation step is required. Depending on the purpose of the model this step can be based on experimental data or ODE simulations and characteristics. Analysis of the resulting Boolean model, both on its own and in comparison with the ODE model, then allows to investigate system properties not accessible in a purely continuous setting. The method is exemplarily applied to a previously published model of the bovine estrous cycle, which leads to new insights regarding the regulation among the components, and also indicates strongly that the system is tailored to generate stable oscillations.

  8. HSP70 mediates survival in apoptotic cells – Boolean network prediction and experimental validation

    Directory of Open Access Journals (Sweden)

    Suhas Vasaikar

    2015-08-01

    Full Text Available Neuronal stress or injury results in the activation of proteins, which regulate the balance between survival and apoptosis. However, the complex mechanism of cell signalling involving cell death and survival, activated in response to cellular stress is not yet completely understood. To bring more clarity about these mechanisms, a Boolean network was constructed that represented the apoptotic pathway in neuronal cells. FasL and neurotrophic growth factor (NGF were considered as inputs in the absence and presence of heat shock proteins known to shift the balance towards survival by rescuing pro-apoptotic cells. The probabilities of survival, DNA repair and apoptosis as cellular fates, in the presence of either the growth factor or FasL, revealed a survival bias encoded in the network. Boolean predictions tested by measuring the mRNA expression level of caspase-3, caspase-8 and BAX in neuronal Neuro2a (N2a cell line with NGF and FasL as external input, showed positive correlation with the observed experimental results for survival and apoptotic states. It was observed that HSP70 contributed more towards rescuing cells from apoptosis in comparison to HSP27, HSP40 and HSP90. Overexpression of HSP70 in N2a transfected cells showed reversal of cellular fate from FasL-induced apoptosis to survival. Further, the pro-survival role of the proteins BCL2, IAP, cFLIP and NFκB determined by vertex perturbation analysis was experimentally validated through protein inhibition experiments using EM20-25, Embelin and Wedelolactone, which resulted in 1.27-fold, 1.26-fold and 1.46-fold increase in apoptosis of N2a cells. The existence of a one-to-one correspondence between cellular fates and attractor states shows that Boolean networks may be employed with confidence in qualitative analytical studies of biological networks.

  9. The behavior of noise-resilient Boolean networks with diverse topologies

    International Nuclear Information System (INIS)

    The dynamics of noise-resilient Boolean networks with majority functions and diverse topologies is investigated. A wide class of possible topological configurations is parametrized as a stochastic blockmodel. For this class of networks, the dynamics always undergoes a phase transition from a non-ergodic regime, where a memory of its past states is preserved, to an ergodic regime, where no such memory exists and every microstate is equally probable. Both the average error on the network and the critical value of noise where the transition occurs are investigated analytically, and compared to numerical simulations. The results for 'partially dense' networks, comprising relatively few, but dynamically important nodes, which have a number of inputs that greatly exceeds the average for the entire network, give very general upper bounds on the maximum resilience against noise attainable on globally sparse systems

  10. Critical line in undirected Kauffman Boolean networks - the role of percolation

    International Nuclear Information System (INIS)

    We show that to describe correctly the position of the critical line in Kauffman random Boolean networks one must take into account percolation phenomena underlying the process of damage spreading. For this reason, since the issue of percolation transition is much simpler in random undirected networks than in the directed ones, we study the Kauffman model in undirected networks. We derive the mean field formula for the critical line in the giant components of these networks, and show that the critical line characterizing the whole network results from the fact that the ordered behavior of small clusters shields the chaotic behavior of the giant component. We also show a possible attitude towards the analytical description of the shielding effect. The theoretical derivations given in this paper very much tally with the numerical simulations done for classical random graphs

  11. Variances as order parameter and complexity measure for random Boolean networks

    Energy Technology Data Exchange (ETDEWEB)

    Luque, Bartolo [Departamento de Matematica Aplicada y EstadIstica, Escuela Superior de Ingenieros Aeronauticos, Universidad Politecnica de Madrid, Plaza Cardenal Cisneros 3, Madrid 28040 (Spain); Ballesteros, Fernando J [Observatori Astronomic, Universitat de Valencia, Ed. Instituts d' Investigacio, Pol. La Coma s/n, E-46980 Paterna, Valencia (Spain); Fernandez, Manuel [Departamento de Matematica Aplicada y EstadIstica, Escuela Superior de Ingenieros Aeronauticos, Universidad Politecnica de Madrid, Plaza Cardenal Cisneros 3, Madrid 28040 (Spain)

    2005-02-04

    Several order parameters have been considered to predict and characterize the transition between ordered and disordered phases in random Boolean networks, such as the Hamming distance between replicas or the stable core, which have been successfully used. In this work, we propose a natural and clear new order parameter: the temporal variance. We compute its value analytically and compare it with the results of numerical experiments. Finally, we propose a complexity measure based on the compromise between temporal and spatial variances. This new order parameter and its related complexity measure can be easily applied to other complex systems.

  12. The receptor mosaic hypothesis of the engram: possible relevance of Boolean network modeling.

    Science.gov (United States)

    Zoli, M; Guidolin, D; Fuxe, K; Agnati, L F

    1996-09-01

    In the past 15 years, several lines of evidence have shown that receptors for chemical signals can interact in domains of the plasma membrane and possibly form molecular circuits encoding logical operators. In this frame, the receptor mosaic hypothesis of the engram was advanced. According to this proposal, aggregates of different receptor species (mosaics) may form in neuronal membranes (typically synapses) and constitute a memory trace (engram) of its activity. In the present paper, we present an attempt to model the functioning of aggregates of interacting receptors in membrane domains by means of random Boolean networks. PMID:8968825

  13. Damage spreading in spatial and small-world random Boolean networks

    Science.gov (United States)

    Lu, Qiming; Teuscher, Christof

    2014-02-01

    The study of the response of complex dynamical social, biological, or technological networks to external perturbations has numerous applications. Random Boolean networks (RBNs) are commonly used as a simple generic model for certain dynamics of complex systems. Traditionally, RBNs are interconnected randomly and without considering any spatial extension and arrangement of the links and nodes. However, most real-world networks are spatially extended and arranged with regular, power-law, small-world, or other nonrandom connections. Here we explore the RBN network topology between extreme local connections, random small-world, and pure random networks, and study the damage spreading with small perturbations. We find that spatially local connections change the scaling of the Hamming distance at very low connectivities (K¯≪1) and that the critical connectivity of stability Ks changes compared to random networks. At higher K¯, this scaling remains unchanged. We also show that the Hamming distance of spatially local networks scales with a power law as the system size N increases, but with a different exponent for local and small-world networks. The scaling arguments for small-world networks are obtained with respect to the system sizes and strength of spatially local connections. We further investigate the wiring cost of the networks. From an engineering perspective, our new findings provide the key design trade-offs between damage spreading (robustness), the network's wiring cost, and the network's communication characteristics.

  14. 高阶布尔网络的结构%Structure of higher order Boolean networks*

    Institute of Scientific and Technical Information of China (English)

    李志强; 赵寅; 程代展

    2011-01-01

    The higher order Boolean (control) network is introduced and its topological structure is studied.Using semi-tensor product of matrices,its dynamics is converted into two algebraic forms,which are standard discrete-time dynamic systems.The one-to-one correspondence of the network dynamics and its first algebraic form is proved,and certain topological structures,including fixed points,cycles,and transient time,of higher order Boolean (control) networks are revealed.The relationship between the original system and its second algebraic form is also studied.%介绍高阶布尔(控制)网络,并研究了其拓扑结构.以矩阵的半张量积作为工具,把高阶布尔网络的动态过程转化为2种标准离散事件动态系统的代数形式.证明了高阶布尔网络和第1代数形式的一一对应关系,并由此得到其拓扑结构(不动点、极限圈以及暂态期等).还研究了高阶布尔网络系统与它第2代数形式的关系.

  15. 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

  16. Damage Spreading in Spatial and Small-world Random Boolean Networks

    Energy Technology Data Exchange (ETDEWEB)

    Lu, Qiming [Fermilab; Teuscher, Christof [Portland State U.

    2014-02-18

    The study of the response of complex dynamical social, biological, or technological networks to external perturbations has numerous applications. Random Boolean Networks (RBNs) are commonly used a simple generic model for certain dynamics of complex systems. Traditionally, RBNs are interconnected randomly and without considering any spatial extension and arrangement of the links and nodes. However, most real-world networks are spatially extended and arranged with regular, power-law, small-world, or other non-random connections. Here we explore the RBN network topology between extreme local connections, random small-world, and pure random networks, and study the damage spreading with small perturbations. We find that spatially local connections change the scaling of the relevant component at very low connectivities ($\\bar{K} \\ll 1$) and that the critical connectivity of stability $K_s$ changes compared to random networks. At higher $\\bar{K}$, this scaling remains unchanged. We also show that the relevant component of spatially local networks scales with a power-law as the system size N increases, but with a different exponent for local and small-world networks. The scaling behaviors are obtained by finite-size scaling. We further investigate the wiring cost of the networks. From an engineering perspective, our new findings provide the key design trade-offs between damage spreading (robustness), the network's wiring cost, and the network's communication characteristics.

  17. Neural logic networks a new class of neural networks

    CERN Document Server

    Heng, Teh Hoon

    1995-01-01

    This book is the first of a series of technical reports of a key research project of the Real-World Computing Program supported by the MITI of Japan.The main goal of the project is to model human intelligence by a special class of mathematical systems called neural logic networks.The book consists of three parts. Part 1 describes the general theory of neural logic networks and their potential applications. Part 2 discusses a new logic called Neural Logic which attempts to emulate more closely the logical thinking process of human. Part 3 studies the special features of neural logic networks wh

  18. Interacting neural networks.

    Science.gov (United States)

    Metzler, R; Kinzel, W; Kanter, I

    2000-08-01

    Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random. PMID:11088736

  19. Iterative Radial Basis Functions Neural Networks as Metamodels of Stochastic Simulations of the Quality of Search Engines in the World Wide Web.

    Science.gov (United States)

    Meghabghab, George

    2001-01-01

    Discusses the evaluation of search engines and uses neural networks in stochastic simulation of the number of rejected Web pages per search query. Topics include the iterative radial basis functions (RBF) neural network; precision; response time; coverage; Boolean logic; regression models; crawling algorithms; and implications for search engine…

  20. 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...

  1. Modeling and controlling the two-phase dynamics of the p53 network: a Boolean network approach

    International Nuclear Information System (INIS)

    Although much empirical evidence has demonstrated that p53 plays a key role in tumor suppression, the dynamics and function of the regulatory network centered on p53 have not yet been fully understood. Here, we develop a Boolean network model to reproduce the two-phase dynamics of the p53 network in response to DNA damage. In particular, we map the fates of cells into two types of Boolean attractors, and we find that the apoptosis attractor does not exist for minor DNA damage, reflecting that the cell is reparable. As the amount of DNA damage increases, the basin of the repair attractor shrinks, accompanied by the rising of the apoptosis attractor and the expansion of its basin, indicating that the cell becomes more irreparable with more DNA damage. For severe DNA damage, the repair attractor vanishes, and the apoptosis attractor dominates the state space, accounting for the exclusive fate of death. Based on the Boolean network model, we explore the significance of links, in terms of the sensitivity of the two-phase dynamics, to perturbing the weights of links and removing them. We find that the links are either critical or ordinary, rather than redundant. This implies that the p53 network is irreducible, but tolerant of small mutations at some ordinary links, and this can be interpreted with evolutionary theory. We further devised practical control schemes for steering the system into the apoptosis attractor in the presence of DNA damage by pinning the state of a single node or perturbing the weight of a single link. Our approach offers insights into understanding and controlling the p53 network, which is of paramount importance for medical treatment and genetic engineering. (paper)

  2. Modeling and controlling the two-phase dynamics of the p53 network: a Boolean network approach

    Science.gov (United States)

    Lin, Guo-Qiang; Ao, Bin; Chen, Jia-Wei; Wang, Wen-Xu; Di, Zeng-Ru

    2014-12-01

    Although much empirical evidence has demonstrated that p53 plays a key role in tumor suppression, the dynamics and function of the regulatory network centered on p53 have not yet been fully understood. Here, we develop a Boolean network model to reproduce the two-phase dynamics of the p53 network in response to DNA damage. In particular, we map the fates of cells into two types of Boolean attractors, and we find that the apoptosis attractor does not exist for minor DNA damage, reflecting that the cell is reparable. As the amount of DNA damage increases, the basin of the repair attractor shrinks, accompanied by the rising of the apoptosis attractor and the expansion of its basin, indicating that the cell becomes more irreparable with more DNA damage. For severe DNA damage, the repair attractor vanishes, and the apoptosis attractor dominates the state space, accounting for the exclusive fate of death. Based on the Boolean network model, we explore the significance of links, in terms of the sensitivity of the two-phase dynamics, to perturbing the weights of links and removing them. We find that the links are either critical or ordinary, rather than redundant. This implies that the p53 network is irreducible, but tolerant of small mutations at some ordinary links, and this can be interpreted with evolutionary theory. We further devised practical control schemes for steering the system into the apoptosis attractor in the presence of DNA damage by pinning the state of a single node or perturbing the weight of a single link. Our approach offers insights into understanding and controlling the p53 network, which is of paramount importance for medical treatment and genetic engineering.

  3. Neural network applications in telecommunications

    Science.gov (United States)

    Alspector, Joshua

    1994-01-01

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

  4. Neural networks at the Tevatron

    International Nuclear Information System (INIS)

    This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF

  5. 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....

  6. Neural Networks for the Beginner.

    Science.gov (United States)

    Snyder, Robin M.

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

  7. Artificial neural networks in NDT

    International Nuclear Information System (INIS)

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

  8. Trends in neural network technology. Neural network gijutsu no doko

    Energy Technology Data Exchange (ETDEWEB)

    Nishimura, K. (Toshiba Corp., Tokyo (Japan))

    1991-12-01

    The present and future of neural network technologies were reviewed. Neural networks simulate the neurons and synapses of human brain, thus permitting the utilization of heuristic knowledge difficult to describe in a logical manner. Such networks can therefore solve optimization problems, difficult to solve by conventional computers, more rapidly while sacrificing a permissible degree of rigor. In light of these advantages, many attempts have been made to apply neural networks to a variety of engineering fields including character recognition, phonetic recognition diagnosis, operation and so on. Now that these attempts have demonstrated the great potential of neural network technology, its application to practical problems will receive increasing attention. The necessity for fundamental studies on learning algorithms, modularization techniques, hardware technologies and so on will grow in conjunction with the above trends in application. 20 refs., 11 figs., 1 tab.

  9. 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...

  10. Bars Problem Solving - New Neural Network Method and Comparison

    Czech Academy of Sciences Publication Activity Database

    Snášel, V.; Húsek, Dušan; Frolov, A.; Řezanková, H.; Moravec, P.; Polyakov, P.Y.

    Berlin : Springer, 2007 - (Gelbukh, A.; Morales, A.), s. 671-682 ISBN 978-3-540-76630-8. - (Lecture Notes in Artificial Intelligence. 4827). [MICAI 2007. Mexican International Conference on Artificial Intelligence /6./. Aguascalientes (MX), 04.11.2007-10.11.2007] R&D Projects: GA MŠk(CZ) 1M0567; GA AV ČR 1ET100300414; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * neural networks * dimension reduction * cluster analysis Subject RIV: IN - Informatics, Computer Science

  11. Medical diagnosis using neural network

    CERN Document Server

    Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque

    2010-01-01

    This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...

  12. Principles of artificial neural networks

    CERN Document Server

    Graupe, Daniel

    2013-01-01

    Artificial neural networks are most suitable for solving problems that are complex, ill-defined, highly nonlinear, of many and different variables, and/or stochastic. Such problems are abundant in medicine, in finance, in security and beyond. This volume covers the basic theory and architecture of the major artificial neural networks. Uniquely, it presents 18 complete case studies of applications of neural networks in various fields, ranging from cell-shape classification to micro-trading in finance and to constellation recognition - all with their respective source codes. These case studies

  13. Modular, Hierarchical Learning By Artificial Neural Networks

    Science.gov (United States)

    Baldi, Pierre F.; Toomarian, Nikzad

    1996-01-01

    Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

  14. 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...

  15. Neural Networks Of VLSI Components

    Science.gov (United States)

    Eberhardt, Silvio P.

    1991-01-01

    Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.

  16. Neural Networks for Fingerprint Recognition

    OpenAIRE

    Baldi, Pierre; Chauvin, Yves

    1993-01-01

    After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to...

  17. Neural Networks and Photometric Redshifts

    OpenAIRE

    Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo

    2002-01-01

    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy...

  18. 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...

  19. Correlational Neural Networks.

    Science.gov (United States)

    Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman

    2016-02-01

    Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210

  20. Neural networks: genuine artifical intelligence. Neurale netwerken: echte kunstmatige intelligentie

    Energy Technology Data Exchange (ETDEWEB)

    Jongepier, A.G. (KEMA NV, Arnhem (Netherlands))

    Artificial neural networks are a new form of artificial intelligence. At this moment KEMA NV is examining the possibilities of applying artificial neural networks to processes that are related to power systems. A number of applications already gives hopeful results. Artificial neural networks are suited to pattern recognition. If a problem can be formulated in terms of pattern recognition, an artificial neural network may give a valuable contribution to the solution of this problem. 8 figs., 15 refs.

  1. 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...

  2. Phase Transitions of Neural Networks

    OpenAIRE

    Kinzel, Wolfgang

    1997-01-01

    The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.

  3. COCOMO Estimates Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Anupama Kaushik

    2012-08-01

    Full Text Available Software cost estimation is an important phase in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most critical tasks and an accurate estimate provides a strong base to the development procedure. In this paper, the most widely used software cost estimation model, the Constructive Cost Model (COCOMO is discussed. The model is implemented with the help of artificial neural networks and trained using the perceptron learning algorithm. The COCOMO dataset is used to train and to test the network. The test results from the trained neural network are compared with that of the COCOMO model. The aim of our research is to enhance the estimation accuracy of the COCOMO model by introducing the artificial neural networks to it.

  4. Neural Networks and Database Systems

    CERN Document Server

    Schikuta, Erich

    2008-01-01

    Object-oriented database systems proved very valuable at handling and administrating complex objects. In the following guidelines for embedding neural networks into such systems are presented. It is our goal to treat networks as normal data in the database system. From the logical point of view, a neural network is a complex data value and can be stored as a normal data object. It is generally accepted that rule-based reasoning will play an important role in future database applications. The knowledge base consists of facts and rules, which are both stored and handled by the underlying database system. Neural networks can be seen as representation of intensional knowledge of intelligent database systems. So they are part of a rule based knowledge pool and can be used like conventional rules. The user has a unified view about his knowledge base regardless of the origin of the unique rules.

  5. Boolean decision problems with competing interactions on scale-free networks: equilibrium and nonequilibrium behavior in an external bias.

    Science.gov (United States)

    Zhu, Zheng; Andresen, Juan Carlos; Moore, M A; Katzgraber, Helmut G

    2014-02-01

    We study the equilibrium and nonequilibrium properties of Boolean decision problems with competing interactions on scale-free networks in an external bias (magnetic field). Previous studies at zero field have shown a remarkable equilibrium stability of Boolean variables (Ising spins) with competing interactions (spin glasses) on scale-free networks. When the exponent that describes the power-law decay of the connectivity of the network is strictly larger than 3, the system undergoes a spin-glass transition. However, when the exponent is equal to or less than 3, the glass phase is stable for all temperatures. First, we perform finite-temperature Monte Carlo simulations in a field to test the robustness of the spin-glass phase and show that the system has a spin-glass phase in a field, i.e., exhibits a de Almeida-Thouless line. Furthermore, we study avalanche distributions when the system is driven by a field at zero temperature to test if the system displays self-organized criticality. Numerical results suggest that avalanches (damage) can spread across the whole system with nonzero probability when the decay exponent of the interaction degree is less than or equal to 2, i.e., that Boolean decision problems on scale-free networks with competing interactions can be fragile when not in thermal equilibrium. PMID:25353433

  6. Detecting a Singleton Attractor in a Boolean Network Utilizing SAT Algorithms

    Science.gov (United States)

    Tamura, Takeyuki; Akutsu, Tatsuya

    The Boolean network (BN) is a mathematical model of genetic networks. It is known that detecting a singleton attractor, which is also called a fixed point, is NP-hard even for AND/OR BNs (i.e., BNs consisting of AND/OR nodes), where singleton attractors correspond to steady states. Though a naive algorithm can detect a singleton attractor for an AND/OR BN in O(n 2n) time, no O((2-ε)n) (ε > 0) time algorithm was known even for an AND/OR BN with non-restricted indegree, where n is the number of nodes in a BN. In this paper, we present an O(1.787n) time algorithm for detecting a singleton attractor of a given AND/OR BN, along with related results. We also show that detection of a singleton attractor in a BN with maximum indegree two is NP-hard and can be polynomially reduced to a satisfiability problem.

  7. Automatic Generation of Neural Networks

    OpenAIRE

    A. Fiszelew; P. Britos; G. Perichisky; R. García-Martínez

    2003-01-01

    This work deals with methods for finding optimal neural network architectures to learn particular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a performance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employ...

  8. On Kolmogorov's superpositions and Boolean functions

    Energy Technology Data Exchange (ETDEWEB)

    Beiu, V.

    1998-12-31

    The paper overviews results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on an explicit numerical (i.e., constructive) algorithm for Kolmogorov's superpositions they will show that for obtaining minimum size neutral networks for implementing any Boolean function, the activation function of the neurons is the identity function. Because classical AND-OR implementations, as well as threshold gate implementations require exponential size (in the worst case), it will follow that size-optimal solutions for implementing arbitrary Boolean functions require analog circuitry. Conclusions and several comments on the required precision are ending the paper.

  9. Extraction of Rules from Data using Piecewise-Linear Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Holeňa, Martin

    Istanbul : ITU Management Science Fakulty, 2002, s. 1-8. ISBN 975-97963-0-9. [FSSCTIMIE'02. Istanbul (TR), 29.05.2002-31.05.2002] R&D Projects: GA AV ČR IAB2030007 Institutional research plan: AV0Z1030915 Keywords : knowledge extraction with artificial neural networks * Boolean rules * fuzzy rules * multilayer perceptron * piecewise-linear activation function * polyhedra and pseudopolyhedra * Lukasiewicz predicate calculus * rational McNaughton function Subject RIV: BA - General Mathematics

  10. New BFA Method Based on Attractor Neural Network and Likelihood Maximization

    Czech Academy of Sciences Publication Activity Database

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

    2014-01-01

    Roč. 132, 20 May (2014), s. 14-29. ISSN 0925-2312 Grant ostatní: GA MŠk(CZ) ED1.1.00/02.0070; GA MŠk(CZ) EE.2.3.20.0073 Institutional support: RVO:67985807 Keywords : recurrent neural network * associative memory * Hebbian learning rule * neural network application * data mining * statistics * Boolean factor analysis * information gain * dimension reduction * likelihood-maximization * bars problem Subject RIV: IN - Informatics, Computer Science Impact factor: 2.083, year: 2014

  11. Video Compression Using Neural Network

    Directory of Open Access Journals (Sweden)

    Sangeeta Mishra

    2012-08-01

    Full Text Available Apart from the existing technology on image compression represented by series of JPEG, MPEG and H.26x standards, new technology such as neural networks and genetic algorithms are being developed to explore the future of image coding. Successful applications of neural networks to basic propagation algorithm have now become well established and other aspects of neural network involvement in this technology. In this paper different algorithms were implemented like gradient descent back propagation, gradient descent with momentum back propagation, gradient descent with adaptive learning back propagation, gradient descent with momentum and adaptive learning back propagation and Levenberg-Marquardt algorithm. The size of original video clip is 25MB and after compression it becomes 21.3MB giving the compression ratio as 85.2% and compression factor of 1.174. It was observed that the size remains same after compression but the difference is in the clarity.

  12. Neural networks in signal processing

    International Nuclear Information System (INIS)

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

  13. Computational complexity of Boolean functions

    International Nuclear Information System (INIS)

    Boolean functions are among the fundamental objects of discrete mathematics, especially in those of its subdisciplines which fall under mathematical logic and mathematical cybernetics. The language of Boolean functions is convenient for describing the operation of many discrete systems such as contact networks, Boolean circuits, branching programs, and some others. An important parameter of discrete systems of this kind is their complexity. This characteristic has been actively investigated starting from Shannon's works. There is a large body of scientific literature presenting many fundamental results. The purpose of this survey is to give an account of the main results over the last sixty years related to the complexity of computation (realization) of Boolean functions by contact networks, Boolean circuits, and Boolean circuits without branching. Bibliography: 165 titles.

  14. Relations Between Wavelet Network and Feedforward Neural Network

    Institute of Scientific and Technical Information of China (English)

    刘志刚; 何正友; 钱清泉

    2002-01-01

    A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.

  15. Application of neural networks in coastal engineering

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    the neural network attractive. A neural network is an information processing system modeled on the structure of the dynamic process. It can solve the complex/nonlinear problems quickly once trained by operating on problems using an interconnected number...

  16. 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.

  17. Ocean wave forecasting using recurrent neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Prabaharan, N.

    , merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off...

  18. Neural network exploitation in reliability assurance

    International Nuclear Information System (INIS)

    The contribution deals with neural network application for the diagnostic system of the three-phase asynchronous electro motor. The case study is done and can be used as a model for the next application of neural network methodology.

  19. Neural Networks for Flight Control

    Science.gov (United States)

    Jorgensen, Charles C.

    1996-01-01

    Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.

  20. Building a Chaotic Proved Neural Network

    CERN Document Server

    Bahi, Jacques M; Salomon, Michel

    2011-01-01

    Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.

  1. Neural Network Adaptations to Hardware Implementations

    OpenAIRE

    Moerland, Perry,; Fiesler,Emile

    1997-01-01

    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential.However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and ...

  2. Neural Network Adaptations to Hardware Implementations

    OpenAIRE

    Moerland, Perry,; Fiesler,Emile; Beale, R

    1997-01-01

    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential. However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and...

  3. 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.

  4. Deep Gate Recurrent Neural Network

    OpenAIRE

    Gao, Yuan; Glowacka, Dorota

    2016-01-01

    This paper introduces two recurrent neural network structures called Simple Gated Unit (SGU) and Deep Simple Gated Unit (DSGU), which are general structures for learning long term dependencies. Compared to traditional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), both structures require fewer parameters and less computation time in sequence classification tasks. Unlike GRU and LSTM, which require more than one gates to control information flow in the network, SGU and DSGU only...

  5. Network Firewall using Artificial Neural Networks

    OpenAIRE

    Kristián Valentín; Michal Malý

    2014-01-01

    Today's most common firewalls are mostly rule-based. Their knowledge consists of a set of rules upon which they process received packets. They cannot do anything they have not been explicitly configured to do. This makes the system more straightforward to set up, but less flexible and less adaptive to changing circumstances. We will investigate a network firewall whose rule-base we will try to model using an artificial neural network, more specifically using a multi-layer perceptron (MLP) tra...

  6. Artificial neural networks in medicine

    Energy Technology Data Exchange (ETDEWEB)

    Keller, P.E.

    1994-07-01

    This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.

  7. Medical Imaging with Neural Networks

    International Nuclear Information System (INIS)

    The objective of this paper is to provide an overview of the recent developments in the use of artificial neural networks in medical imaging. The areas of medical imaging that are covered include : ultrasound, magnetic resonance, nuclear medicine and radiological (including computerized tomography). (authors)

  8. 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 of the...

  9. Model Of Neural Network With Creative Dynamics

    Science.gov (United States)

    Zak, Michail; Barhen, Jacob

    1993-01-01

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

  10. 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 a...

  11. FUZZY NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Vikas Kumar

    2012-09-01

    Full Text Available This paper comparator networks - a well-known modelof parallel computation. This model is used extensivelyfor keys arrangement tasks such as sorting and selection.This work investigates several aspects of comparatornetworks. It starts with presenting handy tools foranalysis of comparator networks in the form ofconclusive sets - non-binary vectors that verify a specificfunctionality. The 0-1 principle introduced by Knuthstates that a comparator network is a sorting network ifand only if it sorts all binary inputs. Hence, it points out acertain binary conclusive set. We compare these twomodels by considering several 0-1 -like principles andshow that the min-max model is the ‘strongest’ model ofcomputation which obeys our principles. That is, if afunction is computable in a model of computation inwhich any of these principles holds, a min-max networkcan compute this function.

  12. Neural Networks and Photometric Redshifts

    CERN Document Server

    Tagliaferri, R; Andreon, S; Capozziello, S; Donalek, C; Giordano, G; Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo

    2002-01-01

    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy of the results, turned out to be the most effective. In the best experiment, the implemented network reached an accuracy of 0.020 (interquartile error) in the range 0

  13. Neural Network Model For Fast Learning And Retrieval

    Science.gov (United States)

    Arsenault, Henri H.; Macukow, Bohdan

    1989-05-01

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

  14. 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.

  15. Parameter Learning of Boolean Bayesian Networks%布尔型贝叶斯网络参数学习

    Institute of Scientific and Technical Information of China (English)

    吴永广; 周兴旺

    2015-01-01

    布尔型贝叶斯网络是一类由布尔型变量组成的网络,它能够以线性多变量函数描述,使计算和处理上灵活高效。通过运用连接树算法对络进行分块化处理的方法,可以提高算法的效率,然后以传统的最大似然估计方法对布尔型网络的参数进行学习。服从同一分布律的贝叶斯网络参数学习算法发展比较成熟,这类以狄利克雷或者高斯分布为基础的算法在应用领域中难以发挥其应有的价值。相比之下,基于布尔型贝叶斯网络下的参数学习更贴近于应用,在人工智能和数据挖掘等领域有很好的发展前景。%Boolean Bayesian network is a class of Bayesian networks which are made up of Boolean varia-bles. The method to describe the network with a multi-linear function is flexible and efficient to compute and process variables. By introducing Junction Tree algorithm,the network can be divided into blocks which can make it easy to calculate. Then the traditional maximum likelihood estimation method was used for learning Boolean networks. Parameter learning algorithm following the same distribution is more ma-ture,but this kind of algorithm based on Dirichlet or Gaussian distribution is difficult to play its proper val-ue in practice. In contrast,parameter learning based on Boolean networks gets close to applications. It has good prospects for development in areas such as artificial intelligence and data mining.

  16. Photon spectrometry utilizing neural networks

    International Nuclear Information System (INIS)

    Having in mind the time spent on the uneventful work of characterization of the radiation beams used in a ionizing radiation metrology laboratory, the Metrology Service of the Centro Regional de Ciencias Nucleares do Nordeste - CRCN-NE verified the applicability of artificial intelligence (artificial neural networks) to perform the spectrometry in photon fields. For this, was developed a multilayer neural network, as an application for the classification of patterns in energy, associated with a thermoluminescent dosimetric system (TLD-700 and TLD-600). A set of dosimeters was initially exposed to various well known medium energies, between 40 keV and 1.2 MeV, coinciding with the beams determined by ISO 4037 standard, for the dose of 10 mSv in the quantity Hp(10), on a chest phantom (ISO slab phantom) with the purpose of generating a set of training data for the neural network. Subsequently, a new set of dosimeters irradiated in unknown energies was presented to the network with the purpose to test the method. The methodology used in this work was suitable for application in the classification of energy beams, having obtained 100% of the classification performed. (authors)

  17. Fuzzy logic systems are equivalent to feedforward neural networks

    Institute of Scientific and Technical Information of China (English)

    2000-01-01

    Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i.e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.

  18. Spiking Neural P Systems and Modularization of Complex Networks from Cortical Neural Network to Social Networks

    OpenAIRE

    Obtulowicz, Adam

    2009-01-01

    An idea of modularization of complex networks (from cortial neural net, Internet computer network, to market and social networks) is explained and some its topic motivations are presented. Then some known modularization algorithms and modular architectures (constructions) of complex networks are discussed in the context of possible applications of spiking neural P systems in order to improve these modularization algorithms and to analyze massively parallel processes in networks of mo...

  19. COMPARING THE IMPACT OF ACCURATE INPUTS ON NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    V.Vaithiyanathan

    2013-06-01

    Full Text Available Artificial neural networks are widely used in medical diagnosis replacing most of the conventional diagnosis methods due to its accuracy and speed. This paper analyses the variation in theaccuracy of diagnosis of type II diabetes using Artificial Neural Networks based on the accuracy of the inputs given to the network. It compares the efficiency of the network based on the input format. Thedata needed for this comparison is collected by interviewing patients who approach the diabetician with various symptoms of the disease. These symptoms can be modeled in 2 different forms. One form justspecifies the presence or absence of the symptom and can be represented using Boolean values. The other form specifies the severity or frequency of occurrence of the symptom. Both these inputs are given to the system and the accuracy of the output is analyzed. This result indicates the impact of the specification of the input on the output. Comparison is done by performing regression analysis on both the outputs. Regression analysis gives the correlation between the output of the system and the target [1]. It makes use of only the most general symptoms of the disease. Further analysis can be done on other diabetes particular symptoms.

  20. 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...

  1. LOAD BALANCING WITH NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    Nada M. Al Sallami

    2013-11-01

    Full Text Available This paper discusses a proposed load balance technique based on artificial neural network. It distributes workload equally across all the nodes by using back propagation learning algorithm to train feed forward Artificial Neural Network (ANN. The proposed technique is simple and it can work efficiently when effective training sets are used. ANN predicts the demand and thus allocates resources according to that demand. Thus, it always maintains the active servers according to current demand, which results in low energy consumption than the conservative approach of over-provisioning. Furthermore, high utilization of server results in more power consumption, server running at higher utilization can process more workload with similar power usage. Finally the existing load balancing techniques in cloud computing are discussed and compared with the proposed technique based on various parameters like performance, scalability, associated overhead... etc. In addition energy consumption and carbon emission perspective are also considered to satisfy green computing.

  2. Color conversion using neural networks

    Science.gov (United States)

    Tominaga, Shoji

    1998-01-01

    Neural network methods are described for color coordinate conversion between color systems. We present solutions for two problems of (1) conversion between two color-specification systems and (2) conversion between a color-specification system and a device coordinate system. First we discuss the color-notation conversion between the Munsell and CIE color systems. The conversion algorithms are developed for both directions of Munsell-to-L*a*b* and L*a*b*-to-Munsell. Second we discuss a neural network method for color reproduction on a printer. The color reproduction problem on the printer using more than four inks is considered as the problem of controlling an unknown system. The practical algorithms are presented for realizing the mapping from the L*a*b* space to the CMYK space. Moreover the method is applied to the color control using CMYK plus light cyan and light magenta.

  3. International joint conference on neural networks

    Energy Technology Data Exchange (ETDEWEB)

    1989-01-01

    This book contains papers on neural networks. Included are the following topics: A self-training visual inspection system with a neural network classifier; A bifurcation theory approach to vector field programming for periodic attractors; and construction of neural nets using the radon transform.

  4. Learning Compact Recurrent Neural Networks

    OpenAIRE

    Lu, Zhiyun; Sindhwani, Vikas; Sainath, Tara N.

    2016-01-01

    Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression ca...

  5. Learning with heterogeneous neural networks

    OpenAIRE

    Belanche Muñoz, Luis Antonio

    2011-01-01

    This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these n...

  6. Process Neural Networks Theory and Applications

    CERN Document Server

    He, Xingui

    2010-01-01

    "Process Neural Networks - Theory and Applications" proposes the concept and model of a process neural network for the first time, showing how it expands the mapping relationship between the input and output of traditional neural networks, and enhancing the expression capability for practical problems, with broad applicability to solving problems relating to process in practice. Some theoretical problems such as continuity, functional approximation capability, and computing capability, are strictly proved. The application methods, network construction principles, and optimization alg

  7. using artificial neural network

    Directory of Open Access Journals (Sweden)

    Rafael do Espírito Santo

    2007-01-01

    Full Text Available In this work, a Multilayer Perceptron implementation – MLP using functional Magnetic Resonance Imaging (fMRI is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for training the MLP network in a leave-one-out manner in order to predict the paradigm that a subject performed by using other images, so far unseen by the MLP network. The aim in this paper is the exploring of the influence of the number of the Principal Component (PC on the performance of the MLP in classifying fMRI paradigms. The classifier´s performance was evaluated in terms of the Sensitivity and Specificity, Prediction Accuracy and the area Az under the receiver operating characteristics (ROC curve. From the ROC analysis, values of Az up to 1 were obtained with 60 PCs in discriminating the visual paradigm from the auditory paradigm.

  8. 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.

  9. Constant fan-in digital neural networks are VLSI-optimal

    Energy Technology Data Exchange (ETDEWEB)

    Beiu, V.

    1995-12-31

    The paper presents a theoretical proof revealing an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures (e.g. neural networks). We are in fact able to prove that efficient digital VLSI implementations (known as VLSI-optimal when minimizing the AT{sup 2} complexity measure - A being the area of the chip, and T the delay for propagating the inputs to the outputs) of neural networks are achieved for small-constant fan-in gates. This result builds on quite recent ones dealing with a very close estimate of the area of neural networks when implemented by threshold gates, but it is also valid for classical Boolean gates. Limitations and open questions are presented in the conclusions.

  10. 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

  11. 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.

  12. 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.

  13. Neural-Network Computer Transforms Coordinates

    Science.gov (United States)

    Josin, Gary M.

    1990-01-01

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

  14. Dynamic Analysis of Structures Using Neural Networks

    Directory of Open Access Journals (Sweden)

    N. Ahmadi

    2008-01-01

    Full Text Available In the recent years, neural networks are considered as the best candidate for fast approximation with arbitrary accuracy in the time consuming problems. Dynamic analysis of structures against earthquake has the time consuming process. We employed two kinds of neural networks: Generalized Regression neural network (GR and Back-Propagation Wavenet neural network (BPW, for approximating of dynamic time history response of frame structures. GR is a traditional radial basis function neural network while BPW categorized as a wavelet neural network. In BPW, sigmoid activation functions of hidden layer neurons are substituted with wavelets and weights training are achieved using Scaled Conjugate Gradient (SCG algorithm. Comparison the results of BPW with those of GR in the dynamic analysis of eight story steel frame indicates that accuracy of the properly trained BPW was better than that of GR and therefore, BPW can be efficiently used for approximate dynamic analysis of structures.

  15. Information Theory for Analyzing Neural Networks

    OpenAIRE

    Sørngård, Bård

    2014-01-01

    The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The classification problem was solved with a feedforward neural network trained with backpropagation, the controller problem was solved with a continuous-time recurrent neural network optimized with evolution.Results from the classification problem shows that mutual information ...

  16. Fast Algorithms for Convolutional Neural Networks

    OpenAIRE

    Lavin, Andrew; Gray, Scott

    2015-01-01

    Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We ...

  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. Modelling Microwave Devices Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Andrius Katkevičius

    2012-04-01

    Full Text Available Artificial neural networks (ANN have recently gained attention as fast and flexible equipment for modelling and designing microwave devices. The paper reviews the opportunities to use them for undertaking the tasks on the analysis and synthesis. The article focuses on what tasks might be solved using neural networks, what challenges might rise when using artificial neural networks for carrying out tasks on microwave devices and discusses problem-solving techniques for microwave devices with intermittent characteristics.Article in Lithuanian

  19. Adaptive Control Based On Neural Network

    OpenAIRE

    Wei, Sun; Lujin, Zhang; Jinhai, Zou; Siyi, Miao

    2009-01-01

    In this paper, the adaptive control based on neural network is studied. Firstly, a neural network based adaptive robust tracking control design is proposed for robotic systems under the existence of uncertainties. In this proposed control strategy, the NN is used to identify the modeling uncertainties, and then the disadvantageous effects caused by neural network approximating error and external disturbances in robotic system are counteracted by robust controller. Especially the proposed cont...

  20. Sequential optimizing investing strategy with neural networks

    OpenAIRE

    Ryo Adachi; Akimichi Takemura

    2010-01-01

    In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a neural network with the best performance until the previous round (trading day) for deciding the investment in the current round. We compare performance of our proposed strategy with various strategies including a strategy based on supervised neural network models and show that our procedure is co...

  1. Boolean implication networks derived from large scale, whole genome microarray datasets

    OpenAIRE

    Sahoo, Debashis; Dill, David L.; Gentles, Andrew J.; Tibshirani, Robert; Plevritis, Sylvia K.

    2008-01-01

    We describe a method for extracting Boolean implications (if-then relationships) in very large amounts of gene expression microarray data. A meta-analysis of data from thousands of microarrays for humans, mice, and fruit flies finds millions of implication relationships between genes that would be missed by other methods. These relationships capture gender differences, tissue differences, development, and differentiation. New relationships are discovered that are preserved across all three sp...

  2. Artificial neural networks in nuclear medicine

    International Nuclear Information System (INIS)

    An analysis of the accessible literature on the diagnostic applicability of artificial neural networks in coronary artery disease and pulmonary embolism appears to be comparative to the diagnosis of experienced doctors dealing with nuclear medicine. Differences in the employed models of artificial neural networks indicate a constant search for the most optimal parameters, which could guarantee the ultimate accuracy in neural network activity. The diagnostic potential within systems containing artificial neural networks proves this calculation tool to be an independent or/and an additional device for supporting a doctor's diagnosis of artery disease and pulmonary embolism. (author)

  3. 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

  4. 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.

  5. Chess Endgames and Neural Networks

    OpenAIRE

    Haworth, Guy McCrossan; Velliste, Meel

    1998-01-01

    The existence of endgame databases challenges us to extract higher-grade information and knowledge from their basic data content. Chess players, for example, would like simple and usable endgame theories if such holy grail exists: endgame experts would like to provide such insights and be inspired by computers to do so. Here, we investigate the use of artificial neural networks (NNs) to mine these databases and we report on a first use of NNs on KPK. The results encourage us to suggest furthe...

  6. Neural Network based Consumption Forecasting

    DEFF Research Database (Denmark)

    Madsen, Per Printz

    2016-01-01

    active participation in the future smart grid environment. One of the main obstacles for making optimal energy consumption is to have good predictions of the future energy consumption. This study is based on real consumption data from eight houses in Denmark. There are designed two different prediction...... models. It is shown that both of the predictions model produce a better consumption prediction then a naïve model. Seen in this perspective is it concluded that it is possible to use Artificial Neural Networks for predicting the energy consumption in ordinary family houses....

  7. Artificial Neural Networks An Introduction

    CERN Document Server

    Priddy, Kevin L

    2005-01-01

    This tutorial text provides the reader with an understanding of artificial neural networks (ANNs) and their application, beginning with the biological systems which inspired them, through the learning methods that have been developed and the data collection processes, to the many ways ANNs are being used today. The material is presented with a minimum of math (although the mathematical details are included in the appendices for interested readers), and with a maximum of hands-on experience. All specialized terms are included in a glossary. The result is a highly readable text that will teach t

  8. Comparison of Seven Methods for Boolean Factor Analysis and Their Evaluation by Information Gain

    Czech Academy of Sciences Publication Activity Database

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

    2016-01-01

    Roč. 27, č. 3 (2016), s. 538-550. ISSN 2162-237X R&D Projects: GA MŠk ED1.1.00/02.0070 Institutional support: RVO:67985807 Keywords : associative memory * bars problem (BP) * Boolean factor analysis (BFA) * data mining * dimension reduction * Hebbian learning rule * information gain * likelihood maximization (LM) * neural network application * recurrent neural network * statistics Subject RIV: IN - Informatics, Computer Science Impact factor: 4.291, year: 2014

  9. 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.

  10. Neural Network Controlled Visual Saccades

    Science.gov (United States)

    Johnson, Jeffrey D.; Grogan, Timothy A.

    1989-03-01

    The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.

  11. Video Traffic Prediction Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Miloš Oravec

    2008-10-01

    Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].

  12. Neural Networks for Emotion Classification

    CERN Document Server

    Sun, Yafei

    2011-01-01

    It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. This thesis describes a neural network-based approach for emotion classification. We learn a classifier that can recognize six basic emotions with an average accuracy of 77% over the Cohn-Kanade database. The novelty of this work is that instead of empirically selecting the parameters of the neural network, i.e. the learning rate, activation function parameter, momentum number, the number of nodes in one layer, etc. we developed a strategy that can automatically select comparatively better combination of these parameters. We also introduce another way to perform back propagation. Instead of using the partial differential of the error function, we use optimal algorithm; namely Powell's direction set to minimize the error function. We were also interested in construction an authentic emotion databases. This...

  13. The Laplacian spectrum of neural networks

    Directory of Open Access Journals (Sweden)

    Siemon ede Lange

    2014-01-01

    Full Text Available 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.

  14. Expectation-Maximization Approach to Boolean Factor Analysis

    Czech Academy of Sciences Publication Activity Database

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

    Piscataway: IEEE, 2011, s. 559-566. ISBN 978-1-4244-9636-5. [IJCNN 2011. International Joint Conference on Neural Networks. San Jose (US), 31.07.2011-05.08.2011] R&D Projects: GA ČR GAP202/10/0262; GA ČR GA205/09/1079; GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean factor analysis * bars problem * dendritic inhibition * expectation-maximization * neural network application * statistics Subject RIV: IN - Informatics, Computer Science

  15. 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.

  16. Extrapolation limitations of multilayer feedforward neural networks

    Science.gov (United States)

    Haley, Pamela J.; Soloway, Donald

    1992-01-01

    The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.

  17. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    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

  18. Coherence resonance in bursting neural networks

    Science.gov (United States)

    Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.

    2015-10-01

    Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.

  19. USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS

    OpenAIRE

    Şeker, Murat; E. Selim YILDIRIM; BERKAY, Ahmet

    2004-01-01

    Examples of successful applications in Artificial Intelligence (AI) field; With financial applications, Control, Communication, Processing Radar signals, Pattern Recognition, general DSP application, Nonlinear Systems can be given. In the financial applications, generally back propagation (Feedforwared) algorithms of the Neural Network (NN) uses. In this application, backpropagation algorithms applied to Multi Layer Feedforward Neural Network for the future estimations of foreign currency exc...

  20. The neural network approach to parton fitting

    International Nuclear Information System (INIS)

    We introduce the neural network approach to global fits of parton distribution functions. First we review previous work on unbiased parametrizations of deep-inelastic structure functions with faithful estimation of their uncertainties, and then we summarize the current status of neural network parton distribution fits

  1. 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. PMID:20713305

  2. 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.

  3. 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.

  4. Self-organization of neural networks

    Science.gov (United States)

    Clark, John W.; Winston, Jeffrey V.; Rafelski, Johann

    1984-05-01

    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 conductive to the simulation of memory and learning phenomena.

  5. 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....

  6. Neural Network Algorithm for Particle Loading

    International Nuclear Information System (INIS)

    An artificial neural network algorithm for continuous minimization is developed and applied to the case of numerical particle loading. It is shown that higher-order moments of the probability distribution function can be efficiently renormalized using this technique. A general neural network for the renormalization of an arbitrary number of moments is given

  7. 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.

  8. Understanding Neural Networks Through Deep Visualization

    OpenAIRE

    Yosinski, Jason; Clune, Jeff; Nguyen, Anh; Fuchs, Thomas; Lipson, Hod

    2015-01-01

    Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural images. However, our understanding of how these models work, especially what computations they perform at intermediate layers, has lagged behind. Progress in the field will be further accelerated by the development of better tools for visualizing and interpreting neural nets. We introduce two such tools ...

  9. Introduction to Concepts in Artificial Neural Networks

    Science.gov (United States)

    Niebur, Dagmar

    1995-01-01

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

  10. MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION

    OpenAIRE

    Artur Popko; Marek Jakubowski; Rafał Wawer

    2013-01-01

    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...

  11. Visual Character Recognition using Artificial Neural Networks

    OpenAIRE

    Araokar, Shashank

    2005-01-01

    The recognition of optical characters is known to be one of the earliest applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In this paper, a simplified neural approach to recognition of optical or visual characters is portrayed and discussed. The document is expected to serve as a resource for learners and amateur investigators in pattern recognition, neural networking and related disciplines.

  12. Secure Key Exchange using Neural Network

    OpenAIRE

    Vineeta Soni

    2014-01-01

    Any cryptographic system is used to exchange confidential information securely over the public channel without any leakage of information to the unauthorized users. Neural networks can be used to generate a common secret key because the processes involve in Cryptographic system requires large computational power and very complex. Moreover Diffi hellman key exchange is suffered from man-in –the middle attack. For overcome this problem neural networks can be used.Two neural netwo...

  13. Modularity as a Solution to Spatial Interference in Neural Networks

    OpenAIRE

    Soldal, Kim Verner

    2012-01-01

    Modularity is an architectural trait that is prominent in biological neural networks, but strangely absent in evolved artificial neural networks. This report contains the results of a theoretical study focusing on two questions about modularity in neural network systems. How does modularity emerge in biological neural networks, and when could modularity be useful in artificial neural networks?The theoretical study resulted in a hypothesis that modularity in biological neural networks is the r...

  14. Rule Extraction using Artificial Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined using pruning algorithm. The ...

  15. 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...

  16. Neural network correspondencies of engineering principles

    Science.gov (United States)

    Schneider, Georg; Korte, Detlef; Rudolph, Stephan

    2000-03-01

    Applications of neural networks have been reported on a lot in recent years, but the research on how to find reliable guidelines to design neural networks is still in its infancy. This work intends to provide some ideas on how to find useful predefined network structures for at least certain parts of the neural net. By breaking off to a certain extend the so-called black-box character of the neural net, the performance of the networks can be improved and the solutions of the nets get more transparent and understandable at the same time. Additionally, the ability of the neural nets to generalize from some training patterns to unlearned data regions is improved substantially. In this work two commonly used engineering principles such as the technique of dimensional analysis and the Laplace- transformation are used to identify suitable topologies for neural networks. The integration of the dimensional analysis in the context of feed-forward neural networks is presented. In the second part of this work the use of the Laplace- transformation in neural networks is demonstrated. Even though at the moment the application of this technique has been shown in a linear time-invariant process, a future use of this method in nonlinear system is considered.

  17. Enhancing neural-network performance via assortativity

    International Nuclear Information System (INIS)

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

  18. Cryptography based on delayed chaotic neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Yu Wenwu [Department of Mathematics, Southeast University, Nanjing 210096 (China); Cao Jinde [Department of Mathematics, Southeast University, Nanjing 210096 (China)]. E-mail: jdcao@seu.edu.cn

    2006-08-14

    In this Letter, a novel approach of encryption based on chaotic Hopfield neural networks with time varying delay is proposed. We use the chaotic neural network to generate binary sequences which will be used for masking plaintext. The plaintext is masked by switching of chaotic neural network maps and permutation of generated binary sequences. Simulation results were given to show the feasibility and effectiveness in the proposed scheme of this Letter. As a result, chaotic cryptography becomes more practical in the secure transmission of large multi-media files over public data communication network.

  19. Cryptography based on delayed chaotic neural networks

    International Nuclear Information System (INIS)

    In this Letter, a novel approach of encryption based on chaotic Hopfield neural networks with time varying delay is proposed. We use the chaotic neural network to generate binary sequences which will be used for masking plaintext. The plaintext is masked by switching of chaotic neural network maps and permutation of generated binary sequences. Simulation results were given to show the feasibility and effectiveness in the proposed scheme of this Letter. As a result, chaotic cryptography becomes more practical in the secure transmission of large multi-media files over public data communication network

  20. Mass reconstruction with a neural network

    International Nuclear Information System (INIS)

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

  1. Neural networks: a biased overview

    International Nuclear Information System (INIS)

    An overview of recent activity in the field of neural networks is presented. The long-range aim of this research is to understand how the brain works. First some of the problems are stated and terminology defined; then an attempt is made to explain why physicists are drawn to the field, and their main potential contribution. In particular, in recent years some interesting models have been introduced by physicists. A small subset of these models is described, with particular emphasis on those that are analytically soluble. Finally a brief review of the history and recent developments of single- and multilayer perceptrons is given, bringing the situation up to date regarding the central immediate problem of the field: search for a learning algorithm that has an associated convergence theorem

  2. Subspace learning of neural networks

    CERN Document Server

    Cheng Lv, Jian; Zhou, Jiliu

    2010-01-01

    PrefaceChapter 1. Introduction1.1 Introduction1.1.1 Linear Neural Networks1.1.2 Subspace Learning1.2 Subspace Learning Algorithms1.2.1 PCA Learning Algorithms1.2.2 MCA Learning Algorithms1.2.3 ICA Learning Algorithms1.3 Methods for Convergence Analysis1.3.1 SDT Method1.3.2 DCT Method1.3.3 DDT Method1.4 Block Algorithms1.5 Simulation Data Set and Notation1.6 ConclusionsChapter 2. PCA Learning Algorithms with Constants Learning Rates2.1 Oja's PCA Learning Algorithms2.1.1 The Algorithms2.1.2 Convergence Issue2.2 Invariant Sets2.2.1 Properties of Invariant Sets2.2.2 Conditions for Invariant Sets2.

  3. Sunspot prediction using neural networks

    Science.gov (United States)

    Villarreal, James; Baffes, Paul

    1990-01-01

    The earliest systematic observance of sunspot activity is known to have been discovered by the Chinese in 1382 during the Ming Dynasty (1368 to 1644) when spots on the sun were noticed by looking at the sun through thick, forest fire smoke. Not until after the 18th century did sunspot levels become more than a source of wonderment and curiosity. Since 1834 reliable sunspot data has been collected by the National Oceanic and Atmospheric Administration (NOAA) and the U.S. Naval Observatory. Recently, considerable effort has been placed upon the study of the effects of sunspots on the ecosystem and the space environment. The efforts of the Artificial Intelligence Section of the Mission Planning and Analysis Division of the Johnson Space Center involving the prediction of sunspot activity using neural network technologies are described.

  4. Introduction to artificial neural networks.

    Science.gov (United States)

    Grossi, Enzo; Buscema, Massimo

    2007-12-01

    The coupling of computer science and theoretical bases such as nonlinear dynamics and chaos theory allows the creation of 'intelligent' agents, such as artificial neural networks (ANNs), able to adapt themselves dynamically to problems of high complexity. ANNs are able to reproduce the dynamic interaction of multiple factors simultaneously, allowing the study of complexity; they can also draw conclusions on individual basis and not as average trends. These tools can offer specific advantages with respect to classical statistical techniques. This article is designed to acquaint gastroenterologists with concepts and paradigms related to ANNs. The family of ANNs, when appropriately selected and used, permits the maximization of what can be derived from available data and from complex, dynamic, and multidimensional phenomena, which are often poorly predictable in the traditional 'cause and effect' philosophy. PMID:17998827

  5. How glassy are neural networks?

    International Nuclear Information System (INIS)

    In this paper we continue our investigation on the high storage regime of a neural network with Gaussian patterns. Through an exact mapping between its partition function and one of a bipartite spin glass (whose parties consist of Ising and Gaussian spins respectively), we give a complete control of the whole annealed region. The strategy explored is based on an interpolation between the bipartite system and two independent spin glasses built respectively by dichotomic and Gaussian spins: critical line, behavior of the principal thermodynamic observables and their fluctuations as well as overlap fluctuations are obtained and discussed. Then, we move further, extending such an equivalence beyond the critical line, to explore the broken ergodicity phase under the assumption of replica symmetry and show that the quenched free energy of this (analogical) Hopfield model can be described as a linear combination of the two quenched spin glass free energies even in the replica symmetric framework. (paper)

  6. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    With the very high event rates projected for experiments at the SSC and LHC, it is important to investigate new approaches to on line pattern recognition. The use of neural networks for pattern recognition. The use of neural networks for pattern recognition in high energy physics detectors has been an area of very active research. The authors discuss drift chamber tracking with a commercial analog 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

  7. Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations

    International Nuclear Information System (INIS)

    In this study, eight image tasks: connected component detection (CCD) with down, right, +45o and -45o directions, edge detection, shadow projection with left and right directions and point removal are analyzed. These tasks are solved using the binary input and binary output discrete-time cellular neural networks (DTCNNs) associated with suitable templates. Furthermore, the behavior of the DTCNNs can be realized using Boolean functions, and the corresponding equivalent logic circuits are derived. An 8 x 8 DTCNNs-based image-processing chip is implemented by the FPGA technology. A simulation of the chip developed for the CCD task is also presented

  8. Neural networks for damage identification

    Energy Technology Data Exchange (ETDEWEB)

    Paez, T.L.; Klenke, S.E.

    1997-11-01

    Efforts to optimize the design of mechanical systems for preestablished use environments and to extend the durations of use cycles establish a need for in-service health monitoring. Numerous studies have proposed measures of structural response for the identification of structural damage, but few have suggested systematic techniques to guide the decision as to whether or not damage has occurred based on real data. Such techniques are necessary because in field applications the environments in which systems operate and the measurements that characterize system behavior are random. This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework; it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.

  9. Exponential Stability for Delayed Cellular Neural Networks

    Institute of Scientific and Technical Information of China (English)

    YANG Jin-xiang; ZHONG Shou-ming; YAN Ke-yu

    2005-01-01

    The exponential stability of the delayed cellular neural networks (DCNN's) is investigated. By dividing the network state variables into some parts according to the characters of the neural networks, some new sufficient conditions of exponential stability are derived via constructing a Liapunov function. It is shown that the conditions differ from previous ones. The new conditions, which are associated with some initial value, are represented by some blocks of the interconnection matrix.

  10. 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.

  11. Nonlinear programming with feedforward neural networks.

    Energy Technology Data Exchange (ETDEWEB)

    Reifman, J.

    1999-06-02

    We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf optimization tool.

  12. Scale-Invariant Convolutional Neural Networks

    OpenAIRE

    Xu, Yichong; Xiao, Tianjun; Zhang, Jiaxing; Yang, Kuiyuan; Zhang, Zheng

    2014-01-01

    Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited. The popular practise is making the model bigger first, and then train it with data augmentation using extensive scale-jittering. In this paper, we propose a scaleinvariant convolutional neural network (SiCNN), a modeldesigned to incorporate multi-scale feature exaction and classification into the network structure. SiCNN use...

  13. Diverse Embedding Neural Network Language Models

    OpenAIRE

    Audhkhasi, Kartik; Sethy, Abhinav; Ramabhadran, Bhuvana

    2014-01-01

    We propose Diverse Embedding Neural Network (DENN), a novel architecture for language models (LMs). A DENNLM projects the input word history vector onto multiple diverse low-dimensional sub-spaces instead of a single higher-dimensional sub-space as in conventional feed-forward neural network LMs. We encourage these sub-spaces to be diverse during network training through an augmented loss function. Our language modeling experiments on the Penn Treebank data set show the performance benefit of...

  14. 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.

  15. Neural network regulation driven by autonomous neural firings

    Science.gov (United States)

    Cho, Myoung Won

    2016-07-01

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

  16. Coronary Artery Diagnosis Aided by Neural Network

    Science.gov (United States)

    Stefko, Kamil

    2007-01-01

    Coronary artery disease is due to atheromatous narrowing and subsequent occlusion of the coronary vessel. Application of optimised feed forward multi-layer back propagation neural network (MLBP) for detection of narrowing in coronary artery vessels is presented in this paper. The research was performed using 580 data records from traditional ECG exercise test confirmed by coronary arteriography results. Each record of training database included description of the state of a patient providing input data for the neural network. Level and slope of ST segment of a 12 lead ECG signal recorded at rest and after effort (48 floating point values) was the main component of input data for neural network was. Coronary arteriography results (verified the existence or absence of more than 50% stenosis of the particular coronary vessels) were used as a correct neural network training output pattern. More than 96% of cases were correctly recognised by especially optimised and a thoroughly verified neural network. Leave one out method was used for neural network verification so 580 data records could be used for training as well as for verification of neural network.

  17. Application of neural network to CT

    International Nuclear Information System (INIS)

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

  18. USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS

    Directory of Open Access Journals (Sweden)

    Murat ŞEKER

    2004-04-01

    Full Text Available Examples of successful applications in Artificial Intelligence (AI field; With financial applications, Control, Communication, Processing Radar signals, Pattern Recognition, general DSP application, Nonlinear Systems can be given. In the financial applications, generally back propagation (Feedforwared algorithms of the Neural Network (NN uses. In this application, backpropagation algorithms applied to Multi Layer Feedforward Neural Network for the future estimations of foreign currency exchange rates data. The calculation results which was founded by using past exchange rates data "estimations that produce by Neural Network Layers and parameters, which carry out by backpropagation algorithms for different values" was compared with the real data for measuring the productivity of the method.

  19. Multispectral-image fusion using neural networks

    Science.gov (United States)

    Kagel, Joseph H.; Platt, C. A.; Donaven, T. W.; Samstad, Eric A.

    1990-08-01

    A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard a circuit card assembly and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations results and a description of the prototype system are presented. 1.

  20. Multispectral image fusion using neural networks

    Science.gov (United States)

    Kagel, J. H.; Platt, C. A.; Donaven, T. W.; Samstad, E. A.

    1990-01-01

    A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.

  1. Advanced Neural Network Applied In Engineering Science

    OpenAIRE

    Nikita Patel*; Rakesh Patel,

    2014-01-01

    The basic idea behind a neural network is to simulate (copy in a simplified but reasonably faithful way) lots of densely interconnected brain cells inside a computer so you can get it to learn things, recognize patterns, and make decisions in a humanlike way. The amazing thing about a neural network is that you don't have to program it to learn explicitly: it learns all by itself, just like a brain! But it isn't a brain. It's important to note that neural networks are (generally) ...

  2. Neural networks for intelligent signal processing

    CERN Document Server

    Zaknich, Anthony

    2003-01-01

    This book provides a thorough theoretical and practical introduction to the application of neural networks to pattern recognition and intelligent signal processing. It has been tested on students, unfamiliar with neural networks, who were able to pick up enough details to successfully complete their masters or final year undergraduate projects. The text also presents a comprehensive treatment of a class of neural networks called common bandwidth spherical basis function NNs, including the probabilistic NN, the modified probabilistic NN and the general regression NN. Contents: A Brief Historica

  3. Stock market index prediction using neural networks

    Science.gov (United States)

    Komo, Darmadi; Chang, Chein-I.; Ko, Hanseok

    1994-03-01

    A neural network approach to stock market index prediction is presented. Actual data of the Wall Street Journal's Dow Jones Industrial Index has been used for a benchmark in our experiments where Radial Basis Function based neural networks have been designed to model these indices over the period from January 1988 to Dec 1992. A notable success has been achieved with the proposed model producing over 90% prediction accuracies observed based on monthly Dow Jones Industrial Index predictions. The model has also captured both moderate and heavy index fluctuations. The experiments conducted in this study demonstrated that the Radial Basis Function neural network represents an excellent candidate to predict stock market index.

  4. 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...... (HNNs) with much fewer parameters than conventional HMMs and other hybrids can obtain comparable performance, and for the broad class task it is illustrated how the HNN can be applied as a purely transition based system, where acoustic context dependent transition probabilities are estimated by neural...... networks...

  5. 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....

  6. Boolean Differential Operators

    OpenAIRE

    Catumba, Jorge; Diaz, Rafael

    2012-01-01

    We consider four combinatorial interpretations for the algebra of Boolean differential operators. We show that each interpretation yields an explicit matrix representation for Boolean differential operators.

  7. 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...

  8. An Introduction to Neural Networks for Hearing Aid Noise Recognition.

    Science.gov (United States)

    Kim, Jun W.; Tyler, Richard S.

    1995-01-01

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

  9. A COMPREHENSIVE EVOLUTIONARY APPROACH FOR NEURAL NETWORK ENSEMBLES AUTOMATIC DESIGN

    OpenAIRE

    Bukhtoyarov, V.; Semenkin, E.

    2010-01-01

    A new comprehensive approach for neural network ensembles design is proposed. It consists of a method of neural networks automatic design and a method of automatic formation of an ensemble solution on the basis of separate neural networks solutions. It is demonstrated that the proposed approach is not less effective than a number of other approaches for neural network ensembles design.

  10. Diagnosis method utilizing neural networks

    International Nuclear Information System (INIS)

    Studies have been made on the technique of neural networks, which will be used to identify a cause of a small anomalous state in the reactor coolant system of the ATR (Advance Thermal Reactor). Three phases of analyses were carried out in this study. First, simulation for 100 seconds was made to determine how the plant parameters respond after the occurence of a transient decrease in reactivity, flow rate and temperature of feed water and increase in the steam flow rate and steam pressure, which would produce a decrease of water level in a steam drum of the ATR. Next, the simulation data was analysed utilizing an autoregressive model. From this analysis, a total of 36 coherency functions up to 0.5 Hz in each transient were computed among nine important and detectable plant parameters: neutron flux, flow rate of coolant, steam or feed water, water level in the steam drum, pressure and opening area of control valve in a steam pipe, feed water temperature and electrical power. Last, learning of neural networks composed of 96 input, 4-9 hidden and 5 output layer units was done by use of the generalized delta rule, namely a back-propagation algorithm. These convergent computations were continued as far as the difference between the desired outputs, 1 for direct cause or 0 for four other ones and actual outputs reached less than 10%. (1) Coherency functions were not governed by decreasing rate of reactivity in the range of 0.41x10-2dollar/s to 1.62x10-2dollar /s or by decreasing depth of the feed water temperature in the range of 3 deg C to 10 deg C or by a change of 10% or less in the three other causes. Change in coherency functions only depended on the type of cause. (2) The direct cause from the other four ones could be discriminated with 0.94+-0.01 of output level. A maximum of 0.06 output height was found among the other four causes. (3) Calculation load which is represented as products of learning times and numbers of the hidden units did not depend on the numbers

  11. Boosted Neural Networks in Evolutionary Computation

    Czech Academy of Sciences Publication Activity Database

    Holeňa, Martin; Linke, D.; Steinfeldt, N.

    Bangkok : King Mongkut's University of Technology Thonburi, 2009. s. 225-226. [ICONIP 2009. International Conference on Neural Information Processing /16./. 01.12.2009-05.12.2009, Bangkok] Institutional research plan: CEZ:AV0Z10300504 Keywords : evolutionary algorithms * empirical objective functions * surrogate modelling * surrogate modelling * artificial neural networks * boosting Subject RIV: IN - Informatics, Computer Science

  12. Artificial neural networks for plasma spectroscopy analysis

    International Nuclear Information System (INIS)

    Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics

  13. Neural Networks in Mobile Robot Motion

    Directory of Open Access Journals (Sweden)

    Danica Janglova

    2008-11-01

    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.

  14. Hindcasting of storm waves using neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Rao, S.; Mandal, S.

    Cyclone generated waves play a significant role in the design of coastal and offshore structures. Instead of conventional numerical models, neural network approach is used in the present study to estimate the wave parameters from cyclone generated...

  15. Hindcasting cyclonic waves using neural networks

    Digital Repository Service at National Institute of Oceanography (India)

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

    Cyclone generated waves play a significant role in the design of coastal and offshore structures. Instead of conventional numerical models, neural network approach is used in the present study to estimate the wave parameters from cyclone generated...

  16. Neural Network Based 3D Surface Reconstruction

    Directory of Open Access Journals (Sweden)

    Vincy Joseph

    2009-11-01

    Full Text Available This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach

  17. TIME SERIES FORECASTING USING NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    BOGDAN OANCEA

    2013-05-01

    Full Text Available Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.

  18. Imbibition well stimulation via neural network design

    Science.gov (United States)

    Weiss, William

    2007-08-14

    A method for stimulation of hydrocarbon production via imbibition by utilization of surfactants. The method includes use of fuzzy logic and neural network architecture constructs to determine surfactant use.

  19. Neural networks for NOx-emission

    International Nuclear Information System (INIS)

    The government wants to restrict nitrogen oxide emissions. However, continuous measurement of these emissions is expensive and maintenance-sensitive. A prediction model based on the use of neural networks might be a reliable and efficient alternative

  20. Generating News Headlines with Recurrent Neural Networks

    OpenAIRE

    Lopyrev, Konstantin

    2015-01-01

    We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news articles. Furthermore, we study how the neural network decides which input words to pay attention to, and specifically we identify the function of the different neurons in a simplified attention mechanism. Interestingly, our simplified attention mechanism performs...

  1. Applications of Pulse-Coupled Neural Networks

    CERN Document Server

    Ma, Yide; Wang, Zhaobin

    2011-01-01

    "Applications of Pulse-Coupled Neural Networks" explores the fields of image processing, including image filtering, image segmentation, image fusion, image coding, image retrieval, and biometric recognition, and the role of pulse-coupled neural networks in these fields. This book is intended for researchers and graduate students in artificial intelligence, pattern recognition, electronic engineering, and computer science. Prof. Yide Ma conducts research on intelligent information processing, biomedical image processing, and embedded system development at the School of Information Sci

  2. Neural networks, D0, and the SSC

    International Nuclear Information System (INIS)

    We outline several exploratory studies involving neural network simulations applied to pattern recognition in high energy physics. We describe the D0 data acquisition system and a natual means by which algorithms derived from neural networks techniques may be incorporated into recently developed hardware associated with the D0 MicroVAX farm nodes. Such applications to the event filtering needed by SSC detectors look interesting. 10 refs., 11 figs

  3. Parameterizing Stellar Spectra Using Deep Neural Networks

    OpenAIRE

    Li, Xiangru; Pan, Ruyang

    2016-01-01

    This work investigates the spectrum parameterization problem using deep neural networks (DNNs). The proposed scheme consists of the following procedures: first, the configuration of a DNN is initialized using a series of autoencoder neural networks; second, the DNN is fine-tuned using a gradient descent scheme; third, stellar parameters ($T_{eff}$, log$~g$, and [Fe/H]) are estimated using the obtained DNN. This scheme was evaluated on both real spectra from SDSS/SEGUE and synthetic spectra ca...

  4. Deep neural networks for spam classification

    OpenAIRE

    Kasmani, Mohamed Khizer

    2013-01-01

    This project elucidates the development of a spam filtering method using deep neural networks. A classification model employing algorithms such as Error Back Propagation (EBP) and Restricted Boltzmann Machines (RBM) is used to identify spam and non-spam emails. Moreover, a spam classification system employing deep neural network algorithms is developed, which has been tested on Enron email dataset in order to help users manage large volumes of email and, furthermore, their email folders. The ...

  5. FUZZY GRAPHS IN FUZZY NEURAL NETWORKS

    OpenAIRE

    K Sameena; M.S. Sunitha

    2009-01-01

    In this paper we observe that, the fuzzy neural network architecture is isomorphic to the fuzzy graph model and the output of a fuzzy neural network with OR fuzzy neuron is equal to the strength of strongest path between the input layer (particular input neuron/neurons) and the out put layer(particular output neuron). We explain this result through an example, which describes the marketability of text books of kindergarten classes.

  6. Development of Polymer Resins using Neural Networks

    OpenAIRE

    Fernandes Fabiano A. N.; Lona Liliane M. F.

    2002-01-01

    The development of polymer resins can benefit from the application of neural networks, using its great ability to correlate inputs and outputs. In this work we have developed a procedure that uses neural networks to correlate the end-user properties of a polymer with the polymerization reactor's operational condition that will produce that desired polymer. This procedure is aimed at speeding up the development of new resins and help finding the appropriate operational conditions to produce a ...

  7. An Introduction to Convolutional Neural Networks

    OpenAIRE

    O'Shea, Keiron; Nash, Ryan

    2015-01-01

    The field of machine learning has taken a dramatic twist in recent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models are able to far exceed the performance of previous forms of artificial intelligence in common machine learning tasks. One of the most impressive forms of ANN architecture is that of the Convolutional Neural Network (CNN). CNNs are primarily used to solve difficult image-driven pattern recognition tasks and with their p...

  8. Density functional and neural network analysis

    DEFF Research Database (Denmark)

    Jalkanen, K. J.; Suhai, S.; Bohr, Henrik

    1997-01-01

    dichroism (VCD) intensities. The large changes due to hydration on the structures, relative stability of conformers, and in the VA and VCD spectra observed experimentally are reproduced by the DFT calculations. Furthermore a neural network was constructed for reproducing the inverse scattering data (infer...... the structural coordinates from spectroscopic data) that the DFT method could produce. Finally the neural network performances are used to monitor a sensitivity or dependence analysis of the importance of secondary structures....

  9. Neural Network Classifier Based on Growing Hyperspheres

    Czech Academy of Sciences Publication Activity Database

    Jiřina Jr., Marcel; Jiřina, Marcel

    2000-01-01

    Roč. 10, č. 3 (2000), s. 417-428. ISSN 1210-0552. [Neural Network World 2000. Prague, 09.07.2000-12.07.2000] Grant ostatní: MŠMT ČR(CZ) VS96047; MPO(CZ) RP-4210 Institutional research plan: AV0Z1030915 Keywords : neural network * classifier * hyperspheres * big -dimensional data Subject RIV: BA - General Mathematics

  10. SAR ATR Based on Convolutional Neural Network

    OpenAIRE

    Tian Zhuangzhuang; Zhan Ronghui; Hu Jiemin; Zhang Jun

    2016-01-01

    This study presents a new method of Synthetic Aperture Radar (SAR) image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recogni...

  11. Memory-Based Boolean Game and Self-Organized Phenomena on Networks

    Institute of Scientific and Technical Information of China (English)

    HUANG Zi-Gang; WU Zhi-Xi; GUAN Jian-Yue; WANG Ying-Hai

    2006-01-01

    @@ We study a memory-based Boolean game (MBBG) taking place on a regular ring, wherein each agent acts according to its local optimal states of the last M time steps recorded in memory, and the agents in the minority are rewarded. One free parameter p between 0 and 1 is introduced to denote the strength of the agent willing to make a decision according to its memory. It is found that giving proper willing strength p, the MBBG system can spontaneously evolve to a state of performance better than the random game; while for larger p, the herd behaviour emerges to reduce the system profit. By analysing the dependence of dynamics of the system on the memory capacity M, we find that a higher memory capacity favours the emergence of the better performance state, and effectively restrains the herd behaviour, thus increases the system profit. Considering the high cost of long-time memory, the enhancement of memory capacity for restraining the herd behaviour is also discussed,and M = 5 is suggested to be a good choice.

  12. Hopfield neural network based on ant system

    Institute of Scientific and Technical Information of China (English)

    洪炳镕; 金飞虎; 郭琦

    2004-01-01

    Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters.This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement.

  13. Cluster detection algorithm in neural networks

    OpenAIRE

    Meunier, David; Paugam-Moisy, Hélène

    2006-01-01

    Complex networks have received much attention in the last few years, and reveal global properties of interacting systems in domains like biology, social sciences and technology. One of the key feature of complex networks is their clusterized structure. Most methods applied to study complex networks are based on undirected graphs. However, when considering neural networks, the directionality of links is fundamental. In this article, a method of cluster detection is extended for directed graphs...

  14. Fastest learning in small world neural networks

    OpenAIRE

    Simard, D.; Nadeau, L; Kröger, H.

    2004-01-01

    We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition.

  15. Option Pricing Using Bayesian Neural Networks

    CERN Document Server

    Pires, Michael Maio

    2007-01-01

    Options have provided a field of much study because of the complexity involved in pricing them. The Black-Scholes equations were developed to price options but they are only valid for European styled options. There is added complexity when trying to price American styled options and this is why the use of neural networks has been proposed. Neural Networks are able to predict outcomes based on past data. The inputs to the networks here are stock volatility, strike price and time to maturity with the output of the network being the call option price. There are two techniques for Bayesian neural networks used. One is Automatic Relevance Determination (for Gaussian Approximation) and one is a Hybrid Monte Carlo method, both used with Multi-Layer Perceptrons.

  16. Optical neural stimulation modeling on degenerative neocortical neural networks

    Science.gov (United States)

    Zverev, M.; Fanjul-Vélez, F.; Salas-García, I.; Arce-Diego, J. L.

    2015-07-01

    Neurodegenerative diseases usually appear at advanced age. Medical advances make people live longer and as a consequence, the number of neurodegenerative diseases continuously grows. There is still no cure for these diseases, but several brain stimulation techniques have been proposed to improve patients' condition. One of them is Optical Neural Stimulation (ONS), which is based on the application of optical radiation over specific brain regions. The outer cerebral zones can be noninvasively stimulated, without the common drawbacks associated to surgical procedures. This work focuses on the analysis of ONS effects in stimulated neurons to determine their influence in neuronal activity. For this purpose a neural network model has been employed. The results show the neural network behavior when the stimulation is provided by means of different optical radiation sources and constitute a first approach to adjust the optical light source parameters to stimulate specific neocortical areas.

  17. Artificial astrocytes improve neural network performance.

    Science.gov (United States)

    Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

    2011-01-01

    Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157

  18. Artificial astrocytes improve neural network performance.

    Directory of Open Access Journals (Sweden)

    Ana B Porto-Pazos

    Full Text Available Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN and artificial neuron-glia networks (NGN to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.

  19. Artificial Neural Network in Prognosticating Human Personality from Social Networks

    Directory of Open Access Journals (Sweden)

    Harish Kumar V

    2013-10-01

    Full Text Available The analysis of text in the form of tweets, chat or posts can be an interesting as well as challenging area of research. In this paper, such an analysis provides information about the human behavior as positive, negative or neutral. For simplicity, tweets from social networking site, Twitter, are extracted for analyzing human personality. Various concepts from natural language processing, text mining and neural networks are used to establish the final outcome of the application. For analyzing text, Neural Networks are implemented which are so modeled that they predict the Human behavior as positive, negative or neutral based on extracted and preprocessed data. Using Neural Networks, the particular pattern is identified and weights are provided to words based on the extracted pattern.Neural networks have an added advantage of adaptive learning. This application can be immensely useful for politics, medical science, sports, matrimonial purposes etc.The results so obtained are quite promising.

  20. Combinatorics of Boolean automata circuits dynamics

    OpenAIRE

    Demongeot, Jacques; Noual, Mathilde; Sené, Sylvain

    2012-01-01

    International audience In line with fields of theoretical computer science and biology that study Boolean automata networks to model regulation networks, we present some results concerning the dynamics of networks whose underlying structures are oriented cycles, that is, Boolean automata circuits. In the context of biological regulation, former studies have highlighted the importance of circuits on the asymptotic dynamical behaviour of the biological networks that contain them. Our work fo...

  1. Digital Recognition using Neural Network

    Directory of Open Access Journals (Sweden)

    Saleh A.K. Al-Omari

    2009-01-01

    Full Text Available Problem statement: Handwriting number recognition is a challenging problem researchers had been research into this area for so long especially in the recent years. In our study there are many fields concern with numbers, for example, checks in banks or recognizing numbers in car plates, the subject of digit recognition appears. A system for recognizing isolated digits may be as an approach for dealing with such application. In other words, to let the computer understand the Arabic numbers that is written manually by users and views them according to the computer process. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with handwriting number recognition problems such as, minimum distance, decision tree and statistics. Approach: The main objective for our system was to recognize isolated Arabic digits exist in different applications. For example, different users had their own handwriting styles where here the main challenge falls to let computer system understand these different handwriting styles and recognize them as standard writing. Result: We presented a system for dealing with such problem. The system started by acquiring an image containing digits, this image was digitized using some optical devices and after applying some enhancements and modifications to the digits within the image it can be recognized using feed forward back propagation algorithm. The studies were conducted on the Arabic handwriting digits of 10 independent writers who contributed a total of 1300 isolated Arabic digits these digits divided into two data sets: Training 1000 digits, testing 300 digits. An overall accuracy meet using this system was 95% on the test data set used. Conclusion: We developed a system for Arabic handwritten recognition. And we efficiently choose a segmentation method to fit our demands. Our system successfully designs and implement a neural network which efficiently

  2. Pattern Classification using Simplified Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    In recent years, many neural network models have been proposed for pattern classification, function approximation and regression problems. This paper presents an approach for classifying patterns from simplified NNs. Although the predictive accuracy of ANNs is often higher than that of other methods or human experts, it is often said that ANNs are practically "black boxes", due to the complexity of the networks. In this paper, we have an attempted to open up these black boxes by reducing the complexity of the network. The factor makes this possible is the pruning algorithm. By eliminating redundant weights, redundant input and hidden units are identified and removed from the network. Using the pruning algorithm, we have been able to prune networks such that only a few input units, hidden units and connections left yield a simplified network. Experimental results on several benchmarks problems in neural networks show the effectiveness of the proposed approach with good generalization ability.

  3. 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…

  4. Estimating Conditional Distributions by Neural Networks

    DEFF Research Database (Denmark)

    Kulczycki, P.; Schiøler, Henrik

    1998-01-01

    Neural Networks for estimating conditionaldistributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency property is considered from a mild set of assumptions. A number of applications...

  5. Comparing artificial and biological dynamical neural networks

    Science.gov (United States)

    McAulay, Alastair D.

    2006-05-01

    Modern computers can be made more friendly and otherwise improved by making them behave more like humans. Perhaps we can learn how to do this from biology in which human brains evolved over a long period of time. Therefore, we first explain a commonly used biological neural network (BNN) model, the Wilson-Cowan neural oscillator, that has cross-coupled excitatory (positive) and inhibitory (negative) neurons. The two types of neurons are used for frequency modulation communication between neurons which provides immunity to electromagnetic interference. We then evolve, for the first time, an artificial neural network (ANN) to perform the same task. Two dynamical feed-forward artificial neural networks use cross-coupling feedback (like that in a flip-flop) to form an ANN nonlinear dynamic neural oscillator with the same equations as the Wilson-Cowan neural oscillator. Finally we show, through simulation, that the equations perform the basic neural threshold function, switching between stable zero output and a stable oscillation, that is a stable limit cycle. Optical implementation with an injected laser diode and future research are discussed.

  6. Design of Robust Neural Network Classifiers

    DEFF Research Database (Denmark)

    Larsen, Jan; Andersen, Lars Nonboe; Hintz-Madsen, Mads;

    1998-01-01

    This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the log-likelihood and a regularization term (prior). In order to perform robust classification, we present...... a modified likelihood function which incorporates the potential risk of outliers in the data. This leads to the introduction of a new parameter, the outlier probability. Designing the neural classifier involves optimization of network weights as well as outlier probability and regularization...

  7. Gamma spectral analysis via neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Keller, P.E.; Kouzes, R.T.

    1994-10-01

    A system combining a portable gamma-ray spectrometer with a neural network is discussed. In this system, the neural network is used to automatically identify radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perceptron and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perceptron 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 successfully tested with data generated by Monte Carlo simulations and with field data from both sodium iodide and germanium detectors. With the neural network 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 in the field. This approach is useful in situations that require fast response but where precise quantification is less important.

  8. Dynamic pricing by hopfield neural network

    Institute of Scientific and Technical Information of China (English)

    Lusajo M Minga; FENG Yu-qiang(冯玉强); LI Yi-jun(李一军); LU Yang(路杨); Kimutai Kimeli

    2004-01-01

    The increase in the number of shopbots users in e-commerce has triggered flexibility of sellers in their pricing strategies. Sellers see the importance of automated price setting which provides efficient services to a large number of buyers who are using shopbots. This paper studies the characteristic of decreasing energy with time in a continuous model of a Hopfield neural network that is the decreasing of errors in the network with respect to time. The characteristic shows that it is possible to use Hopfield neural network to get the main factor of dynamic pricing; the least variable cost, from production function principles. The least variable cost is obtained by reducing or increasing the input combination factors, and then making the comparison of the network output with the desired output, where the difference between the network output and desired output will be decreasing in the same manner as in the Hopfield neural network energy. Hopfield neural network will simplify the rapid change of prices in e-commerce during transaction that depends on the demand quantity for demand sensitive model of pricing.

  9. Neutron spectrometry using artificial neural networks

    International Nuclear Information System (INIS)

    An artificial neural network has been designed to obtain neutron spectra from Bonner spheres spectrometer count rates. The neural network was trained using 129 neutron spectra. These include spectra from isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra based on mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. The re-binned spectra and the UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and their respective spectra were used as output during the neural network training. After training, the network was tested with the Bonner spheres count rates produced by folding a set of neutron spectra with the response matrix. This set contains data used during network training as well as data not used. Training and testing was carried out using the Matlab(R) program. To verify the network unfolding performance, the original and unfolded spectra were compared using the root mean square error. The use of artificial neural networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated with this ill-conditioned problem

  10. Neutron spectrometry with artificial neural networks

    International Nuclear Information System (INIS)

    An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using 129 neutron spectra. These include isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra from mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-bin ned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and the respective spectrum was used as output during neural network training. After training the network was tested with the Bonner spheres count rates produced by a set of neutron spectra. This set contains data used during network training as well as data not used. Training and testing was carried out in the Mat lab program. To verify the network unfolding performance the original and unfolded spectra were compared using the χ2-test and the total fluence ratios. The use of Artificial Neural Networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  11. Using neural networks to describe tracer correlations

    Directory of Open Access Journals (Sweden)

    D. J. Lary

    2004-01-01

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

  12. Fuzzy neural network with fast backpropagation learning

    Science.gov (United States)

    Wang, Zhiling; De Sario, Marco; Guerriero, Andrea; Mugnuolo, Raffaele

    1995-03-01

    Neural filters with multilayer backpropagation network have been proved to be able to define mostly all linear or non-linear filters. Because of the slowness of the networks' convergency, however, the applicable fields have been limited. In this paper, fuzzy logic is introduced to adjust learning rate and momentum parameter depending upon output errors and training times. This makes the convergency of the network greatly improved. Test curves are shown to prove the fast filters' performance.

  13. Modular neural networks and reinforcement learning

    OpenAIRE

    Raicevic, Peter

    2004-01-01

    We investigate the effect of modular architecture in an artificial neural network for a reinforcement learning problem. Using the supervised backpropagation algorithm to solve a two-task problem, the network performance can be increased by using networks with modular structures. However, using a modular architecture to solve a two-task reinforcement learning problem will not increase the performance compared to a non-modular structure. We show that by combining a modular structure with a modu...

  14. Stability of Stochastic Neutral Cellular Neural Networks

    Science.gov (United States)

    Chen, Ling; Zhao, Hongyong

    In this paper, we study a class of stochastic neutral cellular neural networks. By constructing a suitable Lyapunov functional and employing the nonnegative semi-martingale convergence theorem we give some sufficient conditions ensuring the almost sure exponential stability of the networks. The results obtained are helpful to design stability of networks when stochastic noise is taken into consideration. Finally, two examples are provided to show the correctness of our analysis.

  15. Neural network plasticity in the human brain

    OpenAIRE

    Rizk, Sviatlana

    2013-01-01

    The human brain is highly organized within networks. Functionally related neural-assemblies communicate by oscillating synchronously. Intrinsic brain activity contains information on healthy and damaged brain functioning. This thesis investigated the relationship between functional networks and behavior. Furthermore, we assessed functional network plasticity after brain damage and as a result of brain stimulation. In different groups of patients we observed reduced functional connectivity bet...

  16. Antagonistic neural networks underlying differentiated leadership roles

    OpenAIRE

    Boyatzis, Richard E.; Rochford, Kylie; Jack, Anthony I.

    2014-01-01

    The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950s. Recent research in neuroscience suggests that the division between task-oriented and socio-emotional-oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks – the task-positive network (TPN) and the default mode network (DMN). Neural activity in TPN...

  17. Molding the Knowledge in Modular Neural Networks

    OpenAIRE

    Spaanenburg, L.; Achterop, S.; Slump, C. H.; Zwaag, van der, M.B.

    2002-01-01

    Problem description. The learning of monolithic neural networks becomes harder with growing network size. Likewise the knowledge obtained while learning becomes harder to extract. Such disadvantages are caused by a lack of internal structure, that by its presence would reduce the degrees of freedom in evolving to a training target. A suitable internal structure with respect to modular network construction as well as to nodal discrimination is required. Details on the grouping and selection of...

  18. Network Traffic Prediction based on Particle Swarm BP Neural Network

    OpenAIRE

    Yan Zhu; Guanghua Zhang; Jing Qiu

    2013-01-01

    The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and part...

  19. Parameter estimation using compensatory neural networks

    Indian Academy of Sciences (India)

    M Sinha; P K Kalra; K Kumar

    2000-04-01

    Proposed here is a new neuron model, a basis for Compensatory Neural Network Architecture (CNNA), which not only reduces the total number of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron model as well as the higher neuron model (multiplicative aggregation function). It can adapt to standard neuron and higher order neuron, as well as a combination of the two. This approach is found to estimate the orbit with accuracy significantly better than Kalman Filter (KF) and Feedforward Multilayer Neural Network (FMNN) (also simply referred to as Artificial Neural Network, ANN) with lambda-gamma learning. The typical simulation runs also bring out the superiority of the proposed scheme over Kalman filter from the standpoint of computation time and the amount of data needed for the desired degree of estimated accuracy for the specific problem of orbit determination.

  20. Recognition of Properties by Probabilistic Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Grim, Jiří; Hora, Jan

    Vol. 2. Berlin, Heidelberg : Springer Verlag, 2009 - (Polycarpou, M.; Alipi, C.; Panayiotou, C.; Ellinas, G.), s. 165-174 ISBN 3-642-04276-7. ISSN 0302-9743. - (Lecture Notes in Computer Science. LNCS 5769). [19th International Conference on Artificia Neural Networks . Limassol (CY), 14.09.2009-17.09.2009] R&D Projects: GA MŠk 1M0572; GA ČR GA102/07/1594 Grant ostatní: GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : Probabilistic Neural Networks * Non-Exclusive Classes * One-Class Classifiers * Biological Compatibility Subject RIV: IN - Informatics, Computer Science http://library.utia.cas.cz/separaty/2009/RO/grim-recognition of properties by probabilistic neural networks .pdf

  1. Computational Properties of Probabilistic Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Grim, Jiří; Hora, Jan

    Berlin Heidelberg : Springer Verlag, 2010 - (Diamantaras, K.; Duch, W.; Iliadis, L.), s. 31-40 ISBN 978-3-642-15818-6. - (Lecture Notes in Computer Science. LNCS. Volume 6354). [ICANN 2010. International Conference on Artificial Neural Networks /20./. Thessaloniki (GR), 15.09.2010-18.09.2010] R&D Projects: GA ČR GA102/07/1594; GA MŠk 1M0572 Grant ostatní: GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : Probabilistic neural networks * Statistical pattern recognition * Subspace approach * Overfitting reduction Subject RIV: IN - Informatics, Computer Science http://library.utia.cas.cz/separaty/2010/RO/grim-computational properties of probabilistic neural networks .pdf

  2. Critical and resonance phenomena in neural networks

    Science.gov (United States)

    Goltsev, A. V.; Lopes, M. A.; Lee, K.-E.; Mendes, J. F. F.

    2013-01-01

    Brain rhythms contribute to every aspect of brain function. Here, we study critical and resonance phenomena that precede the emergence of brain rhythms. Using an analytical approach and simulations of a cortical circuit model of neural networks with stochastic neurons in the presence of noise, we show that spontaneous appearance of network oscillations occurs as a dynamical (non-equilibrium) phase transition at a critical point determined by the noise level, network structure, the balance between excitatory and inhibitory neurons, and other parameters. We find that the relaxation time of neural activity to a steady state, response to periodic stimuli at the frequency of the oscillations, amplitude of damped oscillations, and stochastic fluctuations of neural activity are dramatically increased when approaching the critical point of the transition.

  3. Prediction of metal corrosion by neural networks

    Directory of Open Access Journals (Sweden)

    Z. Jančíková

    2013-07-01

    Full Text Available The contribution deals with the use of artificial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are not known so far. Classical analytical and mathematical functions are of limited use to describe this type of strongly non-linear system depending on various meteorological-chemical factors and interaction between them and on material parameters. Nowadays there is certain chance to predict a corrosion loss of materials by artificial neural networks. Neural networks are used primarily in real systems, which are characterized by high nonlinearity, considerable complexity and great difficulty of their formal mathematical description.

  4. Hair Loss Diagnosis Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Ahmad Esfandiari

    2012-09-01

    Full Text Available Hair is an appendage of the skin that plays an important role in the beauty of people's face. Daily averages of 50 to 80 hairs are shed naturally. Various factors are effective in hair loss. In this paper using the eight influence attributes of gender, age, genetic factors, surgery, pregnancy, Zinc deficiency, iron deficiency, anemia and the use of cosmetics, the amount of hair loss is predicted. This work has been performed using artificial neural networks. 60 percent of the collected data was used for train, 20 percent for validation and the remaining 20 percent is used for testing the neural networks. For this, various training algorithms has been used. The result of the implementation of these algorithms has been compared. It seems that neural networks can be successful to predict hair loss.

  5. Web traffic prediction with artificial neural networks

    Science.gov (United States)

    Gluszek, Adam; Kekez, Michal; Rudzinski, Filip

    2005-02-01

    The main aim of the paper is to present application of the artificial neural network in the web traffic prediction. First, the general problem of time series modelling and forecasting is shortly described. Next, the details of building of dynamic processes models with the neural networks are discussed. At this point determination of the model structure in terms of its inputs and outputs is the most important question because this structure is a rough approximation of the dynamics of the modelled process. The following section of the paper presents the results obtained applying artificial neural network (classical multilayer perceptron trained with backpropagation algorithm) to the real-world web traffic prediction. Finally, we discuss the results, describe weak points of presented method and propose some alternative approaches.

  6. Reconstruction of neutron spectra through neural networks

    International Nuclear Information System (INIS)

    A neural network has been used to reconstruct the neutron spectra starting from the counting rates of the detectors of the Bonner sphere spectrophotometric system. A group of 56 neutron spectra was selected to calculate the counting rates that would produce in a Bonner sphere system, with these data and the spectra it was trained the neural network. To prove the performance of the net, 12 spectra were used, 6 were taken of the group used for the training, 3 were obtained of mathematical functions and those other 3 correspond to real spectra. When comparing the original spectra of those reconstructed by the net we find that our net has a poor performance when reconstructing monoenergetic spectra, this attributes it to those characteristic of the spectra used for the training of the neural network, however for the other groups of spectra the results of the net are appropriate with the prospective ones. (Author)

  7. Eddy current flaw characterization using neural network

    International Nuclear Information System (INIS)

    Determination of location, shape and size of a flaw from its eddy current testing signal is one of the fundamental issues in eddy current nondestructive evaluation of steam generator tubes. Here, we propose an approach to this problem; an inversion of eddy current flaw signal using neural networks trained with finite element model-based synthetic signatures. Total 216 eddy current signals from four different types of 2-dimensional axisymmetric flaws in tubes are generated by finite element models of which the accuracy are experimentally verified. From each simulated signature, total 24 eddy current features are extracted and among them 13 features are finally selected for the flaw characterization. Based on these features, probabilistic neural networks discriminate flaws into four different types according to the location and the shape, and successively back propagation neural networks determine the size parameters of the discriminated flaw.

  8. Accident scenario diagnostics with neural networks

    International Nuclear Information System (INIS)

    Nuclear power plants are very complex systems. The diagnoses of transients or accident conditions is very difficult because a large amount of information, which is often noisy, or intermittent, or even incomplete, need to be processed in real time. To demonstrate their potential application to nuclear power plants, neural networks axe used to monitor the accident scenarios simulated by the training simulator of TVA's Watts Bar Nuclear Power Plant. A self-organization network is used to compress original data to reduce the total number of training patterns. Different accident scenarios are closely related to different key parameters which distinguish one accident scenario from another. Therefore, the accident scenarios can be monitored by a set of small size neural networks, called modular networks, each one of which monitors only one assigned accident scenario, to obtain fast training and recall. Sensitivity analysis is applied to select proper input variables for modular networks

  9. Network Traffic Prediction based on Particle Swarm BP Neural Network

    Directory of Open Access Journals (Sweden)

    Yan Zhu

    2013-11-01

    Full Text Available The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and particle swarm optimization algorithm is proposed to optimize the weight and threshold value of BP neural network. After network traffic prediction experiment, we can conclude that optimized BP network traffic prediction based on PSO-ABC has high prediction accuracy and has stable prediction performance.

  10. Optimal control learning with artificial neural networks

    International Nuclear Information System (INIS)

    This paper shows neural networks capabilities in optimal control applications of non linear dynamic systems. Our method is issued of a classical method concerning the direct research of the optimal control using gradient techniques. We show that neural approach and backpropagation paradigm are able to solve efficiently equations relative to necessary conditions for an optimizing solution. We have taken into account the known capabilities of multi layered networks in approximation functions. And for dynamic systems, we have generalized the indirect learning of inverse model adaptive architecture that is capable to define an optimal control in relation to a temporal criterion. (orig.)

  11. Human Face Recognition Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Răzvan-Daniel Albu

    2009-10-01

    Full Text Available In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. The convolutional network extracts successively larger features in a hierarchical set of layers. With the weights of the trained neural networks there are created kernel windows used for feature extraction in a 3-stage algorithm. I present experimental results illustrating the efficiency of the proposed approach. I use a database of 796 images of 159 individuals from Reims University which contains quite a high degree of variability in expression, pose, and facial details.

  12. Neural network approach to radiologic lesion detection

    International Nuclear Information System (INIS)

    An area of artificial intelligence that has gained recent attention is the neural network approach to pattern recognition. The authors explore the use of neural networks in radiologic lesion detection with what is known in the literature as the novelty filter. This filter uses a linear model; images of normal patterns become training vectors and are stored as columns of a matrix. An image of an abnormal pattern is introduced and the abnormality or novelty is extracted. A VAX 750 was used to encode the novelty filter, and two experiments have been examined

  13. Neural networks advances and applications 2

    CERN Document Server

    Gelenbe, E

    1992-01-01

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

  14. Alpha spectral analysis via artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Kangas, L.J.; Hashem, S.; Keller, P.E.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States); Troyer, G.L. [Westinghouse Hanford Co., Richland, WA (United States)

    1994-10-01

    An artificial neural network system that assigns quality factors to alpha particle energy spectra is discussed. The alpha energy spectra are used to detect plutonium contamination in the work environment. The quality factors represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with a quality factor by an expert and used in training the artificial neural network expert system. The investigation shows that the expert knowledge of alpha spectra quality factors can be transferred to an ANN system.

  15. Contractor Prequalification Based on Neural Networks

    Institute of Scientific and Technical Information of China (English)

    ZHANG Jin-long; YANG Lan-rong

    2002-01-01

    Contractor Prequalification involves the screening of contractors by a project owner, according to a given set of criteria, in order to determine their competence to perform the work if awarded the construction contract. This paper introduces the capabilities of neural networks in solving problems related to contractor prequalification. The neural network systems for contractor prequalification has an input vector of 8 components and an output vector of 1 component. The output vector represents whether a contractor is qualified or not qualified to submit a bid on a project.

  16. Spectral classification using convolutional neural networks

    CERN Document Server

    Hála, Pavel

    2014-01-01

    There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from one-dimension spectra only. Author developed several scripts and C programs for datasets preparation, preprocessing and postprocessing of the data. EBLearn library (developed by Pierre Sermanet and Yann LeCun) was used to create ConvNets. Application on dataset of more than 60000 spectra yielded success rate of nearly 95%. This thesis conclusively proved great potential of convolutional neural networks and deep learning methods in astrophysics.

  17. SAR ATR Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Tian Zhuangzhuang

    2016-06-01

    Full Text Available This study presents a new method of Synthetic Aperture Radar (SAR image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recognition SAR datasets prove the validity of this method.

  18. Livermore Big Artificial Neural Network Toolkit

    Energy Technology Data Exchange (ETDEWEB)

    2016-07-01

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

  19. Alpha spectral analysis via artificial neural networks

    International Nuclear Information System (INIS)

    An artificial neural network system that assigns quality factors to alpha particle energy spectra is discussed. The alpha energy spectra are used to detect plutonium contamination in the work environment. The quality factors represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with a quality factor by an expert and used in training the artificial neural network expert system. The investigation shows that the expert knowledge of alpha spectra quality factors can be transferred to an ANN system

  20. Speech Recognition Method Based on Multilayer Chaotic Neural Network

    Institute of Scientific and Technical Information of China (English)

    REN Xiaolin; HU Guangrui

    2001-01-01

    In this paper,speech recognitionusing neural networks is investigated.Especially,chaotic dynamics is introduced to neurons,and a mul-tilayer chaotic neural network (MLCNN) architectureis built.A learning algorithm is also derived to trainthe weights of the network.We apply the MLCNNto speech recognition and compare the performanceof the network with those of recurrent neural net-work (RNN) and time-delay neural network (TDNN).Experimental results show that the MLCNN methodoutperforms the other neural networks methods withrespect to average recognition rate.

  1. An efficient algorithm to identify the optimal one-bit perturbation based on the basin-of-state size of Boolean networks.

    Science.gov (United States)

    Hu, Mingxiao; Shen, Liangzhong; Zan, Xiangzhen; Shang, Xuequn; Liu, Wenbin

    2016-01-01

    Boolean networks are widely used to model gene regulatory networks and to design therapeutic intervention strategies to affect the long-term behavior of systems. In this paper, we investigate the less-studied one-bit perturbation, which falls under the category of structural intervention. Previous works focused on finding the optimal one-bit perturbation to maximally alter the steady-state distribution (SSD) of undesirable states through matrix perturbation theory. However, the application of the SSD is limited to Boolean networks with about ten genes. In 2007, Xiao et al. proposed to search the optimal one-bit perturbation by altering the sizes of the basin of attractions (BOAs). However, their algorithm requires close observation of the state-transition diagram. In this paper, we propose an algorithm that efficiently determines the BOA size after a perturbation. Our idea is that, if we construct the basin of states for all states, then the size of the BOA of perturbed networks can be obtained just by updating the paths of the states whose transitions have been affected. Results from both synthetic and real biological networks show that the proposed algorithm performs better than the exhaustive SSD-based algorithm and can be applied to networks with about 25 genes. PMID:27196530

  2. Autonomous robot behavior based on neural networks

    Science.gov (United States)

    Grolinger, Katarina; Jerbic, Bojan; Vranjes, Bozo

    1997-04-01

    The purpose of autonomous robot is to solve various tasks while adapting its behavior to the variable environment, expecting it is able to navigate much like a human would, including handling uncertain and unexpected obstacles. To achieve this the robot has to be able to find solution to unknown situations, to learn experienced knowledge, that means action procedure together with corresponding knowledge on the work space structure, and to recognize working environment. The planning of the intelligent robot behavior presented in this paper implements the reinforcement learning based on strategic and random attempts for finding solution and neural network approach for memorizing and recognizing work space structure (structural assignment problem). Some of the well known neural networks based on unsupervised learning are considered with regard to the structural assignment problem. The adaptive fuzzy shadowed neural network is developed. It has the additional shadowed hidden layer, specific learning rule and initialization phase. The developed neural network combines advantages of networks based on the Adaptive Resonance Theory and using shadowed hidden layer provides ability to recognize lightly translated or rotated obstacles in any direction.

  3. Neutron spectrum unfolding using neural networks

    International Nuclear Information System (INIS)

    An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using a large set of neutron spectra compiled by the International Atomic Energy Agency. These include spectra from iso- topic neutron sources, reference and operational neutron spectra obtained from accelerators and nuclear reactors. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and correspondent spectrum was used as output during neural network training. The network has 7 input nodes, 56 neurons as hidden layer and 31 neurons in the output layer. After training the network was tested with the Bonner spheres count rates produced by twelve neutron spectra. The network allows unfolding the neutron spectrum from count rates measured with Bonner spheres. Good results are obtained when testing count rates belong to neutron spectra used during training, acceptable results are obtained for count rates obtained from actual neutron fields; however the network fails when count rates belong to monoenergetic neutron sources. (Author)

  4. Prediction of transition boiling heat transfer by artificial neural network

    International Nuclear Information System (INIS)

    Based on the capability of nonlinear mapping of artificial neural network, a neural network is presented to predict the transition boiling heat transfer in vertical annulus and vertical tube. The predicting results show good accordance with the experimental results

  5. Stability prediction of berm breakwater using neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Rao, S.; Manjunath, Y.R.

    In the present study, an artificial neural network method has been applied to predict the stability of berm breakwaters. Four neural network models are constructed based on the parameters which influence the stability of breakwater. Training...

  6. Neural network tomography: network replication from output surface geometry.

    Science.gov (United States)

    Minnett, Rupert C J; Smith, Andrew T; Lennon, William C; Hecht-Nielsen, Robert

    2011-06-01

    Multilayer perceptron networks whose outputs consist of affine combinations of hidden units using the tanh activation function are universal function approximators and are used for regression, typically by reducing the MSE with backpropagation. We present a neural network weight learning algorithm that directly positions the hidden units within input space by numerically analyzing the curvature of the output surface. Our results show that under some sampling requirements, this method can reliably recover the parameters of a neural network used to generate a data set. PMID:21377326

  7. Development of programmable artificial neural networks

    Science.gov (United States)

    Meade, Andrew J.

    1993-01-01

    Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed to mate the adaptability of the ANN with the speed and precision of the digital computer. This method was successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.

  8. On Bootstrap Percolation in Living Neural Networks

    CERN Document Server

    Amini, Hamed

    2009-01-01

    Recent experimental studies of living neural networks reveal that their global activation induced by electrical stimulation can be explained using the concept of bootstrap percolation on a directed random network. The experiment consists in activating externally an initial random fraction of the neurons and observe the process of firing until its equilibrium. The final portion of neurons that are active depends in a non linear way on the initial fraction. The main result of this paper is a theorem which enables us to find the asymptotic of final proportion of the fired neurons in the case of random directed graphs with given node degrees as the model for interacting network. This gives a rigorous mathematical proof of a phenomena observed by physicists in neural networks.

  9. Advances in Artificial Neural Networks – Methodological Development and Application

    OpenAIRE

    Yanbo Huang

    2009-01-01

    Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a back...

  10. Neural Networks for Wordform Recognition

    OpenAIRE

    Eineborg, Martin; Gambäck, Björn

    1994-01-01

    The paper outlines a method for automatic lexical acquisition using three-layered back-propagation networks. Several experiments have been carried out where the performance of different network architectures have been compared to each other on two tasks: overall part-of-speech (noun, adjective or verb) classification and classification by a set of 13 possible output categories. The best results for the simple task were obtained by networks consisting of 204-212 input neurons...

  11. Simplified Neural Network Design for Hand Written Digit Recognition

    OpenAIRE

    Muhammad Zubair Asghar; Hussain Ahmad; Shakeel Ahmad; Sheikh Muhammad Saqib; Bashir Ahmad; Muhammad Junaid Asghar

    2011-01-01

    Neural Network is abstraction of the central nervous system and works as parallel processing system. Optimization, image processing, Diagnosis and many other applications are made very simple through neural networks, which are difficult and time consuming when conventional methods are used for their implementation. Neural Network is the simplified version of human brain. Like human brain, neural networks also exhibit efficient performance on perceptive tasks like recognition of visual images ...

  12. Runoff Modelling in Urban Storm Drainage by Neural Networks

    DEFF Research Database (Denmark)

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

    A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural net...... knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model....

  13. Remote Sensing Image Segmentation with Probabilistic Neural Networks

    Institute of Scientific and Technical Information of China (English)

    LIU Gang

    2005-01-01

    This paper focuses on the image segmentation with probabilistic neural networks (PNNs). Back propagation neural networks (BpNNs) and multi perceptron neural networks (MLPs) are also considered in this study. Especially, this paper investigates the implementation of PNNs in image segmentation and optimal processing of image segmentation with a PNN. The comparison between image segmentations with PNNs and with other neural networks is given. The experimental results show that PNNs can be successfully applied to image segmentation for good results.

  14. Performance Comparison of Neural Networks for HRTFs Approximation

    Institute of Scientific and Technical Information of China (English)

    2000-01-01

    In order to approach to head-related transfer functions (HRTFs), this paper employs and compares three kinds of one-input neural network models, namely, multi-layer perceptron (MLP) networks, radial basis function (RBF) networks and wavelet neural networks (WNN) so as to select the best network model for further HRTFs approximation. Experimental results demonstrate that wavelet neural networks are more efficient and useful.

  15. Forecasting Runoff with Artificial Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Neruda, M.; Neruda, Roman; Kudová, Petra

    Paris : UNESCO, 2005 - (Maraga, F.), s. 65-69 [ERB 2004. Euromediterranean Network of Experimental and Representative Basins /10./. Turin (IT), 13.10.2004-17.10.2004] R&D Projects: GA ČR(CZ) GA201/02/0428 Institutional research plan: CEZ:AV0Z10300504 Keywords : artificial neural network s * rainfall-runoff modelling * multilayer perceptron * Radial Basis Functions (RBF) Subject RIV: BA - General Mathematics

  16. Local learning algorithm for optical neural networks

    OpenAIRE

    QIAO, YONG; Psaltis, Demetri

    1992-01-01

    An anti-Hebbian local learning algorithm for two-layer optical neural networks is introduced. With this learning rule, the weight update for a certain connection depends only on the input and output of that connection and a global, scalar error signal. Therefore the backpropagation of error signals through the network, as required by the commonly used back error propagation algorithm, is avoided. It still guarantees, however, that the synaptic weights are updated in the error descent directio...

  17. Applications of Neural Networks in Spinning Prediction

    Institute of Scientific and Technical Information of China (English)

    程文红; 陆凯

    2003-01-01

    The neural network spinning prediction model (BP and RBF Networks) trained by data from the mill can predict yarn qualities and spinning performance. The input parameters of the model are as follows: yarn count, diameter, hauteur, bundle strength, spinning draft, spinning speed, traveler number and twist.And the output parameters are: yarn evenness, thin places, tenacity and elongation, ends-down.Predicting results match the testing data well.

  18. Auto-associative nanoelectronic neural network

    International Nuclear Information System (INIS)

    In this paper, an auto-associative neural network using single-electron tunneling (SET) devices is proposed and simulated at low temperature. The nanoelectronic auto-associative network is able to converge to a stable state, previously stored during training. The recognition of the pattern involves decreasing the energy of the input state until it achieves a point of local minimum energy, which corresponds to one of the stored patterns

  19. Weighted Learning for Feedforward Neural Networks

    Institute of Scientific and Technical Information of China (English)

    Rong-Fang Xu; Thao-Tsen Chen; Shie-Jue Lee

    2014-01-01

    ⎯In this paper, we propose two weighted learning methods for the construction of single hidden layer feedforward neural networks. Both methods incorporate weighted least squares. Our idea is to allow the training instances nearer to the query to offer bigger contributions to the estimated output. By minimizing the weighted mean square error function, optimal networks can be obtained. The results of a number of experiments demonstrate the effectiveness of our proposed methods.

  20. Auto-associative nanoelectronic neural network

    Energy Technology Data Exchange (ETDEWEB)

    Nogueira, C. P. S. M.; Guimarães, J. G. [Departamento de Engenharia Elétrica - Laboratório de Dispositivos e Circuito Integrado, Universidade de Brasília, CP 4386, CEP 70904-970 Brasília DF (Brazil)

    2014-05-15

    In this paper, an auto-associative neural network using single-electron tunneling (SET) devices is proposed and simulated at low temperature. The nanoelectronic auto-associative network is able to converge to a stable state, previously stored during training. The recognition of the pattern involves decreasing the energy of the input state until it achieves a point of local minimum energy, which corresponds to one of the stored patterns.

  1. Multilingual Text Detection with Nonlinear Neural Network

    OpenAIRE

    Lin Li; Shengsheng Yu; Luo Zhong; Xiaozhen Li

    2015-01-01

    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 th...

  2. Neural Networks as Nonlinear Approximators

    Czech Academy of Sciences Publication Activity Database

    Kůrková, Věra

    ICSC, 2000 - (Bothe, H.; Rojas, R.), s. 29-35 ISBN 3-906454-21-5. [NC'2000. ICSC Symposium on Neural Computation /2./. Berlin (DE), 23.05.2000-26.05.2000] R&D Projects: GA ČR GA201/99/0092; GA ČR GA201/00/1489 Institutional research plan: AV0Z1030915 Subject RIV: BA - General Mathematics

  3. Localizing Tortoise Nests by Neural Networks.

    Directory of Open Access Journals (Sweden)

    Roberto Barbuti

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

  4. Psychometric Measurement Models and Artificial Neural Networks

    Science.gov (United States)

    Sese, Albert; Palmer, Alfonso L.; Montano, Juan J.

    2004-01-01

    The study of measurement models in psychometrics by means of dimensionality reduction techniques such as Principal Components Analysis (PCA) is a very common practice. In recent times, an upsurge of interest in the study of artificial neural networks apt to computing a principal component extraction has been observed. Despite this interest, the…

  5. Neural Network Output Optimization Using Interval Analysis

    NARCIS (Netherlands)

    De Weerdt, E.; Chu, Q.P.; Mulder, J.A.

    2009-01-01

    The problem of output optimization within a specified input space of neural networks (NNs) with fixed weights is discussed in this paper. The problem is (highly) nonlinear when nonlinear activation functions are used. This global optimization problem is encountered in the reinforcement learning (RL)

  6. Artificial neural networks in neutron dosimetry

    Energy Technology Data Exchange (ETDEWEB)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A. [Unidades Academicas de Estudios Nucleares, UAZ, A.P. 336, 98000 Zacatecas (Mexico); Gallego, E.; Lorente, A. [Depto. de Ingenieria Nuclear, Universidad Politecnica de Madrid, (Spain)

    2005-07-01

    An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the {chi}{sup 2}- test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  7. NEURAL NETWORK APPROACH FOR EYE DETECTION

    Directory of Open Access Journals (Sweden)

    Vijayalaxmi

    2012-05-01

    Full Text Available Driving support systems, such as car navigation systems are becoming common and they support driver in several aspects. Non-intrusive method of detecting Fatigue and drowsiness based on eye-blink count and eye directed instruction controlhelps the driver to prevent from collision caused by drowsy driving. Eye detection and tracking under various conditions such as illumination, background, face alignment and facial expression makes the problem complex.Neural Network based algorithm is proposed in this paper to detect the eyes efficiently. In the proposed algorithm, first the neural Network is trained to reject the non-eye regionbased on images with features of eyes and the images with features of non-eye using Gabor filter and Support Vector Machines to reduce the dimension and classify efficiently. In the algorithm, first the face is segmented using L*a*btransform color space, then eyes are detected using HSV and Neural Network approach. The algorithm is tested on nearly 100 images of different persons under different conditions and the results are satisfactory with success rate of 98%.The Neural Network is trained with 50 non-eye images and 50 eye images with different angles using Gabor filter. This paper is a part of research work on “Development of Non-Intrusive system for realtime Monitoring and Prediction of Driver Fatigue and drowsiness” project sponsored by Department of Science & Technology, Govt. of India, New Delhi at Vignan Institute of Technology and Sciences, Vignan Hills, Hyderabad.

  8. Convolutional Neural Networks for SAR Image Segmentation

    DEFF Research Database (Denmark)

    Malmgren-Hansen, David; Nobel-Jørgensen, Morten

    2015-01-01

    Segmentation of Synthetic Aperture Radar (SAR) images has several uses, but it is a difficult task due to a number of properties related to SAR images. In this article we show how Convolutional Neural Networks (CNNs) can easily be trained for SAR image segmentation with good results. Besides...

  9. A Modified Algorithm for Feedforward Neural Networks

    Institute of Scientific and Technical Information of China (English)

    夏战国; 管红杰; 李政伟; 孟斌

    2002-01-01

    As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. And the simulation result illustrate the modified algorithm is more effective and practicable.

  10. Advanced Neural Network Applied In Engineering Science

    Directory of Open Access Journals (Sweden)

    Nikita Patel*

    2014-11-01

    Full Text Available The basic idea behind a neural network is to simulate (copy in a simplified but reasonably faithful way lots of densely interconnected brain cells inside a computer so you can get it to learn things, recognize patterns, and make decisions in a humanlike way. The amazing thing about a neural network is that you don't have to program it to learn explicitly: it learns all by itself, just like a brain! But it isn't a brain. It's important to note that neural networks are (generally software simulations: they're made by programming very ordinary computers, working in a very traditional fashion with their ordinary transistors and serially connected logic gates, to behave as though they're built from billions of highly interconnected brain cells working in parallel. This paper is to propose that a neural network applied in engineering science that how a robots that can see, feel, and predict the world around them, improved stock prediction, common usage of self-driving car and much more!

  11. Nonlinear Time Series Analysis via Neural Networks

    Science.gov (United States)

    Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin

    This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.

  12. Additive Feed Forward Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1999-01-01

    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...

  13. Strenght and Weakness of Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Šebesta, Václav

    Prague : EuroMISE Center of Charles University, 1994 - (Bemmel van, J.; Zvárová, J.). s. 40 [EuroMISE - International Working Conference. 01.06.1994-05.06.1994, Harrachov] R&D Projects: GA ČR GA101/93/0430 Keywords : neural networks

  14. Affinely Recursive Functions and Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Kůrková, Věra; Kainen, P.C.

    Atlanta : Georgia Institute of Technology, 1994 - ( Ames , W.), s. 776-779 [IMACS World Congress /14./. Atlanta (US), 11.07.1994-15.07.1994] R&D Projects: GA AV ČR IA23057; GA ČR GA201/93/0427 Keywords : neural networks * affinely recursive functions

  15. Localizing Tortoise Nests by Neural Networks.

    Science.gov (United States)

    Barbuti, Roberto; Chessa, Stefano; Micheli, Alessio; Pucci, Rita

    2016-01-01

    The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. PMID:26985660

  16. Energy Complexity of Recurrent Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Šíma, Jiří

    2014-01-01

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

  17. Empirical generalization assessment of neural network models

    DEFF Research Database (Denmark)

    Larsen, Jan; Hansen, Lars Kai

    1995-01-01

    This paper addresses the assessment of generalization performance of neural network models by use of empirical techniques. We suggest to use the cross-validation scheme combined with a resampling technique to obtain an estimate of the generalization performance distribution of a specific model...

  18. Visualization of neural networks using saliency maps

    DEFF Research Database (Denmark)

    Mørch, Niels J.S.; Kjems, Ulrik; Hansen, Lars Kai;

    1995-01-01

    The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations are...

  19. Neural Networks for protein Structure Prediction

    DEFF Research Database (Denmark)

    Bohr, Henrik

    1998-01-01

    This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones, is...

  20. Vibration monitoring with artificial neural networks

    International Nuclear Information System (INIS)

    Vibration monitoring of components in nuclear power plants has been used for a number of years. This technique involves the analysis of vibration data coming from vital components of the plant to detect features which reflect the operational state of machinery. The analysis leads to the identification of potential failures and their causes, and makes it possible to perform efficient preventive maintenance. Earlydetection is important because it can decrease the probability of catastrophic failures, reduce forced outgage, maximize utilization of available assets, increase the life of the plant, and reduce maintenance costs. This paper documents our work on the design of a vibration monitoring methodology based on neural network technology. This technology provides an attractive complement to traditional vibration analysis because of the potential of neural network to operate in real-time mode and to handle data which may be distorted or noisy. Our efforts have been concentrated on the analysis and classification of vibration signatures collected from operating machinery. Two neural networks algorithms were used in our project: the Recirculation algorithm for data compression and the Backpropagation algorithm to perform the actual classification of the patterns. Although this project is in the early stages of development it indicates that neural networks may provide a viable methodology for monitoring and diagnostics of vibrating components. Our results to date are very encouraging

  1. Density functional and neural network analysis

    DEFF Research Database (Denmark)

    Jalkanen, K. J.; Suhai, S.; Bohr, Henrik

    dichroism (VCD) intensities. The large changes due to hydration on the structures, relative stability of conformers, and in the VA and VCD spectra observed experimentally are reproduced by the DFT calculations. Furthermore a neural network was constructed for reproducing the inverse scattering data (infer...

  2. Applying Artificial Neural Networks for Face Recognition

    Directory of Open Access Journals (Sweden)

    Thai Hoang Le

    2011-01-01

    Full Text Available This paper introduces some novel models for all steps of a face recognition system. In the step of face detection, we propose a hybrid model combining AdaBoost and Artificial Neural Network (ABANN to solve the process efficiently. In the next step, labeled faces detected by ABANN will be aligned by Active Shape Model and Multi Layer Perceptron. In this alignment step, we propose a new 2D local texture model based on Multi Layer Perceptron. The classifier of the model significantly improves the accuracy and the robustness of local searching on faces with expression variation and ambiguous contours. In the feature extraction step, we describe a methodology for improving the efficiency by the association of two methods: geometric feature based method and Independent Component Analysis method. In the face matching step, we apply a model combining many Neural Networks for matching geometric features of human face. The model links many Neural Networks together, so we call it Multi Artificial Neural Network. MIT + CMU database is used for evaluating our proposed methods for face detection and alignment. Finally, the experimental results of all steps on CallTech database show the feasibility of our proposed model.

  3. Mobile robot motion planner via neural network

    Czech Academy of Sciences Publication Activity Database

    Krejsa, Jiří; Věchet, Stanislav

    Prague: Institute of Thermomechanics AS CR, v. v. i., 2011 - (Fuis, V.), s. 327-330 ISBN 978-80-87012-33-8. [Engineering Mechanics 2011 /17./. Svratka (CZ), 09.05.2011-12.05.2011] Institutional research plan: CEZ:AV0Z20760514 Keywords : mobile robot * motion planning * neural network Subject RIV: JD - Computer Applications, Robot ics

  4. Towards semen quality assessment using neural networks

    DEFF Research Database (Denmark)

    Linneberg, Christian; Salamon, P.; Svarer, C.;

    1994-01-01

    The paper presents the methodology and results from a neural net based classification of human sperm head morphology. The methodology uses a preprocessing scheme in which invariant Fourier descriptors are lumped into “energy” bands. The resulting networks are pruned using optimal brain damage...

  5. Artificial neural networks in neutron dosimetry

    International Nuclear Information System (INIS)

    An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the χ2- test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  6. Neural network application to diesel generator diagnostics

    International Nuclear Information System (INIS)

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

  7. Combining neural networks for protein secondary structure prediction

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1995-01-01

    In this paper structured neural networks are applied to the problem of predicting the secondary structure of proteins. A hierarchical approach is used where specialized neural networks are designed for each structural class and then combined using another neural network. The submodels are designe...... is better than most secondary structure prediction methods based on single sequences even though this model contains much fewer parameters...

  8. Self-Organizing Multilayered Neural Networks of Optimal Complexity

    OpenAIRE

    Schetinin, V.

    2005-01-01

    The principles of self-organizing the neural networks of optimal complexity is considered under the unrepresentative learning set. The method of self-organizing the multi-layered neural networks is offered and used to train the logical neural networks which were applied to the medical diagnostics.

  9. A Direct Feedback Control Based on Fuzzy Recurrent Neural Network

    Institute of Scientific and Technical Information of China (English)

    李明; 马小平

    2002-01-01

    A direct feedback control system based on fuzzy-recurrent neural network is proposed, and a method of training weights of fuzzy-recurrent neural network was designed by applying modified contract mapping genetic algorithm. Computer simul ation results indicate that fuzzy-recurrent neural network controller has perfect dynamic and static performances .

  10. SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK

    Institute of Scientific and Technical Information of China (English)

    2003-01-01

    For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.

  11. A Fuzzy Neural Network for Fault Pattern Recognition

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    This paper combines fuzzy set theory with AR T neural network, and demonstrates some important properties of the fuzzy ART neural network algorithm. The results from application on a ball bearing diagnosis indicate that a fuzzy ART neural network has an effect of fast stable recognition for fuzzy patterns.

  12. A brief review of feed-forward neural networks

    OpenAIRE

    SAZLI, Murat Hüsnü

    2006-01-01

    Artificial neural networks, or shortly neural networks, find applications in a very wide spectrum. In this paper, following a brief presentation of the basic aspects of feed-forward neural networks, their mostly used learning/training algorithm, the so-called back-propagation algorithm, have been described.

  13. Recognition of Continuous Digits by Quantum Neural Networks

    Institute of Scientific and Technical Information of China (English)

    2003-01-01

    This paper describes a new kind of neural network-Quantum Neural Network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15 percent error reduction is achieved on a speaker-independent continuous digits recognition task compared with BP networks.

  14. Chaotic time series prediction using artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Bartlett, E.B.

    1991-01-01

    This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.

  15. Chaotic time series prediction using artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Bartlett, E.B.

    1991-12-31

    This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.

  16. Quantum boolean functions

    OpenAIRE

    Montanaro, Ashley; Osborne, Tobias J.

    2008-01-01

    In this paper we introduce the study of quantum boolean functions, which are unitary operators f whose square is the identity: f^2 = I. We describe several generalisations of well-known results in the theory of boolean functions, including quantum property testing; a quantum version of the Goldreich-Levin algorithm for finding the large Fourier coefficients of boolean functions; and two quantum versions of a theorem of Friedgut, Kalai and Naor on the Fourier spectra of boolean functions. In o...

  17. Boolean reasoning the logic of boolean equations

    CERN Document Server

    Brown, Frank Markham

    2012-01-01

    A systematic treatment of Boolean reasoning, this concise, newly revised edition combines the works of early logicians with recent investigations, including previously unpublished research results. Brown begins with an overview of elementary mathematical concepts and outlines the theory of Boolean algebras. Two concluding chapters deal with applications. 1990 edition.

  18. From Designing A Single Neural Network to Designing Neural Network Ensembles

    Institute of Scientific and Technical Information of China (English)

    Liu Yong; Zou Xiu-fer

    2003-01-01

    This paper introduces supervised learning model,and surveys related research work. The paper is organised as follows. A supervised learning model is firstly described. The bias variance trade-off is then discussed for the supervised learning model. Based on the bias variance trade-off, both the single neural network approaches and the neural network en semble approaches are overviewed, and problems with the existing approaches are indicated. Finally, the paper concludes with specifying potential future research directions.

  19. A Fuzzy Quantum Neural Network and Its Application in Pattern Recognition

    Institute of Scientific and Technical Information of China (English)

    MIAOFuyou; XIONGYan; CHENHuanhuan; WANGXingfu

    2005-01-01

    This paper proposes a fuzzy quantum neural network model combining quantum neural network and fuzzy logic, which applies the fuzzy logic to design the collapse rules of the quantum neural network, and solves the character recognition problem. Theoretical analysis and experimental results show that fuzzy quantum neural network improves recognizing veracity than the traditional neural network and quantum neural network.

  20. Boolean Expression Diagrams

    DEFF Research Database (Denmark)

    Andersen, Henrik Reif; Hulgaard, Henrik

    2002-01-01

    This paper presents a new data structure called boolean expression diagrams (BEDs) for representing and manipulating Boolean functions. BEDs are a generalization of binary decision diagrams (BDDs) which can represent any Boolean circuit in linear space. Two algorithms are described for transforming...

  1. 布尔表达式的化简与并行排序网络验证%Boolean expression simplification and parallel sort network validation

    Institute of Scientific and Technical Information of China (English)

    王德才; 徐建国; 吴哲辉; 罗永亮; 王传民

    2009-01-01

    To design an effective tool that can be used to verify the correctness of a parallel sorting network, a Boolean expression sim-plification algorithm based on the [0,1] theory and Boolean function of the characteristics and the nature is put forward, based on this algorithm a validation tool is designed. The characteristics and the nature of [0,1] theory and Boolean function are discussed and the natures that are helpful to simplify of the operation are pointed out. The tool can be used for the design of parallel sorting networks based on the parameters of the network graphics, and it can automatically generate the Boolean expressions and simplify it. The tool's output will be helpful to analyze the network, and it can also be used to design and optimize the sort network. Finally, the validity of the tool is demonstrated by the application.%为设计出能够验证并行排序网络正确性的有效工具,根据[0,1]原理和布尔函数的特点和性质,提出一种布尔表达式的化简算法,并根据此算法设计出验证工具.对[0,1]原理和布尔函数的特点和性质进行了讨论,指出有利于化简操作的性质.设计出的工具能够根据并行排序网络的参数显示网络图形、自动生成布尔表达式并实现化简验证,工具的输出有利于对排序网络的分析,也可以用于辅助排序网络的设计和优化.实验结果表明了该工具的有效性.

  2. Neural Networks for Evolutionary Robotics

    Czech Academy of Sciences Publication Activity Database

    Slušný, Stanislav

    Praha : Ústav informatiky AV ČR, v. v. i. & MATFYZPRESS, 2007 - (Hakl, F.), s. 87-93 ISBN 978-80-7378-019-7. [Doktorandské dny '07 Ústavu informatiky AV ČR, v. v. i.. Malá Úpa (CZ), 17.09.2007-19.09.2007] R&D Projects: GA ČR(CZ) GD201/05/H014 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural neworks * robotics * genetics algorithms

  3. Neural Networks for Evolutionary Robotics

    Czech Academy of Sciences Publication Activity Database

    Slušný, Stanislav

    Praha: Ústav informatiky AV ČR, v. v. i. & MATFYZPRESS, 2007 - (Hakl, F.), s. 87-93 ISBN 978-80-7378-019-7. [Doktorandské dny '07 Ústavu informatiky AV ČR, v. v. i.. Malá Úpa (CZ), 17.09.2007-19.09.2007] R&D Projects: GA ČR(CZ) GD201/05/H014 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural neworks * robotics * genetics algorithms

  4. Two Expectation-Maximization Algorithms for Boolean Factor Analysis

    Czech Academy of Sciences Publication Activity Database

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

    2014-01-01

    Roč. 130, 23 April (2014), s. 83-97. ISSN 0925-2312 R&D Projects: GA ČR GAP202/10/0262 Grant ostatní: GA MŠk(CZ) ED1.1.00/02.0070; GA MŠk(CZ) EE.2.3.20.0073 Institutional research plan: CEZ:AV0Z10300504 Keywords : Boolean Factor analysis * Binary Matrix factorization * Neural networks * Binary data model * Dimension reduction * Bars problem Subject RIV: IN - Informatics, Computer Science Impact factor: 2.083, year: 2014

  5. Controllability and observability of Boolean control networks%布尔控制网络的能控性与能观性

    Institute of Scientific and Technical Information of China (English)

    李志强; 宋金利

    2013-01-01

    Using the semi-tensor product,we convert the Boolean control network to its algebraic form.From the structure matrix of Boolean control network,the controllability and observability of the Boolean control network are discussed.A novel necessary and sufficient condition for controllability,which improves the recent results,is given.The new controllability condition eliminates the redundant computation of controllability matrix.The highest power of matrix is reduced from 2m+n to 2 n.Also,a sufficient condition for observability is obtained,which can be computed easily.A numerical example is presented to show the applicability of our controllability and observability condition.%利用矩阵的半张量积,布尔控制网络被转化为离散时间系统.本文从离散时间系统的结构矩阵出发,讨论了逻辑控制系统的能控能观性条件,得到了一个新的能控性条件.新的条件简化了原有能控性矩阵的计算复杂性,矩阵的最高阶数由原来的2m+n降到了2n.另外,还得到了检验布尔控制网络能观性的条件.与原有条件相比,新的条件更容易计算检验.最后,给出一个实例,检验给出的能控能观性判断条件的正确性.

  6. Genetic optimization of neural network architecture

    International Nuclear Information System (INIS)

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

  7. Color control of printers by neural networks

    Science.gov (United States)

    Tominaga, Shoji

    1998-07-01

    A method is proposed for solving the mapping problem from the 3D color space to the 4D CMYK space of printer ink signals by means of a neural network. The CIE-L*a*b* color system is used as the device-independent color space. The color reproduction problem is considered as the problem of controlling an unknown static system with four inputs and three outputs. A controller determines the CMYK signals necessary to produce the desired L*a*b* values with a given printer. Our solution method for this control problem is based on a two-phase procedure which eliminates the need for UCR and GCR. The first phase determines a neural network as a model of the given printer, and the second phase determines the combined neural network system by combining the printer model and the controller in such a way that it represents an identity mapping in the L*a*b* color space. Then the network of the controller part realizes the mapping from the L*a*b* space to the CMYK space. Practical algorithms are presented in the form of multilayer feedforward networks. The feasibility of the proposed method is shown in experiments using a dye sublimation printer and an ink jet printer.

  8. a Heterosynaptic Learning Rule for Neural Networks

    Science.gov (United States)

    Emmert-Streib, Frank

    In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.

  9. 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.

  10. Neural network construction via back-propagation

    International Nuclear Information System (INIS)

    A method is presented that combines back-propagation with multi-layer neural network construction. Back-propagation is used not only to adjust the weights but also the signal functions. Going from one network to an equivalent one that has additional linear units, the non-linearity of these units and thus their effective presence is then introduced via back-propagation (weight-splitting). The back-propagated error causes the network to include new units in order to minimize the error function. We also show how this formalism allows to escape local minima

  11. Computationally Efficient Neural Network Intrusion Security Awareness

    Energy Technology Data Exchange (ETDEWEB)

    Todd Vollmer; Milos Manic

    2009-08-01

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

  12. 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.

  13. Distribution network planning algorithm based on Hopfield neural network

    Institute of Scientific and Technical Information of China (English)

    GAO Wei-xin; LUO Xian-jue

    2005-01-01

    This paper presents a new algorithm based on Hopfield neural network to find the optimal solution for an electric distribution network. This algorithm transforms the distribution power network-planning problem into a directed graph-planning problem. The Hopfield neural network is designed to decide the in-degree of each node and is in combined application with an energy function. The new algorithm doesn't need to code city streets and normalize data, so the program is easier to be realized. A case study applying the method to a district of 29 street proved that an optimal solution for the planning of such a power system could be obtained by only 26 iterations. The energy function and algorithm developed in this work have the following advantages over many existing algorithms for electric distribution network planning: fast convergence and unnecessary to code all possible lines.

  14. Boosted Neural Networks in Evolutionary Computation

    Czech Academy of Sciences Publication Activity Database

    Holeňa, Martin; Linke, D.; Steinfeldt, N.

    Berlin : Springer, 2009 - (Leung, C.; Lee, M.; Chan, J.), s. 131-140 ISBN 978-3-642-10682-8. - (Lecture Notes in Computer Science. 5864). [ICONIP 2009. International Conference on Neural Information Processing /16./. Bangkok (TH), 01.12.2009-05.12.2009] R&D Projects: GA ČR GA201/08/0802; GA ČR GEICC/08/E018 Institutional research plan: CEZ:AV0Z10300504 Keywords : evolutionary algorithms * empirical objective functions * surrogate modelling * surrogate modelling * artificial neural network s * boosting Subject RIV: IN - Informatics, Computer Science

  15. Fuzzy logic and neural networks basic concepts & application

    CERN Document Server

    Alavala, Chennakesava R

    2008-01-01

    About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank

  16. Boolean algebra essentials

    CERN Document Server

    Solomon, Alan D

    2012-01-01

    REA's Essentials provide quick and easy access to critical information in a variety of different fields, ranging from the most basic to the most advanced. As its name implies, these concise, comprehensive study guides summarize the essentials of the field covered. Essentials are helpful when preparing for exams, doing homework and will remain a lasting reference source for students, teachers, and professionals. Boolean Algebra includes set theory, sentential calculus, fundamental ideas of Boolean algebras, lattices, rings and Boolean algebras, the structure of a Boolean algebra, and Boolean

  17. Membership generation using multilayer neural network

    Science.gov (United States)

    Kim, Jaeseok

    1992-01-01

    There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.

  18. Clustering in mobile ad hoc network based on neural network

    Institute of Scientific and Technical Information of China (English)

    CHEN Ai-bin; CAI Zi-xing; HU De-wen

    2006-01-01

    An on-demand distributed clustering algorithm based on neural network was proposed. The system parameters and the combined weight for each node were computed, and cluster-heads were chosen using the weighted clustering algorithm, then a training set was created and a neural network was trained. In this algorithm, several system parameters were taken into account, such as the ideal node-degree, the transmission power, the mobility and the battery power of the nodes. The algorithm can be used directly to test whether a node is a cluster-head or not. Moreover, the clusters recreation can be speeded up.

  19. Computational capabilities of recurrent NARX neural networks.

    Science.gov (United States)

    Siegelmann, H T; Horne, B G; Giles, C L

    1997-01-01

    Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with eXogenous Inputs (NARX models), and are therefore called NARX networks. As opposed to other recurrent networks, NARX networks have a limited feedback which comes only from the output neuron rather than from hidden states. They are formalized by y(t)=Psi(u(t-n(u)), ..., u(t-1), u(t), y(t-n(y)), ..., y(t-1)) where u(t) and y(t) represent input and output of the network at time t, n(u) and n(y) are the input and output order, and the function Psi is the mapping performed by a Multilayer Perceptron. We constructively prove that the NARX networks with a finite number of parameters are computationally as strong as fully connected recurrent networks and thus Turing machines. We conclude that in theory one can use the NARX models, rather than conventional recurrent networks without any computational loss even though their feedback is limited. Furthermore, these results raise the issue of what amount of feedback or recurrence is necessary for any network to be Turing equivalent and what restrictions on feedback limit computational power. PMID:18255858

  20. The EEG signal prediction bz using neural network

    OpenAIRE

    Babušiak, B.; Mohylová, J.

    2008-01-01

    The neural network is computational model based on the features abstraction of biological neural systems. The neural networks have many ways of usage in technical field. They have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents or autonomous robots. In this paper is described usage of neural networks for ECG signal prediction. The ECG signal prediction can be used for automated detection of irregular heart...

  1. The EEG Signal Prediction by Using Neural Network

    OpenAIRE

    Branko Babusiak; Jitka Mohylova

    2008-01-01

    The neural network is computational model based on the features abstraction of biological neural systems. The neural networks have many ways of usage in technical field. They have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents or autonomous robots. In this paper is described usage of neural networks for ECG signal prediction. The ECG signal prediction can be used for  automated detection of irregular heartbeat – extr...

  2. Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents

    CERN Document Server

    Sher, Gene I

    2011-01-01

    Though machine learning has been applied to the foreign exchange market for quiet some time now, and neural networks have been shown to yield good results, in modern approaches neural network systems are optimized through the traditional methods, and their input signals are vectors containing prices and other indicator elements. The aim of this paper is twofold, the presentation and testing of the application of topology and weight evolving artificial neural network (TWEANN) systems to automated currency trading, and the use of chart images as input to a geometrical regularity aware indirectly encoded neural network systems. This paper presents the benchmark results of neural network based automated currency trading systems evolved using TWEANNs, and compares the generalization capabilities of these direct encoded neural networks which use the standard price vector inputs, and the indirect (substrate) encoded neural networks which use chart images as input. The TWEANN algorithm used to evolve these currency t...

  3. Comparison of Control Approaches in Genetic Regulatory Networks by Using Stochastic Master Equation Models, Probabilistic Boolean Network Models and Differential Equation Models and Estimated Error Analyzes

    Science.gov (United States)

    Caglar, Mehmet Umut; Pal, Ranadip

    2011-03-01

    Central dogma of molecular biology states that ``information cannot be transferred back from protein to either protein or nucleic acid''. However, this assumption is not exactly correct in most of the cases. There are a lot of feedback loops and interactions between different levels of systems. These types of interactions are hard to analyze due to the lack of cell level data and probabilistic - nonlinear nature of interactions. Several models widely used to analyze and simulate these types of nonlinear interactions. Stochastic Master Equation (SME) models give probabilistic nature of the interactions in a detailed manner, with a high calculation cost. On the other hand Probabilistic Boolean Network (PBN) models give a coarse scale picture of the stochastic processes, with a less calculation cost. Differential Equation (DE) models give the time evolution of mean values of processes in a highly cost effective way. The understanding of the relations between the predictions of these models is important to understand the reliability of the simulations of genetic regulatory networks. In this work the success of the mapping between SME, PBN and DE models is analyzed and the accuracy and affectivity of the control policies generated by using PBN and DE models is compared.

  4. Functional expansion representations of artificial neural networks

    Science.gov (United States)

    Gray, W. Steven

    1992-01-01

    In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.

  5. Convolutional Neural Network Based dem Super Resolution

    Science.gov (United States)

    Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang

    2016-06-01

    DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.

  6. 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

  7. Artificial Neural Networks Applied To Landslide Hazard Assessment

    Science.gov (United States)

    Casagli, N.; Catani, F.; Ermini, L.

    Landslide hazard mapping is often performed through the identification and analysis of hillslope instability factors. GIS techniques are widely applied for the manage- ment of hillslope factors as thematic data rated by the attribution of scores based on the assumed role played by each factor controlling the development of a sliding pro- cess. Other more refined methods, based on the principle that the present and the past are keys to the future, have been also developed, thus allowing to perform less sub- jective analyses, in which landslide susceptibility is assessed by statistical relation- ships between the past landslides and the hillslope instability factors. The objective of this research is to define a method able to foresee landslide susceptibility through the application of Artificial Neural Networks (ANN). The Riomaggiore catchment, a sub-watershed of the Reno River basin located in the Northern Apennine at half way between Florence and Bologna, was chosen as the test site. The utilized ANN (AiNet 1.25) was trained by vector-based GIS data corresponding to five hillslope factors: a) geology, b) slope, c), curvature, d) land cover e) contributing area. The intersection between the hillslope factors, all ranked in nominal scales, singled out 3263 homoge- neous domains (Unique Condition Unit) containing unique combinations of hillslope factors. The final model was formed by vectors in which the hillslope factors, once organized as Boolean variables, are represented by 20 binary numbers. The compari- son between the most recent inventory of the landslides in the Riomaggiore catchment and the hazardous areas, as predicted by the ANN, showed very satisfactory results and allowed us to validate the methodology.

  8. Implementing Boolean Matrix Factorization

    Czech Academy of Sciences Publication Activity Database

    Neruda, Roman; Snášel, V.; Platoš, J.; Krömer, P.; Húsek, Dušan; Frolov, A. A.

    Vol. Part I. Berlin : Springer, 2008 - (Kůrková, V.; Neruda, R.; Koutník, J.), s. 543-552 ISBN 978-3-540-87535-2. - (Lecture Notes in Computer Science. 5163). [ICANN 2008. International Conference on Artificial Neural Network s /18./. Prague (CZ), 03.09.2008-06.09.2008] Institutional research plan: CEZ:AV0Z10300504 Keywords : factor analysis * genetic algorithm * neural network s Subject RIV: IN - Informatics, Computer Science

  9. A classifier neural network for rotordynamic systems

    Science.gov (United States)

    Ganesan, R.; Jionghua, Jin; Sankar, T. S.

    1995-07-01

    A feedforward backpropagation neural network is formed to identify the stability characteristic of a high speed rotordynamic system. The principal focus resides in accounting for the instability due to the bearing clearance effects. The abnormal operating condition of 'normal-loose' Coulomb rub, that arises in units supported by hydrodynamic bearings or rolling element bearings, is analysed in detail. The multiple-parameter stability problem is formulated and converted to a set of three-parameter algebraic inequality equations. These three parameters map the wider range of physical parameters of commonly-used rotordynamic systems into a narrow closed region, that is used in the supervised learning of the neural network. A binary-type state of the system is expressed through these inequalities that are deduced from the analytical simulation of the rotor system. Both the hidden layer as well as functional-link networks are formed and the superiority of the functional-link network is established. Considering the real time interpretation and control of the rotordynamic system, the network reliability and the learning time are used as the evaluation criteria to assess the superiority of the functional-link network. This functional-link network is further trained using the parameter values of selected rotor systems, and the classifier network is formed. The success rate of stability status identification is obtained to assess the potentials of this classifier network. The classifier network is shown that it can also be used, for control purposes, as an 'advisory' system that suggests the optimum way of parameter adjustment.

  10. Binary Factorization by Neural Autoassociators

    Czech Academy of Sciences Publication Activity Database

    Húsek, Dušan; Frolov, A. A.; Muraviev, I.; Řezanková, H.; Snášel, V.; Polyakov, P.Y.

    Zürich : ACTA Press, 2003 - (Hamza, M.), s. 649-653 ISBN 0-88986-390-3. ISSN 1482-7913. [IASTED International Conference /3./. Benalmadena (ES), 08.09.2003-10.09.2003] R&D Projects: GA MŠk LN00B096 Keywords : Boolean factorization * recurrent neural network s * single-step approximation Subject RIV: BD - Theory of Information

  11. Investigations into the relationship between feedback loops and functional importance of a signal transduction network based on Boolean network modeling

    OpenAIRE

    Cho Kwang-Hyun; Choi Sun; Kwon Yung-Keun

    2007-01-01

    Abstract Background A number of studies on biological networks have been carried out to unravel the topological characteristics that can explain the functional importance of network nodes. For instance, connectivity, clustering coefficient, and shortest path length were previously proposed for this purpose. However, there is still a pressing need to investigate another topological measure that can better describe the functional importance of network nodes. In this respect, we considered a fee...

  12. Classification of Epileptic EEG Signals using Time-Delay Neural Networks and Probabilistic Neural Networks

    Directory of Open Access Journals (Sweden)

    Ateke Goshvarpour

    2013-05-01

    Full Text Available The aim of this paper is to investigate the performance of time delay neural networks (TDNNs and the probabilistic neural networks (PNNs trained with nonlinear features (Lyapunov exponents and Entropy on electroencephalogram signals (EEG in a specific pathological state. For this purpose, two types of EEG signals (normal and partial epilepsy are analyzed. To evaluate the performance of the classifiers, mean square error (MSE and elapsed time of each classifier are examined. The results show that TDNN with 12 neurons in hidden layer result in a lower MSE with the training time of about 19.69 second. According to the results, when the sigma values are lower than 0.56, the best performance in the proposed probabilistic neural network structure is achieved. The results of present study show that applying the nonlinear features to train these networks can serve as useful tool in classifying of the EEG signals.

  13. Asymmetric continuous-time neural networks without local traps for solving constraint satisfaction problems.

    Directory of Open Access Journals (Sweden)

    Botond Molnár

    Full Text Available There has been a long history of using neural networks for combinatorial optimization and constraint satisfaction problems. Symmetric Hopfield networks and similar approaches use steepest descent dynamics, and they always converge to the closest local minimum of the energy landscape. For finding global minima additional parameter-sensitive techniques are used, such as classical simulated annealing or the so-called chaotic simulated annealing, which induces chaotic dynamics by addition of extra terms to the energy landscape. Here we show that asymmetric continuous-time neural networks can solve constraint satisfaction problems without getting trapped in non-solution attractors. We concentrate on a model solving Boolean satisfiability (k-SAT, which is a quintessential NP-complete problem. There is a one-to-one correspondence between the stable fixed points of the neural network and the k-SAT solutions and we present numerical evidence that limit cycles may also be avoided by appropriately choosing the parameters of the model. This optimal parameter region is fairly independent of the size and hardness of instances, this way parameters can be chosen independently of the properties of problems and no tuning is required during the dynamical process. The model is similar to cellular neural networks already used in CNN computers. On an analog device solving a SAT problem would take a single operation: the connection weights are determined by the k-SAT instance and starting from any initial condition the system searches until finding a solution. In this new approach transient chaotic behavior appears as a natural consequence of optimization hardness and not as an externally induced effect.

  14. Asymmetric continuous-time neural networks without local traps for solving constraint satisfaction problems.

    Science.gov (United States)

    Molnár, Botond; Ercsey-Ravasz, Mária

    2013-01-01

    There has been a long history of using neural networks for combinatorial optimization and constraint satisfaction problems. Symmetric Hopfield networks and similar approaches use steepest descent dynamics, and they always converge to the closest local minimum of the energy landscape. For finding global minima additional parameter-sensitive techniques are used, such as classical simulated annealing or the so-called chaotic simulated annealing, which induces chaotic dynamics by addition of extra terms to the energy landscape. Here we show that asymmetric continuous-time neural networks can solve constraint satisfaction problems without getting trapped in non-solution attractors. We concentrate on a model solving Boolean satisfiability (k-SAT), which is a quintessential NP-complete problem. There is a one-to-one correspondence between the stable fixed points of the neural network and the k-SAT solutions and we present numerical evidence that limit cycles may also be avoided by appropriately choosing the parameters of the model. This optimal parameter region is fairly independent of the size and hardness of instances, this way parameters can be chosen independently of the properties of problems and no tuning is required during the dynamical process. The model is similar to cellular neural networks already used in CNN computers. On an analog device solving a SAT problem would take a single operation: the connection weights are determined by the k-SAT instance and starting from any initial condition the system searches until finding a solution. In this new approach transient chaotic behavior appears as a natural consequence of optimization hardness and not as an externally induced effect. PMID:24066045

  15. Neural network for sonogram gap filling

    DEFF Research Database (Denmark)

    Klebæk, Henrik; Jensen, Jørgen Arendt; Hansen, Lars Kai

    1995-01-01

    In duplex imaging both an anatomical B-mode image and a sonogram are acquired, and the time for data acquisition is divided between the two images. This gives problems when rapid B-mode image display is needed, since there is not time for measuring the velocity data. Gaps then appear in the...... of the B-mode and sonogram pulses, and time must be shared between the two. Gaps will appear frequently in the sonogram since, e.g., half the time is spent on B-mode acquisition. The information in the gaps can be filled from the available information through interpolation. One possibility is to use...... a neural network for predicting mean frequency of the velocity signal and its variance. The neural network then predicts the evolution of the mean and variance in the gaps, and the sonogram and audio signal are reconstructed from these. The technique is applied on in-vivo data from the carotid...

  16. Automatic breast density classification using neural network

    International Nuclear Information System (INIS)

    According to studies, the risk of breast cancer directly associated with breast density. Many researches are done on automatic diagnosis of breast density using mammography. In the current study, artifacts of mammograms are removed by using image processing techniques and by using the method presented in this study, including the diagnosis of points of the pectoral muscle edges and estimating them using regression techniques, pectoral muscle is detected with high accuracy in mammography and breast tissue is fully automatically extracted. In order to classify mammography images into three categories: Fatty, Glandular, Dense, a feature based on difference of gray-levels of hard tissue and soft tissue in mammograms has been used addition to the statistical features and a neural network classifier with a hidden layer. Image database used in this research is the mini-MIAS database and the maximum accuracy of system in classifying images has been reported 97.66% with 8 hidden layers in neural network

  17. Neural network prediction of solar cycle 24

    Institute of Scientific and Technical Information of China (English)

    A. Ajabshirizadeh; N. Masoumzadeh Jouzdani; Shahram Abbassi

    2011-01-01

    The ability to predict the future behavior of solar activity has become extremely import due to its effect on the environment near the Earth. Predictions of both the amplitude and timing of the next solar cycle will assist in estimating the various consequences of space weather. The level of solar activity is usually expressed by international sunspot number (Rz). Several prediction techniques have been applied and have achieved varying degrees of success in the domain of solar activity prediction.We predict a solar index (Rz) in solar cycle 24 by using a neural network method. The neural network technique is used to analyze the time series of solar activity. According to our predictions of yearly sunspot number, the maximum of cycle 24 will occur in the year 2013 and will have an annual mean sunspot number of 65. Finally, we discuss our results in order to compare them with other suggested predictions.

  18. Hierarchical Neural Network Structures for Phoneme Recognition

    CERN Document Server

    Vasquez, Daniel; Minker, Wolfgang

    2013-01-01

    In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a  Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.

  19. Web Page Categorization Using Artificial Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    Web page categorization is one of the challenging tasks in the world of ever increasing web technologies. There are many ways of categorization of web pages based on different approach and features. This paper proposes a new dimension in the way of categorization of web pages using artificial neural network (ANN) through extracting the features automatically. Here eight major categories of web pages have been selected for categorization; these are business & economy, education, government, entertainment, sports, news & media, job search, and science. The whole process of the proposed system is done in three successive stages. In the first stage, the features are automatically extracted through analyzing the source of the web pages. The second stage includes fixing the input values of the neural network; all the values remain between 0 and 1. The variations in those values affect the output. Finally the third stage determines the class of a certain web page out of eight predefined classes. This stage i...

  20. Recurrent Bayesian Reasoning in Probabilistic Neural Networks

    Czech Academy of Sciences Publication Activity Database

    Grim, Jiří; Hora, Jan

    Vol. Part I. Berlin: Springer, 2007 - (Marques de Sá, J.; Alexandre, L.; Duch, W.; Mandic, D.), s. 129-138. (Lecture Notes in Computer Scinece. SL 1 - Theoretical Computer Science and General Issues. 4669). ISBN 3-540-74693-5. [International Conference on Artificial Neural Networks /17./. Porto (PT), 09.09.2007-13.09.2007] R&D Projects: GA MŠk 1M0572; GA ČR GA102/07/1594 EU Projects: European Commission(XE) 507752 - MUSCLE Grant ostatní: GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : neural networks * probabilistic approach * distribution mixtures Subject RIV: BD - Theory of Information

  1. Application of neural networks in space construction

    Science.gov (United States)

    Thilenius, Stephen C.; Barnes, Frank

    1990-01-01

    When trying to decide what task should be done by robots and what tasks should be done by humans with respect to space construction, there has been one decisive barrier which ultimately divides the tasks: can a computer do the job? Von Neumann type computers have great difficulty with problems that the human brain seems to do instantaneously and with little effort. Some of these problems are pattern recognition, speech recognition, content addressable memories, and command interpretation. In an attempt to simulate these talents of the human brain, much research was currently done into the operations and construction of artificial neural networks. The efficiency of the interface between man and machine, robots in particular, can therefore be greatly improved with the use of neural networks. For example, wouldn't it be easier to command a robot to 'fetch an object' rather then having to remotely control the entire operation with remote control?

  2. Development of Polymer Resins using Neural Networks

    Directory of Open Access Journals (Sweden)

    Fernandes Fabiano A. N.

    2002-01-01

    Full Text Available The development of polymer resins can benefit from the application of neural networks, using its great ability to correlate inputs and outputs. In this work we have developed a procedure that uses neural networks to correlate the end-user properties of a polymer with the polymerization reactor's operational condition that will produce that desired polymer. This procedure is aimed at speeding up the development of new resins and help finding the appropriate operational conditions to produce a given polymer resin; reducing experimentation, pilot plant tests and therefore time and money spent on development. The procedure shown in this paper can predict the reactor's operational condition with an error lower than 5%.

  3. Sensor Validation Using Auto associative Neural Network

    International Nuclear Information System (INIS)

    Sensor Validation Using Auto associative Neural Network. Sensor signal accuration plays a significant role in safety and operation of a nuclear reactor. These sensor performance could be decline even become totally fault when the reactor in operation. This paper demonstrates the application of auto associative neural network (AANN) to validate signals from various correlated sensor so that the sensor performance deterioration can be earlier detected. An AANN model produces predicted signal, which is used as a measured signal validator. The faulty of a sensor will not disturb the reactor operation since the predicted signal can be used as redundant signal and replace the faulty signal. This method is applied to a set of data from Borselle Nuclear Power Plant and corresponds to various operation modes. Result showed that the system could be used to detect 3% drift on one of the input channel. (author)

  4. Privacy-preserving backpropagation neural network learning.

    Science.gov (United States)

    Chen, Tingting; Zhong, Sheng

    2009-10-01

    With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets. PMID:19709975

  5. 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...

  6. Neural network correction of astrometric chromaticity

    CERN Document Server

    Gai, M

    2005-01-01

    In this paper we deal with the problem of chromaticity, i.e. apparent position variation of stellar images with their spectral distribution, using neural networks to analyse and process astronomical images. The goal is to remove this relevant source of systematic error in the data reduction of high precision astrometric experiments, like Gaia. This task can be accomplished thanks to the capability of neural networks to solve a nonlinear approximation problem, i.e. to construct an hypersurface that approximates a given set of scattered data couples. Images are encoded associating each of them with conveniently chosen moments, evaluated along the y axis. The technique proposed, in the current framework, reduces the initial chromaticity of few milliarcseconds to values of few microarcseconds.

  7. Artificial Neural Network for Displacement Vectors Determination

    Directory of Open Access Journals (Sweden)

    P. Bohmann

    1997-09-01

    Full Text Available An artificial neural network (NN for displacement vectors (DV determination is presented in this paper. DV are computed in areas which are essential for image analysis and computer vision, in areas where are edges, lines, corners etc. These special features are found by edges operators with the following filtration. The filtration is performed by a threshold function. The next step is DV computation by 2D Hamming artificial neural network. A method of DV computation is based on the full search block matching algorithms. The pre-processing (edges finding is the reason why the correlation function is very simple, the process of DV determination needs less computation and the structure of the NN is simpler.

  8. The principles of artificial neural network information processing

    International Nuclear Information System (INIS)

    In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as Perceptron, Back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally, the application of artificial neural network for Chinese Character Recognition is also given. (author)

  9. The principles of artificial neural network information processing

    International Nuclear Information System (INIS)

    In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as perception, back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally the application of artificial neural network for Chinese character recognition is also given. (author)

  10. A Bionic Neural Network for Fish-Robot Locomotion

    Institute of Scientific and Technical Information of China (English)

    Dai-bing Zhang; De-wen Hu; Lin-cheng Shen; Hai-bin Xie

    2006-01-01

    A bionic neural network for fish-robot locomotion is presented. The bionic neural network inspired from fish neural network consists of one high level controller and one chain of central pattern generators (CPGs). Each CPG contains a nonlinear neural Zhang oscillator which shows properties similar to sine-cosine model. Simulation results show that the bionic neural network presents a good performance in controlling the fish-robot to execute various motions such as startup,stop,forward swimming,backward swimming,turn right and turn left.

  11. Neural network error correction for solving coupled ordinary differential equations

    Science.gov (United States)

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

    1992-01-01

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

  12. Review: Competitive Learning Algorithm of Neural Network

    OpenAIRE

    Jithendra Singh Sengar; Niresh Sharma

    2011-01-01

    This paper deals mainly with the development of new learning algorithms and the study of the dynamics of neural networks. This survey paper will cover issues about the unsupervised competitive learning as well as some of its variances like hard competitive learning and soft competitive learning. After introducing of unsupervised learning algorithms, we will discuss the other competitive learning methods and motivations and goodness as well as the weakness of this model. Paper focuses on the e...

  13. Artificial Neural Networks, Symmetries and Differential Evolution

    OpenAIRE

    Urfalioglu, Onay; Arikan, Orhan

    2010-01-01

    Neuroevolution is an active and growing research field, especially in times of increasingly parallel computing architectures. Learning methods for Artificial Neural Networks (ANN) can be divided into two groups. Neuroevolution is mainly based on Monte-Carlo techniques and belongs to the group of global search methods, whereas other methods such as backpropagation belong to the group of local search methods. ANN's comprise important symmetry properties, which can influence Monte-Carlo methods....

  14. Lamarckian training of feedforward neural networks

    OpenAIRE

    Cortez, Paulo; Rocha, Miguel; Neves, José

    2001-01-01

    Living creatures improve their adaptation capabilities to a changing world by means of two orthogonal processes: evolution and lifetime learning. Within Artificial Intelligence, both mechanisms inspired the development of non-orthodox problem solving tools, namely Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). Several local search gradient-based methods have been developed for ANN training, with considerable success; however, in some situations, such pr...

  15. Improving Recurrent Neural Networks For Sequence Labelling

    OpenAIRE

    Dinarelli, Marco; Tellier, Isabelle

    2016-01-01

    In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNNs integrating improvements for sequence labeling, and we compare them to the more traditional Elman and Jordan RNNs. We compare all models, either traditional or new, on four distinct tasks of sequence labeling: two on Spoken Language Understanding (ATIS and MEDIA); and two of POS tagging for the French Treebank (FTB) and the Penn Treebank (PTB) corpora. The...

  16. RBF Neural Networks and Radial Fuzzy Systems

    Czech Academy of Sciences Publication Activity Database

    Coufal, David

    Cham: Springer, 2015 - (Iliadis, L.; Jayne, C.), s. 206-215. (Communications in Computer and Information Science. 517). ISBN 978-3-319-23981-1. ISSN 1865-0929. [EANN 2015. International Conference /16./. Rhodes (GR), 25.09.2015-28.09.2015] R&D Projects: GA MŠk(CZ) LD13002 Institutional support: RVO:67985807 Keywords : RBF neural networks * Radial fuzzy systems * Conjunctive and implicative rule base s Subject RIV: IN - Informatics, Computer Science

  17. Neural Network Learning as Approximate Optimization

    Czech Academy of Sciences Publication Activity Database

    Kůrková, Věra; Sanguineti, M.

    Wien : SpringerVerlag, 2003 - (Pearson, D.; Steele, N.; Albrecht, R.), s. 53-57 ISBN 3-211-00743-1. [ICANNGA'2003 /6./. Roanne (FR), 23.04.2003-25.04.2003] R&D Projects: GA ČR GA201/02/0428 Grant ostatní: IT-CZ Area MC6(XX) Project 22 Institutional research plan: AV0Z1030915 Keywords : neural network s * learning from data * approximate optimization Subject RIV: BA - General Mathematics

  18. Deep convolutional neural networks for pedestrian detection

    OpenAIRE

    Tomè, Denis; Monti, Federico; Baroffio, Luca; Bondi, Luca; Tagliasacchi, Marco; Tubaro, Stefano

    2015-01-01

    Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learning and in particular convolutional neural networks emerged as the state of the art in terms of accuracy for a number of computer vision tasks such as...

  19. Artificial Neural Networks for Pollution Forecast

    OpenAIRE

    Pasero, Eros; Mesin, Luca

    2010-01-01

    This chapter provides an introduction to non-linear methods for the prediction of the concentration of air pollutants. We focused on the selection of features and the modelling and processing techniques based on the theory of Artificial Neural Networks, using Multi Layer Perceptrons and Support Vector Machines. Joint measurements of meteorological data and pollutants concentrations is useful in order to increase the number of parameters to be studied for the construction of mathematical air q...

  20. 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...

  1. Context dependent learning in neural networks

    OpenAIRE

    Spreeuwers, L.J.; Zwaag, van der, Berend Jan; Heijden, van der, M.

    1995-01-01

    In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent informa...

  2. Sequence to Sequence Learning with Neural Networks

    OpenAIRE

    Sutskever, Ilya; Vinyals, Oriol; Le, Quoc V.

    2014-01-01

    Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensi...

  3. Optimizing and Contrasting Recurrent Neural Network Architectures

    OpenAIRE

    Krause, Ben

    2015-01-01

    Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization, a powerful second order optimization method that has shown promising results, but still does not enjoy widespread use. This algorithm was used to train to a number of RNN arch...

  4. Cells in Multidimensional Recurrent Neural Networks

    OpenAIRE

    Leifert, G.; Strauß, T.; Grüning, T; Labahn, R.

    2014-01-01

    The transcription of handwritten text on images is one task in machine learning and one solution to solve it is using multi-dimensional recurrent neural networks (MDRNN) with connectionist temporal classification (CTC). The RNNs can contain special units, the long short-term memory (LSTM) cells. They are able to learn long term dependencies but they get unstable when the dimension is chosen greater than one. We defined some useful and necessary properties for the one-dimensional LSTM cell and...

  5. Polarized DIS Structure Functions from Neural Networks

    International Nuclear Information System (INIS)

    We present a parametrization of polarized Deep-Inelastic-Scattering (DIS) structure functions based on Neural Networks. The parametrization provides a bias-free determination of the probability measure in the space of structure functions, which retains information on experimental errors and correlations. As an example we discuss the application of this method to the study of the structure function g1p(x,Q2)

  6. Prediction of metal corrosion by neural networks

    OpenAIRE

    Jančíková, Zora; Zimný, Ondřej; Koštial, Pavol

    2013-01-01

    The contribution deals with the use of artifi cial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are...

  7. Prediction of metal corrosion by neural networks

    OpenAIRE

    Jančíková, Z.; Zimný, O.; Koštial, P.

    2013-01-01

    The contribution deals with the use of artificial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are not known so...

  8. Applying neural networks to optimize instrumentation performance

    International Nuclear Information System (INIS)

    Well calibrated instrumentation is essential in providing meaningful information about the status of a plant. Signals from plant instrumentation frequently have inherent non-linearities, may be affected by environmental conditions and can therefore cause calibration difficulties for the people who maintain them. Two neural network approaches are described in this paper for improving the accuracy of a non-linear, temperature sensitive level probe ised in Expermental Breeder Reactor II (EBR-II) that was difficult to calibrate

  9. Turing Computation with Recurrent Artificial Neural Networks

    OpenAIRE

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

    2015-01-01

    We improve the results by Siegelmann & Sontag (1995) by providing a novel and parsimonious constructive mapping between Turing Machines and Recurrent Artificial Neural Networks, based on recent developments of Nonlinear Dynamical Automata. The architecture of the resulting R-ANNs is simple and elegant, stemming from its transparent relation with the underlying NDAs. These characteristics yield promise for developments in machine learning methods and symbolic computation with continuous time d...

  10. Web Page Categorization Using Artificial Neural Networks

    OpenAIRE

    S. M. Kamruzzaman

    2010-01-01

    Web page categorization is one of the challenging tasks in the world of ever increasing web technologies. There are many ways of categorization of web pages based on different approach and features. This paper proposes a new dimension in the way of categorization of web pages using artificial neural network (ANN) through extracting the features automatically. Here eight major categories of web pages have been selected for categorization; these are business & economy, education, government, en...

  11. Neural network with dynamically adaptable neurons

    Science.gov (United States)

    Tawel, Raoul (Inventor)

    1994-01-01

    This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.

  12. Analysis of SSR Using Artificial Neural Networks

    OpenAIRE

    Nagabhushana, BS; Chandrasekharaiah, HS

    1996-01-01

    Artificial neural networks (ANNs) are being advantageously applied to power system analysis problems. They possess the ability to establish complicated input-output mappings through a learning process, without any explicit programming. In this paper, an ANN based method for subsynchronous resonance (SSR) analysis is presented. The designed ANN outputs a measure of the possibility of the occurrence of SSR and is fully trained to accommodate the variations of power system parameters over the en...

  13. POWER SCALABLE IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORKS

    OpenAIRE

    Modi, Sankalp; Wilson, Peter; Brown, Andrew

    2005-01-01

    As the use of Artificial Neural Network(ANN) in mobile embedded devices gets more pervasive, power consumption of ANN hardware is becoming a major limiting factor. Although considerable research efforts are now directed towards low-power implementations of ANN, the issue of dynamic power scalability of the implemented design has been largely overlooked. In this paper, we discuss the motivation and basic principles for implementing power scaling in ANN Hardware. With the help of a simple examp...

  14. Practical introduction to artificial neural networks

    OpenAIRE

    Bougrain, Laurent

    2004-01-01

    What are they ? What for are they ? How to use them ? This article wants to answer these three fundamental questions about artificial neural networks that every engineer interested by this machine learning technique asks to oneself. We present the most useful architectures. We explain how to train them using a supervised or an unsupervised learning depending on the task we want to do : regression, discrimination or clustering. What kind of data can one use and how to prepare them ? Finally, w...

  15. Neural Networks with Complex and Quaternion Inputs

    OpenAIRE

    Rishiyur, Adityan

    2006-01-01

    This article investigates Kak neural networks, which can be instantaneously trained, for complex and quaternion inputs. The performance of the basic algorithm has been analyzed and shown how it provides a plausible model of human perception and understanding of images. The motivation for studying quaternion inputs is their use in representing spatial rotations that find applications in computer graphics, robotics, global navigation, computer vision and the spatial orientation of instruments. ...

  16. Feature Representation in Convolutional Neural Networks

    OpenAIRE

    Athiwaratkun, Ben; Kang, Keegan

    2015-01-01

    Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors. This paper aims to gain insight into the feature aspect of CNN and demonstrate other uses of CNN features. Our results show that CNN feature maps can be used with Random Forests and SVM to yield classification results that outperforms the original CNN. A CNN that is less t...

  17. Quantized Convolutional Neural Networks for Mobile Devices

    OpenAIRE

    Wu, Jiaxiang; Leng, Cong; Wang, Yuhang; Hu, Qinghao; Cheng, Jian

    2015-01-01

    Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter kernels in co...

  18. Vehicle Color Recognition using Convolutional Neural Network

    OpenAIRE

    Rachmadi, Reza Fuad; Purnama, I. Ketut Eddy

    2015-01-01

    Vehicle color information is one of the important elements in ITS (Intelligent Traffic System). In this paper, we present a vehicle color recognition method using convolutional neural network (CNN). Naturally, CNN is designed to learn classification method based on shape information, but we proved that CNN can also learn classification based on color distribution. In our method, we convert the input image to two different color spaces, HSV and CIE Lab, and run it to some CNN architecture. The...

  19. Neural Networks in Chemical Reaction Dynamics

    CERN Document Server

    Raff, Lionel; Hagan, Martin

    2011-01-01

    This monograph presents recent advances in neural network (NN) approaches and applications to chemical reaction dynamics. Topics covered include: (i) the development of ab initio potential-energy surfaces (PES) for complex multichannel systems using modified novelty sampling and feedforward NNs; (ii) methods for sampling the configuration space of critical importance, such as trajectory and novelty sampling methods and gradient fitting methods; (iii) parametrization of interatomic potential functions using a genetic algorithm accelerated with a NN; (iv) parametrization of analytic interatomic

  20. Classification of coffee using artificial neural network

    OpenAIRE

    Yip, DHF; Yu, WWH

    1996-01-01

    The paper presents a method for classifying coffees according to their scents using artificial neural network (ANN). The proposed method of uses genetic algorithm (GA) to determine the optimal parameters and topology of ANN. It uses adaptive backpropagation to accelerate the training process so that the entire optimization process can be achieved in an accelerated time. The optimized ANN has successfully classified the coffees using a relatively small set of training data. The performance of ...

  1. Differential Recurrent Neural Networks for Action Recognition

    OpenAIRE

    Veeriah, Vivek; Zhuang, Naifan; Qi, Guo-Jun

    2015-01-01

    The long short-term memory (LSTM) neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences. It has the potential to model any sequential time-series data, where the current hidden state has to be considered in the context of the past hidden states. This property makes LSTM an ideal choice to learn the complex dynamics of various actions. Unfortunately, the conventional LSTMs do not co...

  2. Pedestrian Detection Using Convolutional Neural Networks

    OpenAIRE

    Molin, David

    2015-01-01

    Pedestrian detection is an important field with applications in active safety systems for cars as well as autonomous driving. Since autonomous driving and active safety are becoming technically feasible now the interest for these applications has dramatically increased.The aim of this thesis is to investigate convolutional neural networks (CNN) for pedestrian detection. The reason for this is that CNN have recently beensuccessfully applied to several different computer vision problems. The ma...

  3. Comparison of Training Methods for Deep Neural Networks

    OpenAIRE

    Glauner, Patrick O.

    2015-01-01

    This report describes the difficulties of training neural networks and in particular deep neural networks. It then provides a literature review of training methods for deep neural networks, with a focus on pre-training. It focuses on Deep Belief Networks composed of Restricted Boltzmann Machines and Stacked Autoencoders and provides an outreach on further and alternative approaches. It also includes related practical recommendations from the literature on training them. In the second part, in...

  4. Artificial Neural Network Model for Predicting Compressive

    Directory of Open Access Journals (Sweden)

    Salim T. Yousif

    2013-05-01

    Full Text Available   Compressive strength of concrete is a commonly used criterion in evaluating concrete. Although testing of the compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. Therefore, strength estimation of concrete at early time is highly desirable. This study presents the effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions, maximum aggregate size (MAS, and slump of fresh concrete. Back-propagation neural networks model is successively developed, trained, and tested using actual data sets of concrete mix proportions gathered from literature.    The test of the model by un-used data within the range of input parameters shows that the maximum absolute error for model is about 20% and 88% of the output results has absolute errors less than 10%. The parametric study shows that water/cement ratio (w/c is the most significant factor  affecting the output of the model.     The results showed that neural networks has strong potential as a feasible tool for predicting compressive strength of concrete.

  5. Artificial neural network applications in ionospheric studies

    Directory of Open Access Journals (Sweden)

    L. R. Cander

    1998-06-01

    Full Text Available The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC. Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.

  6. Pattern recognition using asymmetric attractor neural networks

    Science.gov (United States)

    Jin, Tao; Zhao, Hong

    2005-12-01

    The asymmetric attractor neural networks designed by the Monte Carlo- (MC-) adaptation rule are shown to be promising candidates for pattern recognition. In such a neural network with relatively low symmetry, when the members of a set of template patterns are stored as fixed-point attractors, their attraction basins are shown to be isolated islands embedded in a “chaotic sea.” The sizes of these islands can be controlled by a single parameter. We show that these properties can be used for effective pattern recognition and rejection. In our method, the pattern to be identified is attracted to a template pattern or a chaotic attractor. If the difference between the pattern to be identified and the template pattern is smaller than a predescribed threshold, the pattern is attracted to the template pattern automatically and thus is identified as belonging to this template pattern. Otherwise, it wanders in a chaotic attractor for ever and thus is rejected as an unknown pattern. The maximum sizes of these islands allowed by this kind of neural networks are determined by a modified MC-adaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method for pattern recognition and rejection with an example of recognizing a set of Chinese characters.

  7. Pattern recognition using asymmetric attractor neural networks

    International Nuclear Information System (INIS)

    The asymmetric attractor neural networks designed by the Monte Carlo- (MC-) adaptation rule are shown to be promising candidates for pattern recognition. In such a neural network with relatively low symmetry, when the members of a set of template patterns are stored as fixed-point attractors, their attraction basins are shown to be isolated islands embedded in a ''chaotic sea.'' The sizes of these islands can be controlled by a single parameter. We show that these properties can be used for effective pattern recognition and rejection. In our method, the pattern to be identified is attracted to a template pattern or a chaotic attractor. If the difference between the pattern to be identified and the template pattern is smaller than a predescribed threshold, the pattern is attracted to the template pattern automatically and thus is identified as belonging to this template pattern. Otherwise, it wanders in a chaotic attractor for ever and thus is rejected as an unknown pattern. The maximum sizes of these islands allowed by this kind of neural networks are determined by a modified MC-adaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method for pattern recognition and rejection with an example of recognizing a set of Chinese characters

  8. Analysis of complex systems using neural networks

    International Nuclear Information System (INIS)

    The application of neural networks, alone or in conjunction with other advanced technologies (expert systems, fuzzy logic, and/or genetic algorithms), to some of the problems of complex engineering systems has the potential to enhance the safety, reliability, and operability of these systems. Typically, the measured variables from the systems are analog variables that must be sampled and normalized to expected peak values before they are introduced into neural networks. Often data must be processed to put it into a form more acceptable to the neural network (e.g., a fast Fourier transformation of the time-series data to produce a spectral plot of the data). Specific applications described include: (1) Diagnostics: State of the Plant (2) Hybrid System for Transient Identification, (3) Sensor Validation, (4) Plant-Wide Monitoring, (5) Monitoring of Performance and Efficiency, and (6) Analysis of Vibrations. Although specific examples described deal with nuclear power plants or their subsystems, the techniques described can be applied to a wide variety of complex engineering systems

  9. 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.

  10. Neural Network Approach for Eye Detection

    CERN Document Server

    Vijayalaxmi,; Sreehari, S

    2012-01-01

    Driving support systems, such as car navigation systems are becoming common and they support driver in several aspects. Non-intrusive method of detecting Fatigue and drowsiness based on eye-blink count and eye directed instruction controlhelps the driver to prevent from collision caused by drowsy driving. Eye detection and tracking under various conditions such as illumination, background, face alignment and facial expression makes the problem complex.Neural Network based algorithm is proposed in this paper to detect the eyes efficiently. In the proposed algorithm, first the neural Network is trained to reject the non-eye regionbased on images with features of eyes and the images with features of non-eye using Gabor filter and Support Vector Machines to reduce the dimension and classify efficiently. In the algorithm, first the face is segmented using L*a*btransform color space, then eyes are detected using HSV and Neural Network approach. The algorithm is tested on nearly 100 images of different persons under...

  11. Multiresolution training of Kohonen neural networks

    Science.gov (United States)

    Tamir, Dan E.

    2007-09-01

    This paper analyses a trade-off between convergence rate and distortion obtained through a multi-resolution training of a Kohonen Competitive Neural Network. Empirical results show that a multi-resolution approach can improve the training stage of several unsupervised pattern classification algorithms including K-means clustering, LBG vector quantization, and competitive neural networks. While, previous research concentrated on convergence rate of on-line unsupervised training. New results, reported in this paper, show that the multi-resolution approach can be used to improve training quality (measured as a derivative of the rate distortion function) on the account of convergence speed. The probability of achieving a desired point in the quality/convergence-rate space of Kohonen Competitive Neural Networks (KCNN) is evaluated using a detailed Monte Carlo set of experiments. It is shown that multi-resolution can reduce the distortion by a factor of 1.5 to 6 while maintaining the convergence rate of traditional KCNN. Alternatively, the convergence rate can be improved without loss of quality. The experiments include a controlled set of synthetic data, as well as, image data. Experimental results are reported and evaluated.

  12. Shale Gas reservoirs characterization using neural network

    Science.gov (United States)

    Ouadfeul, Sid-Ali; Aliouane, Leila

    2014-05-01

    In this paper, a tentative of shale gas reservoirs characterization enhancement from well-logs data using neural network is established. The goal is to predict the Total Organic carbon (TOC) in boreholes where the TOC core rock or TOC well-log measurement does not exist. The Multilayer perceptron (MLP) neural network with three layers is established. The MLP input layer is constituted with five neurons corresponding to the Bulk density, Neutron porosity, sonic P wave slowness and photoelectric absorption coefficient. The hidden layer is forms with nine neurons and the output layer is formed with one neuron corresponding to the TOC log. Application to two boreholes located in Barnett shale formation where a well A is used as a pilot and a well B is used for propagation shows clearly the efficiency of the neural network method to improve the shale gas reservoirs characterization. The established formalism plays a high important role in the shale gas plays economy and long term gas energy production.

  13. File access prediction using neural networks.

    Science.gov (United States)

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

    2010-06-01

    One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors. PMID:20421183

  14. Seasonal Rainfall Forecasting Using Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    G.A. Fallah-Ghalhary

    2009-01-01

    Full Text Available The rainfall of Khorasan Province, the Northeastern part of Iran, was evaluated from Dec. to May that is included 80% total of annual rainfall in the area under study using artificial neural network. The data of 37 rainfall stations were selected and analyzed over a period of 33 years (1970-2002. The Digital Elevation Model (DEM was then used to calculate the average rainfall in the area of interest. The relation between variation of synoptic patterns including Sea Surface Temperature (SST, Sea Level Pressure (SLP, the difference of sea level pressure, the difference between sea surface temperature and 1000 hPa surface level, relative humidity at 300 hPa level, geopotential height at 500 hPa level and air temperature at 850 hPa level with mean rainfall of the region were considered. Then the artificial neural network model was trained for 1970-2002 period and rainfall for period of 1993-2002 was predicted. The results showed that artificial neural network method was very successful in predicting rainfall and in more than 70% of years could predict rainfall within acceptable precision. The root mean square error of the model was found to be 41 mm which is considered negligible at yearly level and it is expected that by increasing the number of years of statistical data the precision of the model would increase.

  15. Deep learning in neural networks: an overview.

    Science.gov (United States)

    Schmidhuber, Jürgen

    2015-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes 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 backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. PMID:25462637

  16. Neural network method for characterizing video cameras

    Science.gov (United States)

    Zhou, Shuangquan; Zhao, Dazun

    1998-08-01

    This paper presents a neural network method for characterizing color video camera. A multilayer feedforward network with the error back-propagation learning rule for training, is used as a nonlinear transformer to model a camera, which realizes a mapping from the CIELAB color space to RGB color space. With SONY video camera, D65 illuminant, Pritchard Spectroradiometer, 410 JIS color charts as training data and 36 charts as testing data, results show that the mean error of training data is 2.9 and that of testing data is 4.0 in a 2563 RGB space.

  17. Clustering-based selective neural network ensemble

    Institute of Scientific and Technical Information of China (English)

    FU Qiang; HU Shang-xu; ZHAO Sheng-ying

    2005-01-01

    An effective ensemble should consist of a set of networks that are both accurate and diverse. We propose a novel clustering-based selective algorithm for constructing neural network ensemble, where clustering technology is used to classify trained networks according to similarity and optimally select the most accurate individual network from each cluster to make up the ensemble. Empirical studies on regression of four typical datasets showed that this approach yields significantly smaller en semble achieving better performance than other traditional ones such as Bagging and Boosting. The bias variance decomposition of the predictive error shows that the success of the proposed approach may lie in its properly tuning the bias/variance trade-offto reduce the prediction error (the sum of bias2 and variance).

  18. Detector response unfolding using artificial neural networks

    International Nuclear Information System (INIS)

    We present new results on the identification and unfolding of neutron spectra from the pulse height distribution measured with liquid scintillators. The novelty of the method consists of the dual use of linear and nonlinear artificial neural networks (ANNs). The linear networks solve the superposition problem in the general unfolding problem, whereas the nonlinear networks provide greater accuracy in the neutron source identification problem. Two additional new aspects of the present approach are (i) the use of a very accurate Monte Carlo code for the simulations needed in the training phase of the ANNs and (ii) the ability of the network to respond to short-time and therefore very noisy experimental measurements. This approach ensures sufficient accuracy, timeliness, and robustness to make it a candidate of choice for the heretofore unaddressed nuclear nonproliferation and safeguards applications in which both identification and unfolding are needed

  19. Desynchronization in diluted neural networks

    International Nuclear Information System (INIS)

    The dynamical behavior of a weakly diluted fully inhibitory network of pulse-coupled spiking neurons is investigated. Upon increasing the coupling strength, a transition from regular to stochasticlike regime is observed. In the weak-coupling phase, a periodic dynamics is rapidly approached, with all neurons firing with the same rate and mutually phase locked. The strong-coupling phase is characterized by an irregular pattern, even though the maximum Lyapunov exponent is negative. The paradox is solved by drawing an analogy with the phenomenon of 'stable chaos', i.e., by observing that the stochasticlike behavior is 'limited' to an exponentially long (with the system size) transient. Remarkably, the transient dynamics turns out to be stationary

  20. Fuzzy Neural Network Based Traffic Prediction and Congestion Control in High-Speed Networks

    Institute of Scientific and Technical Information of China (English)

    费翔; 何小燕; 罗军舟; 吴介一; 顾冠群

    2000-01-01

    Congestion control is one of the key problems in high-speed networks, such as ATM. In this paper, a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach. Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error. Fuzzy neural network developed in this paper can solve these problems satisfactorily. Simulations show the comparison among no-feedback control scheme,reactive control scheme and neural network based control scheme.