Oscillatory and chaotic dynamics in neural networks under varying operating conditions

This paper studies the effects of a time-dependent operating environment on the dynamics of a neural network. In the previous paper Wang et al. (1990) studied an exactly solvable model of a higher order neural network. We identified a bifurcation parameter for the system, i.e., the rescaled noise level, which represents the combined effects of incomplete connectivity, interference among stored patterns, and additional stochastic noise. When this bifurcation parameter assumes different but static (time-independent) values, the network shows a spectrum of dynamics ranging from fixed points, to oscillations, to chaos. This paper shows that varying operating conditions described by the time-dependence of the rescaled noise level give rise to many more interesting dynamical behaviours, such as disappearances of fixed points and transitions between periodic oscillations and deterministic chaos. These results suggest that a varying environment, such as the one studied in the present model, may be used to facilitate memory retrieval if dynamic states are used for information storage in a neural network.

[1]  Grebogi,et al.  Using chaos to direct trajectories to targets. , 1990, Physical review letters.

[2]  Qing Yang,et al.  Pattern recognition by a distributed neural network: An industrial application , 1991, Neural Networks.

[3]  François Chapeau-Blondeau,et al.  Stable, oscillatory, and chaotic regimes in the dynamics of small neural networks with delay , 1992, Neural Networks.

[4]  A. S. Dmitriyev,et al.  CHAOTIC SCANNING AND RECOGNITION OF IMAGES IN NEURON-LIKE SYSTEMS WITH LEARNING , 1994 .

[5]  J. Yorke,et al.  Period Three Implies Chaos , 1975 .

[6]  François Chapeau-Blondeau,et al.  Dynamic Properties of A Biologically Motivated Neural Network Model , 1992, Int. J. Neural Syst..

[7]  L. Wang,et al.  Synchronous neural networks of nonlinear threshold elements with hysteresis. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Wang,et al.  Chaos, multiplicity, crisis, and synchronicity in higher-order neural networks. , 1991, Physical review. A, Atomic, molecular, and optical physics.

[9]  J. M. Cowley.  An Approximate Theory of Order in Alloys , 1950 .

[10]  Edward Ott,et al.  Controlling chaos , 2006, Scholarpedia.

[11]  A Hjelmfelt,et al.  Pattern recognition, chaos, and multiplicity in neural networks of excitable systems. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Ichiro Tsuda,et al.  Noise-induced order , 1983 .

[13]  L. Wang,et al.  Interactions of neural networks: models for distraction and concentration. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Mario Markus,et al.  Populations under Periodically and Randomly Varying Growth Conditions , 1987 .

[15]  E. Gardner,et al.  An Exactly Solvable Asymmetric Neural Network Model , 1987 .

[16]  Ditto,et al.  Experimental control of chaos. , 1990, Physical review letters.

[17]  K Fukushima,et al.  Handwritten alphanumeric character recognition by the neocognitron , 1991, IEEE Trans. Neural Networks.

[18]  Yong Yao,et al.  Central pattern generating and recognizing in olfactory bulb: A correlation learning rule , 1988, Neural Networks.

[19]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.

[20]  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.

[21]  Lipo Wang,et al.  Physical Modeling of Neural Networks , 1992 .

[22]  L. Wang,et al.  Oscillations and chaos in neural networks: an exactly solvable model. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[23]  François Chapeau-Blondeau.  Analysis of neural networks with chaotic dynamics , 1993 .

[24]  W. Freeman.  The physiology of perception. , 1991, Scientific American.

[25]  Ying-Cheng Lai,et al.  Controlling chaos , 1994 .

[26]  J. E. Moreira.  Intermittency in a neural network with variable threshold , 1993 .

[27]  P. Peretto,et al.  Collective Properties of Neural Networks , 1986 .