New stability criteria for recurrent neural networks with interval time-varying delay

Yong Qiang Bai; Jie Chen

doi:10.1016/j.neucom.2013.04.031

New stability criteria for recurrent neural networks with interval time-varying delay

Yong Qiang Bai^*, Jie Chen

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

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

46 Citations (Scopus)

Abstract

This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay belonging to a given interval. By constructing a novel augmented Lyapunov functional which contains some triple-integral terms, improved delay-dependent stability criteria are derived in terms of linear matrix inequality (LMI) by introducing some free-weighting matrices and using integral inequality technique and convex combination method. Numerical examples are given to illustrate the effectiveness of the proposed method.

Original language	English
Pages (from-to)	179-184
Number of pages	6
Journal	Neurocomputing
Volume	121
DOIs	https://doi.org/10.1016/j.neucom.2013.04.031
Publication status	Published - 9 Dec 2013

Keywords

Delay-dependent stability
Interval time-varying delay
Linear matrix inequality
Recurrent neural network

Access to Document

10.1016/j.neucom.2013.04.031

Cite this

@article{a765efad869f4a1285e7a5ed9e27917b,

title = "New stability criteria for recurrent neural networks with interval time-varying delay",

abstract = "This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay belonging to a given interval. By constructing a novel augmented Lyapunov functional which contains some triple-integral terms, improved delay-dependent stability criteria are derived in terms of linear matrix inequality (LMI) by introducing some free-weighting matrices and using integral inequality technique and convex combination method. Numerical examples are given to illustrate the effectiveness of the proposed method.",

keywords = "Delay-dependent stability, Interval time-varying delay, Linear matrix inequality, Recurrent neural network",

author = "Bai, {Yong Qiang} and Jie Chen",

year = "2013",

month = dec,

day = "9",

doi = "10.1016/j.neucom.2013.04.031",

language = "English",

volume = "121",

pages = "179--184",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - New stability criteria for recurrent neural networks with interval time-varying delay

AU - Bai, Yong Qiang

AU - Chen, Jie

PY - 2013/12/9

Y1 - 2013/12/9

N2 - This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay belonging to a given interval. By constructing a novel augmented Lyapunov functional which contains some triple-integral terms, improved delay-dependent stability criteria are derived in terms of linear matrix inequality (LMI) by introducing some free-weighting matrices and using integral inequality technique and convex combination method. Numerical examples are given to illustrate the effectiveness of the proposed method.

AB - This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay belonging to a given interval. By constructing a novel augmented Lyapunov functional which contains some triple-integral terms, improved delay-dependent stability criteria are derived in terms of linear matrix inequality (LMI) by introducing some free-weighting matrices and using integral inequality technique and convex combination method. Numerical examples are given to illustrate the effectiveness of the proposed method.

KW - Delay-dependent stability

KW - Interval time-varying delay

KW - Linear matrix inequality

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=84884151990&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2013.04.031

DO - 10.1016/j.neucom.2013.04.031

M3 - Article

AN - SCOPUS:84884151990

SN - 0925-2312

VL - 121

SP - 179

EP - 184

JO - Neurocomputing

JF - Neurocomputing

ER -

New stability criteria for recurrent neural networks with interval time-varying delay

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this