LMI-based approach for asymptotically stability analysis of delayed neural networks

Xiaofeng Liao; Guanrong Chen; Edgar N. Sanchez

doi:10.1109/TCSI.2002.800842

LMI-based approach for asymptotically stability analysis of delayed neural networks

Xiaofeng Liao
, Guanrong Chen
, Edgar N. Sanchez

Department of Electrical Engineering

Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal

357 Citations (Scopus)

Abstract

This paper derives some sufficient conditions for asymptotic stability of neural networks with constant or time-varying delays. The Lyapunov-Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) approach are employed to investigate the problem. It shows how some well-known results can be refined and generalized in a straightforward manner. For the case of constant time delays, the stability criteria are delay-independent; for the case of time-varying delays, the stability criteria are delay-dependent. The results obtained in this paper are less conservative than the ones reported so far in the literature and provides one more set of criteria for determining the stability of delayed neural networks.

Original language	English
Pages (from-to)	1033-1039
Journal	IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Volume	49
Issue number	7
DOIs	https://doi.org/10.1109/TCSI.2002.800842
Publication status	Published - Jul 2002

Research Keywords

Asymptotical stability
Linear matrix inequality
Lyapunov-Krasovskii functional
Neural networks
Time delays

Access Output

10.1109/TCSI.2002.800842

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{7216056643c04d09a6c6b26f186c065b,

title = "LMI-based approach for asymptotically stability analysis of delayed neural networks",

abstract = "This paper derives some sufficient conditions for asymptotic stability of neural networks with constant or time-varying delays. The Lyapunov-Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) approach are employed to investigate the problem. It shows how some well-known results can be refined and generalized in a straightforward manner. For the case of constant time delays, the stability criteria are delay-independent; for the case of time-varying delays, the stability criteria are delay-dependent. The results obtained in this paper are less conservative than the ones reported so far in the literature and provides one more set of criteria for determining the stability of delayed neural networks.",

keywords = "Asymptotical stability, Linear matrix inequality, Lyapunov-Krasovskii functional, Neural networks, Time delays",

author = "Xiaofeng Liao and Guanrong Chen and Sanchez, \{Edgar N.\}",

year = "2002",

month = jul,

doi = "10.1109/TCSI.2002.800842",

language = "English",

volume = "49",

pages = "1033--1039",

journal = "IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications",

issn = "1057-7122",

publisher = "IEEE",

number = "7",

}

TY - JOUR

T1 - LMI-based approach for asymptotically stability analysis of delayed neural networks

AU - Liao, Xiaofeng

AU - Chen, Guanrong

AU - Sanchez, Edgar N.

PY - 2002/7

Y1 - 2002/7

N2 - This paper derives some sufficient conditions for asymptotic stability of neural networks with constant or time-varying delays. The Lyapunov-Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) approach are employed to investigate the problem. It shows how some well-known results can be refined and generalized in a straightforward manner. For the case of constant time delays, the stability criteria are delay-independent; for the case of time-varying delays, the stability criteria are delay-dependent. The results obtained in this paper are less conservative than the ones reported so far in the literature and provides one more set of criteria for determining the stability of delayed neural networks.

AB - This paper derives some sufficient conditions for asymptotic stability of neural networks with constant or time-varying delays. The Lyapunov-Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) approach are employed to investigate the problem. It shows how some well-known results can be refined and generalized in a straightforward manner. For the case of constant time delays, the stability criteria are delay-independent; for the case of time-varying delays, the stability criteria are delay-dependent. The results obtained in this paper are less conservative than the ones reported so far in the literature and provides one more set of criteria for determining the stability of delayed neural networks.

KW - Asymptotical stability

KW - Linear matrix inequality

KW - Lyapunov-Krasovskii functional

KW - Neural networks

KW - Time delays

UR - https://www.scopus.com/pages/publications/0036647562

UR - https://www.scopus.com/pages/publications/0036647562#tab=impact

U2 - 10.1109/TCSI.2002.800842

DO - 10.1109/TCSI.2002.800842

M3 - RGC 22 - Publication in policy or professional journal

SN - 1057-7122

VL - 49

SP - 1033

EP - 1039

JO - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

JF - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

IS - 7

ER -

LMI-based approach for asymptotically stability analysis of delayed neural networks

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Corrections to "LMI-based Approach for Asymptotically Stability Analysis of Delayed Neural Networks"

Cite this