Strange attractors in chaotic neural networks

This paper aims to prove theoretically that transiently chaotic neural networks (TCNNs) have a strange attractor, which is generated by a bounded fixed point corresponding to a unique repeller in the case that absolute values of the self-feedback connection weights in TCNNs are sufficiently large. We provide sufficient conditions under which the fixed point actually evolves into a strange attractor by a homoclinic bifurcation, which results in complicated chaotic dynamics. The strange attractor of n-dimensional TCNNs is actually the global unstable set of the repeller, which is asymptotically stable, sensitively dependent on initial conditions and topologically transitive. The existence of the strange attractor implies that TCNNs have a globally searching ability for globally optimal solutions of the commonly used objective functions in combinatorial optimization problems when the size of the strange attractor is sufficiently large.

[1]  D. Ruelle,et al.  Ergodic theory of chaos and strange attractors , 1985 .

[2]  S. Amari,et al.  Characteristics of Random Nets of Analog Neuron-Like Elements , 1972, IEEE Trans. Syst. Man Cybern..

[3]  C. S. Chen,et al.  Application of load survey systems to proper tariff design , 1997 .

[4]  R. Westervelt,et al.  Dynamics of iterated-map neural networks. , 1989, Physical review. A, General physics.

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

[6]  F. R. Marotto.  Snap-back repellers imply chaos in Rn , 1978 .

[7]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .

[8]  Luonan Chen,et al.  Mean field theory for optimal power flow , 1997 .

[9]  Christian Mira,et al.  Chaotic Dynamics in Two-Dimensional Noninvertible Maps , 1996 .

[10]  Kazuyuki Aihara,et al.  Global searching ability of chaotic neural networks , 1999 .

[11]  K. Aihara,et al.  Chaos and asymptotical stability in discrete-time neural networks , 1997, chao-dyn/9701020.

[12]  Y. Kuznetsov.  Elements of Applied Bifurcation Theory , 2023, Applied Mathematical Sciences.

[13]  Kazuyuki Aihara,et al.  AN ANALYSIS ON INSTANTANEOUS STABILITY OF AN ASSOCIATIVE CHAOTIC NEURAL NETWORK , 1999 .

[14]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[15]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[16]  I. Shimada,et al.  A Numerical Approach to Ergodic Problem of Dissipative Dynamical Systems , 1979 .

[17]  Carsten Peterson,et al.  A Mean Field Theory Learning Algorithm for Neural Networks , 1987, Complex Syst..

[18]  M. Urabe,et al.  Galerkin's procedure for nonlinear periodic systems , 1968 .

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

[20]  On regularity properties of extremal controls , 1995 .

[21]  P. Holmes,et al.  Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields , 1983, Applied Mathematical Sciences.

[22]  Jorge Buescu,et al.  Exotic Attractors: From Liapunov Stability to Riddled Basins , 1997 .

[23]  Kazuyuki Aihara,et al.  Chaotic simulated annealing by a neural network model with transient chaos , 1995, Neural Networks.

[24]  Kazuyuki Aihara,et al.  Associative Dynamics in a Chaotic Neural Network , 1997, Neural Networks.