Improved free-weighting matrix approach for stability analysis of discrete-time recurrent neural networks with time-varying delay

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

Research output: Contribution to journalArticle

45 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)690-694
Number of pages5
JournalIEEE Transactions on Circuits and Systems II: Express Briefs
Volume55
Issue number7
DOIs
Publication statusPublished - 2008 Jul

Fingerprint

Recurrent neural networks
Stability criteria
Lyapunov functions
Asymptotic stability
Linear matrix inequalities

Keywords

  • Delay-dependent stability
  • Discrete-time recurrent neural networks
  • Linear matrix inequalities (LMIs)
  • Lyapunov function
  • Time-varying delay

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Improved free-weighting matrix approach for stability analysis of discrete-time recurrent neural networks with time-varying delay. / Wu, Min; Liu, Fang; Shi, Peng; He, Yong; Yokoyama, Ryuichi.

In: IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 55, No. 7, 07.2008, p. 690-694.

Research output: Contribution to journalArticle

@article{ada9da29dc0e48c594e362e271912cc1,
title = "Improved free-weighting matrix approach for stability analysis of discrete-time recurrent neural networks with time-varying delay",
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 = "Delay-dependent stability, Discrete-time recurrent neural networks, Linear matrix inequalities (LMIs), Lyapunov function, Time-varying delay",
author = "Min Wu and Fang Liu and Peng Shi and Yong He and Ryuichi Yokoyama",
year = "2008",
month = "7",
doi = "10.1109/TCSII.2008.921597",
language = "English",
volume = "55",
pages = "690--694",
journal = "IEEE Transactions on Circuits and Systems I: Regular Papers",
issn = "1549-8328",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Improved free-weighting matrix approach for stability analysis of discrete-time recurrent neural networks with time-varying delay

AU - Wu, Min

AU - Liu, Fang

AU - Shi, Peng

AU - He, Yong

AU - Yokoyama, Ryuichi

PY - 2008/7

Y1 - 2008/7

N2 - 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.

AB - 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.

KW - Delay-dependent stability

KW - Discrete-time recurrent neural networks

KW - Linear matrix inequalities (LMIs)

KW - Lyapunov function

KW - Time-varying delay

UR - http://www.scopus.com/inward/record.url?scp=48849110858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48849110858&partnerID=8YFLogxK

U2 - 10.1109/TCSII.2008.921597

DO - 10.1109/TCSII.2008.921597

M3 - Article

VL - 55

SP - 690

EP - 694

JO - IEEE Transactions on Circuits and Systems I: Regular Papers

JF - IEEE Transactions on Circuits and Systems I: Regular Papers

SN - 1549-8328

IS - 7

ER -