Design of a chaotic neural network for training and retrieval of grayscale and binary patterns

Experimental and theoretical evidence shows that biological system processing behavior has nonlinear and chaotic properties. The ability of emerging various solutions for a problem and the existence of a supervisor to guide this variety to become close to the goal, are the two main properties of a problem solver. In this paper, a chaotic neural network which uses chaotic nodes with the logistic map as activation functions is designed to make the ability of emerging various solutions and an NDRAM is considered as a supervisor to guide these various solutions. The proposed chaotic neural network has better performance in comparison with Hopfield, NDRAM, and L. Zhao et al. ChNN.

[1]  William L. Ditto,et al.  DYNAMICS BASED COMPUTATION , 1998 .

[2]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[3]  M. E. Shirokov,et al.  Chaotic synchronization in ensembles of coupled maps , 1997 .

[4]  Jan Walleczek,et al.  Self-Organized Biological Dynamics and Nonlinear Control , 2006 .

[5]  Nabil H. Farhat,et al.  The bifurcating neuron network 3 , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  Kunihiko Kaneko,et al.  Complex Systems: Chaos and Beyond , 2001 .

[7]  Opper,et al.  Learning of correlated patterns in spin-glass networks by local learning rules. , 1987, Physical review letters.

[8]  K. Kaneko.  Period-Doubling of Kink-Antikink Patterns, Quasiperiodicity in Antiferro-Like Structures and Spatial Intermittency in Coupled Logistic Lattice*) -- Towards a Prelude of a "Field Theory of Chaos"-- , 1984 .

[9]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Robert Kozma,et al.  Time series prediction using chaotic neural networks on the CATS benchmark , 2007, Neurocomputing.

[11]  Robert Proulx,et al.  NDRAM: nonlinear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns , 2005, IEEE Transactions on Neural Networks.

[12]  Liang Zhao,et al.  Chaotic dynamics for multi-value content addressable memory , 2006, Neurocomputing.

[13]  K. Kaneko.  Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements , 1990 .

[15]  Amos J. Storkey,et al.  The basins of attraction of a new Hopfield learning rule , 1999, Neural Networks.

[16]  Arash Mohammadi,et al.  Design of a chaotic neural network by using chaotic nodes and NDRAM network , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[17]  Nabil H. Farhat.  Corticonics: the way to designing machines with brainlike intelligence , 2000, SPIE Optics + Photonics.

[18]  Jacek M. Zurada,et al.  Bifurcating neuron: computation and learning , 2004, Neural Networks.

[19]  Jan Bogg,et al.  Complexity, Science and Society , 2007 .

[20]  Masa-aki Sato,et al.  Associative memory based on parametrically coupled chaotic elements , 1998 .

[21]  R M Borisyuk,et al.  Information coding on the basis of synchronization of neuronal activity. , 1997, Bio Systems.

[22]  Patricia Shaw,et al.  Complexity and Management: Fad or Radical Challenge to Systems Thinking? , 2002 .

[23]  H. G. Schuster,et al.  CONTROL OF CHAOS BY OSCILLATING FEEDBACK , 1997 .

[24]  Robert Kozma,et al.  Chaotic Resonance - Methods and Applications for Robust Classification of noisy and Variable Patterns , 2001, Int. J. Bifurc. Chaos.

[25]  Emilio Del Moral Hernandez.  2005 Special Issue: Non-homogenous neural networks with chaotic recursive nodes: Connectivity and multi-assemblies structures in recursive processing elements architectures , 2005, ISNN 2005.

[26]  Walter J. Freeman,et al.  Strange attractors that govern mammalian brain dynamics shown by trajectories of electroencephalographic (EEG) potential , 1988 .

[27]  Kanter,et al.  Associative recall of memory without errors. , 1987, Physical review. A, General physics.

[28]  Robert Proulx,et al.  Categorization in unsupervised neural networks: the Eidos model , 1996, IEEE Trans. Neural Networks.

[29]  Gianfranco Basti,et al.  Neural images and neural coding , 1995, Behavioral and Brain Sciences.

[30]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[31]  K. Aihara,et al.  Chaotic neural networks , 1990 .

[32]  E DelMoralHernandez.  Non-homogenous neural networks with chaotic recursive nodes: Connectivity and multi-assemblies structures in recursive processing elements architectures , 2005, Neural Networks.

[33]  Francis Heylighen,et al.  Self-organization, Emergence and the Architecture of Complexity , 1989 .

[34]  Ali A. Minai,et al.  Stimulus-induced bifurcations in discrete-time neural oscillators , 1998, Biological Cybernetics.

[35]  P Varona,et al.  Synchronous behavior of two coupled electronic neurons. , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[36]  Xiao-Song Yang,et al.  Chaos and transient chaos in simple Hopfield neural networks , 2005, Neurocomputing.

[37]  Lipo Wang,et al.  Oscillatory and chaotic dynamics in neural networks under varying operating conditions , 1996, IEEE Trans. Neural Networks.