Global equilibrium stability of discrete-time analog neural networks

Author

Jin, Liang ; Nikiforuk, Peter N. ; Gupta, Madan M.

Author_Institution

Intelligent Syst. Res. Lab., Saskatchewan Univ., Saskatoon, Sask., Canada

Volume

4

fYear

1995

fDate

20-24 Mar 1995

Firstpage

1949

Abstract

In this paper, some global stability criteria of an equilibrium state for a general class of discrete-time dynamic neural networks are presented using a novel diagonal Lyapunov function approach, and the resulting criteria are described by the diagonal Lyapunov matrix equations. First, globally diagonal Lyapunov function approaches are applied to study equilibrium stability problem of a class of discrete-time dynamic neural networks without linear terms. Some novel stability conditions are then obtained for a general class of discrete-time dynamic neural networks

Keywords

Lyapunov matrix equations; analogue processing circuits; neural nets; stability; stability criteria; diagonal Lyapunov function; diagonal Lyapunov matrix equations; discrete-time analog neural networks; equilibrium state; global equilibrium stability; Asymptotic stability; Difference equations; Hopfield neural networks; Intelligent networks; Intelligent systems; Laboratories; Lyapunov method; Neural networks; Nonlinear dynamical systems; Stability criteria;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int

Conference_Location

Yokohama

Print_ISBN

0-7803-2461-7

Type

conf

DOI

10.1109/FUZZY.1995.409946

Filename

409946