Global asymptotic stability of Hopfield neural network involving distributed delays

In the paper, we study dynamical behaviors of Hopfield neural networks system with distributed delays. Some new criteria ensuring the existence and uniqueness, and the global asymptotic stability (GAS) of equilibrium point are derived. In the results, we do not assume that the signal propagation functions satisfy the Lipschitz condition and do not require them to be bounded, differentiable or strictly increasing. Moreover, the symmetry of the connection matrix is not also necessary. Thus, we improve some previous works of other researchers. These conditions are presented in terms of system parameters and have importance leading significance in designs and applications of the GAS for Hopfield neural networks system with distributed delays. Two examples are also worked out to demonstrate the advantages of our results.

[1]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[2]  Leon O. Chua,et al.  Stability analysis of generalized cellular neural networks , 1993, Int. J. Circuit Theory Appl..

[3]  William A. Brock,et al.  Differential Equations, Stability and Chaos in Dynamic Economics , 1989 .

[4]  Eduardo F. Camacho,et al.  Neural network for constrained predictive control , 1993 .

[5]  Hongyong Zhao.  Global stability of bidirectional associative memory neural networks with distributed delays , 2002 .

[6]  Réjean Plamondon,et al.  On the stability analysis of delayed neural networks systems , 2001, Neural Networks.

[7]  Anthony N. Michel,et al.  Analysis and synthesis of neural networks with lower block triangular interconnecting structure , 1990 .

[8]  M. Forti,et al.  Necessary and sufficient condition for absolute stability of neural networks , 1994 .

[9]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[10]  R. D. Driver,et al.  A Uniqueness Theorem for Ordinary Differential Equations , 1981 .

[11]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[12]  K. Gopalsamy,et al.  Stability in asymmetric Hopfield nets with transmission delays , 1994 .

[13]  Pauline van den Driessche,et al.  Global Attractivity in Delayed Hopfield Neural Network Models , 1998, SIAM J. Appl. Math..

[14]  D. Kelly,et al.  Stability in contractive nonlinear neural networks , 1990, IEEE Transactions on Biomedical Engineering.

[15]  Dao-Yi Xu,et al.  Integro-differential equations and delay integral inequalities , 1992 .

[16]  Brian D. O. Anderson,et al.  Stability of adaptive systems: passivity and averaging analysis , 1986 .

[17]  Daoyi Xu,et al.  Global dynamics of Hopfield neural networks involving variable delays , 2001 .

[18]  Dao-Yi Xu,et al.  Invariant and attracting sets of Hopfield neural networks with delay , 2001, Int. J. Syst. Sci..

[19]  J. P. Lasalle.  The stability of dynamical systems , 1976 .

[20]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[21]  Xuesong Jin,et al.  Global stability analysis in delayed Hopfield neural network models , 2000, Neural Networks.

[22]  A. Tesi,et al.  New conditions for global stability of neural networks with application to linear and quadratic programming problems , 1995 .