Global Attractivity in Delayed Hopfield Neural Network Models

Two different approaches are employed to investigate the global attractivity of delayed Hopfield neural network models. Without assuming the monotonicity and differentiability of the activation functions, Liapunov functionals and functions (combined with the Razumikhin technique) are constructed and employed to establish sufficient conditions for global asymptotic stability independent of the delays. In the case of monotone and smooth activation functions, the theory of monotone dynamical systems is applied to obtain criteria for global attractivity of the delayed model. Such criteria depend on the magnitude of delays and show that self-inhibitory connections can contribute to the global convergence.

[1]  Jianhong Wu.  SYMMETRIC FUNCTIONAL DIFFERENTIAL EQUATIONS AND NEURAL NETWORKS WITH MEMORY , 1998 .

[2]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[4]  Jacques Bélair,et al.  Bifurcations, stability, and monotonicity properties of a delayed neural network model , 1997 .

[5]  Hal L. Smith,et al.  Strongly order preserving semiflows generated by functional differential equations , 1991 .

[6]  Wolfgang Porod,et al.  Qualitative analysis and synthesis of a class of neural networks , 1988 .

[7]  Hal L. Smith,et al.  Monotone Dynamical Systems: An Introduction To The Theory Of Competitive And Cooperative Systems (Mathematical Surveys And Monographs) By Hal L. Smith , 1995 .

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

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

[10]  Q. Henry Wu,et al.  A note on stability of analog neural networks with time delays , 1996, IEEE Trans. Neural Networks.

[11]  Kiyotoshi Matsuoka,et al.  Stability conditions for nonlinear continuous neural networks with asymmetric connection weights , 1992, Neural Networks.

[12]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[13]  Amir F. Atiya.  Learning on a General Network , 1987, NIPS.

[14]  J. R. Haddock,et al.  Liapunov-Razumikhin functions and an invariance principle for functional differential equations , 1983 .

[15]  WU J.,et al.  Patterns of Sustained Oscillations in Neural Networks with Delayed Interactions , 1995 .

[16]  Soo-Young Lee,et al.  An Optimization Network for Matrix Inversion , 1987, NIPS.

[17]  M. Forti.  On Global Asymptotic Stability of a Class of Nonlinear Systems Arising in Neural Network Theory , 1994 .

[18]  Masahiko Morita,et al.  Capacity of associative memory using a nonmonotonic neuron model , 1993, Neural Networks.

[19]  Morris W. Hirsch,et al.  Convergent activation dynamics in continuous time networks , 1989, Neural Networks.

[20]  J. Bélair.  Stability in a model of a delayed neural network , 1993 .

[21]  J. Farrell,et al.  Qualitative analysis of neural networks , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[22]  F. V. Vleck,et al.  Stability and Asymptotic Behavior of Differential Equations , 1965 .

[23]  Sue Ann Campbell,et al.  Frustration, Stability, and Delay-Induced Oscillations in a Neural Network Model , 1996, SIAM J. Appl. Math..

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

[25]  Robert J. Plemmons,et al.  Nonnegative Matrices in the Mathematical Sciences , 1979, Classics in Applied Mathematics.

[26]  M. Forti,et al.  A condition for global convergence of a class of symmetric neural circuits , 1992 .

[27]  Masahiko Morita,et al.  Associative memory with nonmonotone dynamics , 1993, Neural Networks.