Robust exponential stability criterion for uncertain neural networks with discontinuous activation functions and time-varying delays

被引：33

作者：

Wu, Xiru ^{[1
]}

Wang, Yaonan ^{[1
]}

Huang, Lihong ^{[2
]}

Zuo, Yi ^{[3
,4
]}

机构：

[1] Hunan Univ, Coll Elect & Informat Technol, Changsha 410082, Hunan, Peoples R China

[2] Hunan Univ, Coll Math & Econometr, Changsha 410082, Hunan, Peoples R China

[3] Changsha Univ Sci & Technol, Sch Energy & Power Engn, Changsha 410004, Hunan, Peoples R China

[4] Univ Guelph, Sch Engn, ARIS Lab, Guelph, ON N2L 2W1, Canada

来源：

NEUROCOMPUTING | 2010年 / 73卷 / 7-9期

关键词：

Delayed neural networks; Global robust exponential stability; LMIs; Discontinuous activation functions; Norm-bounded uncertainties; DYNAMICAL BEHAVIORS; GLOBAL CONVERGENCE; PERIODIC-SOLUTION; SYSTEMS; NORM;

D O I：

10.1016/j.neucom.2010.01.002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper considers the global robust exponential stability of time-varying delayed neural networks with discontinuous activation functions and norm-bounded uncertainties. Based on the Lyapunov-Krasovskii stability theory, we originally analyze the global robust exponential stability of discontinuous neural networks with time-varying delays in view of the linear matrix inequalities (LMIs). Therefore, our results are brand new compared to previous literatures. A numerical example is given to validate the effectiveness of our results. (C) 2010 Elsevier B.V. All rights reserved.

引用

页码：1265 / 1271

页数：7

共 36 条

[1]

[Anonymous], 1988, Differential Equations with Discontinuous Righthand Sides

[2]

Aubin J.P., 1984, DIFFERENTIAL INCLUSI

[3]

BACIOTTI A, 2000, DISCONTINUOUS ORDINA

[4]

Boyd S., 1994, LINEAR MATRIX INEQUA

[5] Global asymptotic and robust stability of recurrent neural networks with time delays [J].

Cao, JD ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2005, 52 (02) :417-426

[6] New LMI conditions for global exponential stability of cellular neural networks with delays [J].

Chen, Ling ;

Zhao, Hongyong .

NONLINEAR ANALYSIS-REAL WORLD APPLICATIONS, 2009, 10 (01) :287-297

[7] Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations [J].

Forti, A ;

Grazzini, A ;

Nistri, P ;

Pancioni, L .

PHYSICA D-NONLINEAR PHENOMENA, 2006, 214 (01) :88-99

[8] Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain [J].

Forti, M ;

Nistri, P ;

Papini, D .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (06) :1449-1463

[9] Global convergence of neural networks with discontinuous neuron activations [J].

Forti, M ;

Nistri, P .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2003, 50 (11) :1421-1435

[10] Global exponential stability for uncertain cellular neural networks with multiple time-varying delays via LMI approach [J].

Gau, R. S. ;

Lien, C. H. ;

Hsieh, J. G. .

CHAOS SOLITONS & FRACTALS, 2007, 32 (04) :1258-1267

← 1 2 3 4 →