Robust Stability Criterion for Delayed Neural Networks with Discontinuous Activation Functions

被引：26

作者：

Zuo, Yi ^{[1
,2
]}

Wang, Yaonan ^{[1
]}

Huang, Lihong ^{[3
]}

Wang, Zengyun ^{[3
]}

Liu, Xinzhi ^{[2
]}

Wu, Xiru ^{[1
]}

机构：

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

[2] Univ Waterloo, Dept Appl Math, Waterloo, ON N2L 3G1, Canada

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

来源：

NEURAL PROCESSING LETTERS | 2009年 / 29卷 / 01期

基金：

加拿大自然科学与工程研究理事会; 国家高技术研究发展计划(863计划); 中国国家自然科学基金;

关键词：

Delayed neural network; Global stability; Linear matrix inequality; Discontinuous neuron activations; Norm-bounded uncertain; GLOBAL EXPONENTIAL STABILITY; DYNAMICAL BEHAVIORS; LMI APPROACH; CONVERGENCE; TIME; SYSTEMS; MATRIX; NORM;

D O I：

10.1007/s11063-008-9093-x

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The problem of global robust stability for a class of uncertain delayed neural networks with discontinuous activation functions has been discussed. The uncertainty is assumed to be of norm-bounded form. Based on Lyapunov-Krasovskii stability theory as well as Filippov theory, the conditions are expressed in terms of linear matrix inequality, which make them computationally efficient and flexible. An illustrative numerical example is also given to show the applicability and effectiveness of the proposed results.

引用

页码：29 / 44

页数：16

共 30 条

[1]

Aubin J., 1984, DIFFERENTIAL INCLUSI

[2]

BACIOTTI A, 2000, DISCONTINUOUS ORDINA

[3]

Boyd S., 1994, LINEAR MATRIX INEQUA

[4] 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

[5]

CLARKE F, 1994, OPTIMIZATION NONSMOO

[6]

Filippov A. F., 1988, Differential Equations with Discontinuous Righthand Sides

[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]

Hale J., 1994, ORDINARY DIFFERENTIA

← 1 2 3 →