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
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
IMS Algorithm for Learning Representations in Boolean Neural Networks
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...
Binary higher order neural networks for realizing Boolean functions.
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
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
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
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
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
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
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
Decisional Processes with Boolean Neural Network: the Emergence of Mental Schemes
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.
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)
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.
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.
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
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
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.
Boolean networks with reliable dynamics
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...
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
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.
Boolean network robotics: a proof of concept
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.
Effect of memory in non-Markovian Boolean networks
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.
Solving the Satisfiability Problem Through Boolean Networks
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...
Solving the Satisfiability Problem Through Boolean Networks
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.
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
ON REDUCED SCALAR EQUATIONS FOR SYNCHRONOUS BOOLEAN NETWORKS
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...
Evolution of a designless nanoparticle network into reconfigurable Boolean logic
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.
Evolution of a designless nanoparticle network into reconfigurable Boolean logic.
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
Consistent stabilizability of switched Boolean networks.
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
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.
Measuring Mutual Information in Random Boolean Networks
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...
Enhancing Boolean networks with fuzzy operators and edge tuning
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 ...
The Influence of Canalization on the Robustness of Boolean Networks
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...
Classes of feedforward neural networks and their circuit complexity
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...
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
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
Optimal Computation of Symmetric Boolean Functions in Collocated Networks
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 ...
Boolean network representation of contagion dynamics during a financial crisis
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.
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.
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
The value of less connected agents in Boolean networks
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
Self-organized networks of competing boolean agents
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
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.
Harmonic Analysis of Boolean Networks: Determinative Power and Perturbations
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...
Evolution and Controllability of Cancer Networks: A Boolean Perspective.
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
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.
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
Multilayer neural networks with extensively many hidden units.
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
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
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.
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.
A SAT-based algorithm for finding attractors in synchronous Boolean networks.
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
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
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
Characterizing short-term stability for Boolean networks over any distribution of transfer functions
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.
Boolean modeling of neural systems with point-process inputs and outputs.
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
SAT-based Distributed Reactive Control Protocol Synthesis for Boolean Networks
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...
Propagation of external regulation and asynchronous dynamics in random Boolean networks
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...
Neural Networks, Game Theory and Time Series Generation
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...
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.
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.
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)
Relative stability of network states in Boolean network models of gene regulation in development.
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
Autonomous Modeling, Statistical Complexity and Semi-annealed Treatment of Boolean Networks
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
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.
Neural Networks: Implementations and Applications
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
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...
Mapping Complex Networks: Exploring Boolean Modeling of Signal Transduction Pathways
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 ...
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...
Neural networks for aircraft control
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.
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....
Critical Branching Neural Networks
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…
Analysis and control of Boolean networks a semi-tensor product approach
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.
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.
Recurrent Neural Network Regularization
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.
Deep Sequential Neural Network
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...
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...
Neural Networks in Data Mining
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.
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.
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
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
From Boolean Network Model to Continuous Model Helps in Design of Functional Circuits
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, ...
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
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
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
Hyperbolic Hopfield neural networks.
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
Exploring phospholipase C-coupled Ca(2+) signalling networks using Boolean modelling.
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
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.
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....
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
Artificial neural network modelling
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. .
Detecting small attractors of large Boolean networks by function-reduction-based strategy.
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
Neural Networks and Micromechanics
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.
Generalized Adaptive Artificial Neural Networks
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.
Coevolution of Information Processing and Topology in Hierarchical Adaptive Random Boolean Networks
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.
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
Random Boolean Networks and Attractors of their Intersecting Circuits
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...
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.
Dynamical modeling of the cholesterol regulatory pathway with Boolean networks
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...
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.
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
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.
Implementing Neural Networks Efficiently
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 ...
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.
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
Dynamic recurrent neural networks
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...
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.
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.
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
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
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.
The receptor mosaic hypothesis of the engram: possible relevance of Boolean network modeling.
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
Damage spreading in spatial and small-world random Boolean networks
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.
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.
Multiple neural network approaches to clinical expert systems
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
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.
Neural logic networks a new class of neural networks
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
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
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…
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...
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)
Modeling and controlling the two-phase dynamics of the p53 network: a Boolean network approach
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.
Neural network applications in telecommunications
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.
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
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....
Neural Networks for the Beginner.
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…
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)
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.
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...
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
Medical diagnosis using neural network
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...
Principles of artificial neural networks
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
Modular, Hierarchical Learning By Artificial Neural Networks
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.
Neural networks and statistical learning
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...
Neural Networks Of VLSI Components
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.
Neural Networks for Fingerprint Recognition
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...
Neural Networks and Photometric Redshifts
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...
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...
Correlational Neural Networks.
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
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.
Complex-Valued Neural Networks
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...
Phase Transitions of Neural Networks
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.
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.
Neural Networks and Database Systems
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.
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
Detecting a Singleton Attractor in a Boolean Network Utilizing SAT Algorithms
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.
Automatic Generation of Neural Networks
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...
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.
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
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
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.
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.)
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.
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.
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...
Plant Growth Models Using Artificial Neural Networks
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.
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...
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.
Neural Networks for Flight Control
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.
Building a Chaotic Proved Neural Network
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.
Neural Network Adaptations to Hardware Implementations
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 ...
Neural Network Adaptations to Hardware Implementations
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...
Neural networks and applications tutorial
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.
Deep Gate Recurrent Neural Network
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...
Network Firewall using Artificial Neural Networks
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...
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.
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)
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...
Model Of Neural Network With Creative Dynamics
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.
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...
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.
Neural Networks and Photometric Redshifts
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
Neural Network Model For Fast Learning And Retrieval
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.
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.
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.
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)
Fuzzy logic systems are equivalent to feedforward neural networks
Institute of Scientific and Technical Information of China (English)
无
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.
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...
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.
Neural Networks Methodology and Applications
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...
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.
Color conversion using neural networks
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.
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.
Learning Compact Recurrent Neural Networks
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...
Learning with heterogeneous neural networks
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...
Process Neural Networks Theory and Applications
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
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.
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.
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.
Practical neural network recipies in C++
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
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.
Neural network modeling of emotion
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.
Neural-Network Computer Transforms Coordinates
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.
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.
Information Theory for Analyzing Neural Networks
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 ...
Fast Algorithms for Convolutional Neural Networks
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 ...
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.
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
Adaptive Control Based On Neural Network
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...
Sequential optimizing investing strategy with neural networks
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...
Boolean implication networks derived from large scale, whole genome microarray datasets
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...
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)
Fuzzy neural network theory and application
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
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.
Chess Endgames and Neural Networks
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...
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....
Artificial Neural Networks An Introduction
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
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
Three dimensional living neural networks
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.
Neural Network Controlled Visual Saccades
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.
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].
Neural Networks for Emotion Classification
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...
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.
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
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.
Extrapolation limitations of multilayer feedforward neural networks
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.
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
Coherence resonance in bursting neural networks
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.
USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS
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...
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
Medical image analysis with artificial neural networks.
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
Adaptive Neurons For Artificial Neural Networks
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.
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.
Self-organization of neural networks
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.
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....
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
Radiation Behavior of Analog Neural Network Chip
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.
Understanding Neural Networks Through Deep Visualization
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 ...
Introduction to Concepts in Artificial Neural Networks
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.
MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION
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...
Visual Character Recognition using Artificial Neural Networks
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.
Secure Key Exchange using Neural Network
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...
Modularity as a Solution to Spatial Interference in Neural Networks
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...
Rule Extraction using Artificial Neural Networks
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 ...
International Conference on Artificial Neural Networks (ICANN)
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...
Neural network correspondencies of engineering principles
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.
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.
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.
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
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.)
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
Subspace learning of neural networks
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.
Sunspot prediction using neural networks
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.
Introduction to artificial neural networks.
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
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)
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
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
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.
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.
Learning Processes of Layered Neural Networks
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.