论文信息 - A sufficient condition for absolute stability of a larger class of dynamical neural networks

A sufficient condition for absolute stability of a larger class of dynamical neural networks

In this paper, we present a sufficient condition for absolute stability of a larger class of dynamical neural networks. It is shown that the H-matrix condition on the interconnection matrix ensures the existence, uniqueness and global asymptotic stability (GAS) of the equilibrium point with respect to slope-limited activation functions.

S. Arik | V. Tavsanoglu

[1] T. Roska. Some qualitative aspects of neural computing circuits , 1988, 1988., IEEE International Symposium on Circuits and Systems.

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

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

[4] J. Farrell,et al. Qualitative analysis of neural networks , 1989 .

[5] Charles R. Johnson,et al. Topics in Matrix Analysis , 1991 .

[6] Kiyotoshi Matsuoka. Absolute stability of neural networks , 1992, Systems and Computers in Japan.

[7] E. Kaszkurewicz,et al. On a class of globally stable neural circuits , 1994 .

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

[9] Mauro Forti,et al. On absolute stability of neural networks , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

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

[11] Eugenius Kaszkurewicz,et al. Comments on "Necessary and sufficient condition for absolute stability of neural networks" , 1995 .

[12] Vedat Tavsanoglu,et al. A comment on "Comments on 'Necessary and sufficient condition for absolute stability of neural networks'" , 1998 .