Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays

Hongyi Li; B. Chen; Q. Zhou; S. Fang

doi:10.1016/j.physleta.2008.01.060

Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays

Hongyi Li, B. Chen, Q. Zhou, S. Fang

Research output: Contribution to journal › Article › peer-review

248 Downloads (Pure)

Abstract

This letter deals with the problem of delay-dependent robust exponential stability in mean square for a class of uncertain stochastic Hopfield neural networks with discrete and distributed time-varying delays. Based on Lyapunov–Krasovskii functional and the stochastic stability theory, delay-dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs). Because of introducing some free-weighting matrices to develop the stability criteria, the proposed stability conditions have less conservatism. Numerical examples are given to illustrate the effectiveness of our results.

Original language	English
Pages (from-to)	3385-3394
Number of pages	10
Journal	Physics Letters A
Volume	372
Issue number	19
DOIs	https://doi.org/10.1016/j.physleta.2008.01.060
Publication status	Published - 5 May 2008

Keywords

Neural networks
Exponential stability
Stochastic systems
Uncertain systems
LMIs

Access to Document

10.1016/j.physleta.2008.01.060

LiPLA2008.pdfFinal published version, 172 KBLicence: CC BY

http://www.sciencedirect.com/science/article/pii/S0375960108001825

Cite this

@article{0a95945b17fb4efe959cbd9599cc904f,

title = "Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays",

abstract = "This letter deals with the problem of delay-dependent robust exponential stability in mean square for a class of uncertain stochastic Hopfield neural networks with discrete and distributed time-varying delays. Based on Lyapunov–Krasovskii functional and the stochastic stability theory, delay-dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs). Because of introducing some free-weighting matrices to develop the stability criteria, the proposed stability conditions have less conservatism. Numerical examples are given to illustrate the effectiveness of our results.",

keywords = "Neural networks, Exponential stability, Stochastic systems, Uncertain systems, LMIs",

author = "Hongyi Li and B. Chen and Q. Zhou and S. Fang",

note = "Funders: Natural Science Foundation of China under grant 60674055. Natural Science Foundation of China under grant 60774047. Taishan Scholar programme of Shandong Province.",

year = "2008",

month = may,

day = "5",

doi = "10.1016/j.physleta.2008.01.060",

language = "English",

volume = "372",

pages = "3385--3394",

journal = "Physics Letters A",

issn = "0375-9601",

publisher = "Elsevier BV",

number = "19",

}

TY - JOUR

T1 - Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays

AU - Li, Hongyi

AU - Chen, B.

AU - Zhou, Q.

AU - Fang, S.

N1 - Funders: Natural Science Foundation of China under grant 60674055. Natural Science Foundation of China under grant 60774047. Taishan Scholar programme of Shandong Province.

PY - 2008/5/5

Y1 - 2008/5/5

N2 - This letter deals with the problem of delay-dependent robust exponential stability in mean square for a class of uncertain stochastic Hopfield neural networks with discrete and distributed time-varying delays. Based on Lyapunov–Krasovskii functional and the stochastic stability theory, delay-dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs). Because of introducing some free-weighting matrices to develop the stability criteria, the proposed stability conditions have less conservatism. Numerical examples are given to illustrate the effectiveness of our results.

AB - This letter deals with the problem of delay-dependent robust exponential stability in mean square for a class of uncertain stochastic Hopfield neural networks with discrete and distributed time-varying delays. Based on Lyapunov–Krasovskii functional and the stochastic stability theory, delay-dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs). Because of introducing some free-weighting matrices to develop the stability criteria, the proposed stability conditions have less conservatism. Numerical examples are given to illustrate the effectiveness of our results.

KW - Neural networks

KW - Exponential stability

KW - Stochastic systems

KW - Uncertain systems

KW - LMIs

U2 - 10.1016/j.physleta.2008.01.060

DO - 10.1016/j.physleta.2008.01.060

M3 - Article

SN - 0375-9601

VL - 372

SP - 3385

EP - 3394

JO - Physics Letters A

JF - Physics Letters A

IS - 19

ER -

Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays

Abstract

Keywords

Access to Document

Fingerprint

Cite this