Multistability in Recurrent Neural Networks

Stable stationary solutions correspond to memory capacity in the application of associative memory for neural networks. In this presentation, existence of multiple stable stationary solutions for Hopfield-type neural networks with delay and without delay is investigated. Basins of attraction for these stationary solutions are also estimated. Such a scenario of dynamics is established through formulating parameter conditions based on a geometrical setting. The present theory is demonstrated by two numerical simulations on the Hopfield neural networks with delays.

[1]  Jinde Cao,et al.  Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays , 2004, Neural Networks.

[2]  Hong Qiao,et al.  A new approach to stability of neural networks with time-varying delays , 2002, Neural Networks.

[3]  L. Chua.  Cnn: A Paradigm for Complexity , 1998 .

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

[5]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

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

[7]  José Carlos Goulart de Siqueira,et al.  Differential Equations , 1919, Nature.

[8]  Xingfu Zou,et al.  Stabilization role of inhibitory self-connections in a delayed neural network , 2001 .

[9]  Chih-Wen Shih,et al.  On the Templates Corresponding to Cycle-Symmetric Connectivity in Cellular Neural Networks , 2002, Int. J. Bifurc. Chaos.

[10]  Jinde Cao.  New results concerning exponential stability and periodic solutions of delayed cellular neural networks , 2003 .

[11]  Jack K. Hale,et al.  Introduction to Functional Differential Equations , 1993, Applied Mathematical Sciences.

[12]  Leon O. Chua,et al.  Cellular neural networks with non-linear and delay-type template elements and non-uniform grids , 1992, Int. J. Circuit Theory Appl..

[13]  Shyan-Shiou Chen,et al.  Transversal homoclinic orbits in a transiently chaotic neural network. , 2002, Chaos.

[14]  Stability , 1973 .

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

[16]  Chih-Wen Shih.  Influence of Boundary Conditions on Pattern Formation and Spatial Chaos in Lattice Systems , 2000, SIAM J. Appl. Math..

[17]  Tianping Chen,et al.  Global exponential stability of delayed Hopfield neural networks , 2001, Neural Networks.

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

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

[20]  Chi-Ming Chen,et al.  Winner-take-all neural networks using the highest threshold , 2000, IEEE Trans. Neural Networks Learn. Syst..

[21]  Chih-Wen Shih,et al.  Pattern Formation and Spatial Chaos for Cellular Neural Networks with Asymmetric Templates , 1998 .

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

[23]  Pheng-Ann Heng,et al.  Winner-take-all discrete recurrent neural networks , 2000 .

[24]  Sue Ann Campbell,et al.  Stability, Bifurcation, and Multistability in a System of Two Coupled Neurons with Multiple Time Delays , 2000, SIAM J. Appl. Math..

[25]  Richard H. R. Hahnloser,et al.  On the piecewise analysis of networks of linear threshold neurons , 1998, Neural Networks.

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

[27]  Xiaofeng Liao,et al.  (Corr. to) Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach , 2002, Neural Networks.

[28]  Hongyong Zhao,et al.  Global asymptotic stability of Hopfield neural network involving distributed delays , 2004, Neural Networks.

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

[30]  Pauline van den Driessche,et al.  Delayed Coupling Between Two Neural Network Loops , 2004, SIAM J. Appl. Math..

[31]  Foss,et al.  Multistability and delayed recurrent loops. , 1996, Physical review letters.

[32]  A. Siamj.,et al.  CELLULAR NEURAL NETWORKS : MOSAIC PATTERN AND SPATIAL CHAOS , 2000 .

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

[34]  K. Gopalsamy.  Stability and Oscillations in Delay Differential Equations of Population Dynamics , 1992 .

[35]  K. Gopalsamy,et al.  Exponential stability of continuous-time and discrete-time cellular neural networks with delays , 2003, Appl. Math. Comput..

[36]  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.