Interval criterion for stability analysis of discrete-time neural networks with partial state saturation nonlinearities

Author

Kolev, Lubomir ; Petrakieva, Simona ; Mladenov, Eri

Author_Institution

Dept. Theor. of Electr. Eng., Tech. Univ. of Sofia, Bulgaria

fYear

2004

fDate

23-25 Sept. 2004

Firstpage

11

Lastpage

16

Abstract

A generalization of sufficient conditions for global asymptotic stability of the equilibrium x_e=0 of discrete-time neural networks, described by systems which have saturation nonlinearities on part of the states in the case of interval uncertainties, is considered. When using quadratic form Lyapunov functions, sufficient conditions, based on the positive definite interval matrices, are presented. In order to check this, a recent proposed method for determining the outer bounds of eigenvalues ranges is used. A numerical example, illustrating the applicability of the method suggested, is solved at the end of the paper.

Keywords

Lyapunov matrix equations; asymptotic stability; discrete time systems; eigenvalues and eigenfunctions; neural nets; numerical stability; discrete-time neural networks; eigenvalue range outer bounds; equilibrium global asymptotic stability; interval matrix independent coefficients; interval uncertainties; partial state saturation nonlinearities; positive definite interval matrices; quadratic form Lyapunov functions; stability analysis interval criterion; Asymptotic stability; Eigenvalues and eigenfunctions; Electronic mail; Hypercubes; Lyapunov method; Neural networks; Robust stability; Stability analysis; Sufficient conditions; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Network Applications in Electrical Engineering, 2004. NEUREL 2004. 2004 7th Seminar on

Print_ISBN

0-7803-8547-0

Type

conf

DOI

10.1109/NEUREL.2004.1416520

Filename

1416520