Global robust exponential stability analysis for interval recurrent neural networks

被引：117

作者：

Xu, SY

Lam, J

Ho, DWC

Zou, Y

机构：

[1] Univ Hong Kong, Dept Mech Engn, Hong Kong, Hong Kong, Peoples R China

[2] Nanjing Univ Sci & Technol, Dept Automat, Nanjing 210094, Peoples R China

[3] City Univ Hong Kong, Dept Math, Kowloon, Hong Kong, Peoples R China

来源：

PHYSICS LETTERS A | 2004年 / 325卷 / 02期

基金：

中国国家自然科学基金;

关键词：

recurrent neural networks; global exponential stability; interval systems; linear matrix inequality;

D O I：

10.1016/j.physleta.2004.03.038

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

This Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via the linear matrix inequality (LMI) approach. The values of the time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition for the existence of a unique equilibrium point and its global exponential stability of RNNs with known parameters is proposed. Based on this, a sufficient condition for the global robust exponential stability for interval RNNs is obtained. Both of the conditions are expressed in terms of LMIs, which can be checked easily by various recently developed convex optimization algorithms. Examples are provided to demonstrate the reduced conservatism of the proposed exponential stability condition. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：124 / 133

页数：10

共 19 条

[11] Global stability of a class of continuous-time recurrent neural networks [J].

Hu, SQ ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2002, 49 (09) :1334-1347

[12]

JUANG YT, 1989, INT J CONTROL, V49, P1401, DOI 10.1080/00207178908961321

[13]

Kohonen T., 2001, INFORM SCIENCES

[14] Novel robust stability criteria for interval-delayed Hopfield neural networks [J].

Liao, XF ;

Wong, KW ;

Wu, ZF ;

Chen, GR .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2001, 48 (11) :1355-1359

[15] STABILITY CONDITIONS FOR NONLINEAR CONTINUOUS NEURAL NETWORKS WITH ASYMMETRIC CONNECTION WEIGHTS [J].

MATSUOKA, K .

NEURAL NETWORKS, 1992, 5 (03) :495-500

[16] ANALYSIS AND SYNTHESIS OF NEURAL NETWORKS WITH LOWER BLOCK TRIANGULAR INTERCONNECTING STRUCTURE [J].

MICHEL, AN ;

GRAY, DL .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (10) :1267-1283

[17] QUALITATIVE-ANALYSIS OF NEURAL NETWORKS [J].

MICHEL, AN ;

FARRELL, JA ;

POROD, W .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (02) :229-243

[18] On the stability of globally projected dynamical systems [J].

Xia, YS ;

Wang, J .

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2000, 106 (01) :129-150

[19] Robust H∞ filtering for uncertain Markovian jump systems with mode-dependent time delays. [J].

Xu, SY ;

Chen, TW ;

Lam, J .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2003, 48 (05) :900-907

← 1 2 →