Delay-dependent approach to robust stability for uncertain discretestochastic recurrent neural networks with interval time-varying delays

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

This paper considers the problem of global robust delay-dependent stabilityfor uncertain discrete stochastic recurrent neural networks with intervaltime-varying delays. The parameter uncertainties are assumed to be time-varyingnorm-bounded in the state equation. The activation functions are assumed to beglobally Lipschitz continuous. Based on an appropriate Lyapunov-Krasovskiifunctional, global robust delay-dependent stability criterion which is dependenton both the lower bound and upper bound of the interval time-varying delays isderived by introducing some slack matrix variables. A sufficient condition forthe discrete stochastic recurrent neural networks with interval time-varyingdelays is presented in terms of the linear matrix inequality (LMI). A Numericalexample is given to demonstrate the reduced conservatism of the proposed resultsin this paper. ICIC International

Original languageEnglish
Pages (from-to)457-463
Number of pages7
JournalICIC Express Letters
Volume3
Issue number3
Publication statusPublished - 2009 Sep 1

Fingerprint

Recurrent neural networks
Stability criteria
Linear matrix inequalities
Chemical activation
Robust stability
Uncertainty

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

@article{9f5b457f225143dc8d38d369bb7ba7b8,
title = "Delay-dependent approach to robust stability for uncertain discretestochastic recurrent neural networks with interval time-varying delays",
abstract = "This paper considers the problem of global robust delay-dependent stabilityfor uncertain discrete stochastic recurrent neural networks with intervaltime-varying delays. The parameter uncertainties are assumed to be time-varyingnorm-bounded in the state equation. The activation functions are assumed to beglobally Lipschitz continuous. Based on an appropriate Lyapunov-Krasovskiifunctional, global robust delay-dependent stability criterion which is dependenton both the lower bound and upper bound of the interval time-varying delays isderived by introducing some slack matrix variables. A sufficient condition forthe discrete stochastic recurrent neural networks with interval time-varyingdelays is presented in terms of the linear matrix inequality (LMI). A Numericalexample is given to demonstrate the reduced conservatism of the proposed resultsin this paper. ICIC International",
author = "Lu, {Chien Yu} and Shyr, {Wen Jye} and Yao, {Kai Chao} and Chen, {Der Fa}",
year = "2009",
month = "9",
day = "1",
language = "English",
volume = "3",
pages = "457--463",
journal = "ICIC Express Letters",
issn = "1881-803X",
publisher = "ICIC Express Letters Office",
number = "3",

}

TY - JOUR

T1 - Delay-dependent approach to robust stability for uncertain discretestochastic recurrent neural networks with interval time-varying delays

AU - Lu, Chien Yu

AU - Shyr, Wen Jye

AU - Yao, Kai Chao

AU - Chen, Der Fa

PY - 2009/9/1

Y1 - 2009/9/1

N2 - This paper considers the problem of global robust delay-dependent stabilityfor uncertain discrete stochastic recurrent neural networks with intervaltime-varying delays. The parameter uncertainties are assumed to be time-varyingnorm-bounded in the state equation. The activation functions are assumed to beglobally Lipschitz continuous. Based on an appropriate Lyapunov-Krasovskiifunctional, global robust delay-dependent stability criterion which is dependenton both the lower bound and upper bound of the interval time-varying delays isderived by introducing some slack matrix variables. A sufficient condition forthe discrete stochastic recurrent neural networks with interval time-varyingdelays is presented in terms of the linear matrix inequality (LMI). A Numericalexample is given to demonstrate the reduced conservatism of the proposed resultsin this paper. ICIC International

AB - This paper considers the problem of global robust delay-dependent stabilityfor uncertain discrete stochastic recurrent neural networks with intervaltime-varying delays. The parameter uncertainties are assumed to be time-varyingnorm-bounded in the state equation. The activation functions are assumed to beglobally Lipschitz continuous. Based on an appropriate Lyapunov-Krasovskiifunctional, global robust delay-dependent stability criterion which is dependenton both the lower bound and upper bound of the interval time-varying delays isderived by introducing some slack matrix variables. A sufficient condition forthe discrete stochastic recurrent neural networks with interval time-varyingdelays is presented in terms of the linear matrix inequality (LMI). A Numericalexample is given to demonstrate the reduced conservatism of the proposed resultsin this paper. ICIC International

UR - http://www.scopus.com/inward/record.url?scp=77953651481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953651481&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77953651481

VL - 3

SP - 457

EP - 463

JO - ICIC Express Letters

JF - ICIC Express Letters

SN - 1881-803X

IS - 3

ER -