Improved Free-Weighting Matrix Approach for Stability Analysis of Discrete-Time Recurrent Neural Networks With Time-Varying Delay

Author

Wu, Min ; Liu, Fang ; Shi, Peng ; He, Yong ; Yokoyama, Ryuichi

Author_Institution

Sch. of Inf. Sci. & Eng., Central South Univ., Changsha

Volume

55

Issue

7

fYear

2008

fDate

7/1/2008 12:00:00 AM

Firstpage

690

Lastpage

694

Abstract

This paper deals with the problem of exponential stability for a class of discrete-time recurrent neural networks with time-varying delay by employing an improved free-weighting matrix approach. The relationship among the time-varying delay, its upper bound and their difference is taken into account. As a result, a new and less conservative delay-dependent stability criterion is obtained without ignoring any useful terms on the difference of a Lyapunov function, which is expressed in terms of linear matrix inequalities. Finally, numerical examples are given to demonstrate the effectiveness of the proposed techniques.

Keywords

Lyapunov methods; asymptotic stability; delays; discrete time systems; linear matrix inequalities; recurrent neural nets; stability criteria; time-varying systems; Lyapunov function; delay-dependent stability criterion; discrete-time recurrent neural networks; exponential stability; free-weighting matrix; linear matrix inequalities; stability analysis; time-varying delay; Delay; Helium; Linear matrix inequalities; Lyapunov method; Neural networks; Recurrent neural networks; Stability analysis; Stability criteria; Time varying systems; Upper bound; Discrete-time recurrent neural networks; Lyapunov function; delay-dependent stability; linear matrix inequalities (LMIs); time-varying delay;

fLanguage

English

Journal_Title

Circuits and Systems II: Express Briefs, IEEE Transactions on

Publisher

ieee

ISSN

1549-7747

Type

jour

DOI

10.1109/TCSII.2008.921597

Filename

4567631