Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

被引：135

作者：

Zeng, ZG ^{[1
]}

Wang, J

机构：

[1] Wuhan Univ Technol, Sch Automat, Wuhan 430070, Peoples R China

[2] Chinese Univ Hong Kong, Dept Automat & Comp Aided Engn, Shatin, Hong Kong, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2006年 / 17卷 / 03期

基金：

中国国家自然科学基金;

关键词：

external inputs; M-matrix; neural networks (NNs); stability; time-varying delay;

D O I：

10.1109/TNN.2006.873283

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 presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail.

引用

页码：623 / 635

页数：13

共 22 条

[1] An improved global stability result for delayed cellular neural networks [J].

Arik, S .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2002, 49 (08) :1211-1214

[2] Global asymptotic stability of a general class of recurrent neural networks with time-varying delays [J].

Cao, J ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2003, 50 (01) :34-44

[3] Global stability conditions for delayed CNNs [J].

Cao, J. .

IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2001, 48 (11) :1330-1333

[4] An estimation of upperbound of delays for global asymptotic stability of delayed Hopfield neural networks [J].

Chen, AP ;

Cao, JD ;

Huang, LH .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2002, 49 (07) :1028-1032

[5] Robust global exponential stability of Cohen-Grossberg neural networks with time delays [J].

Chen, TP ;

Rong, LB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15 (01) :203-206

[6] Equilibrium analysis of cellular neural networks [J].

Gilli, M ;

Biey, M ;

Checco, P .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2004, 51 (05) :903-912

[7] Time delays and stimulus-dependent pattern formation in periodic environments in isolated neurons [J].

Gopalsamy, K ;

Sariyasa .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (03) :551-563

[8] NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092

[9] Absolute exponential stability of a class of continuous-time recurrent neural networks [J].

Hu, SQ ;

Wang, J .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (01) :35-45

[10] Global exponential stability and periodic solutions of recurrent neural networks with delays [J].

Huang, H ;

Cao, JD ;

Wang, J .

PHYSICS LETTERS A, 2002, 298 (5-6) :393-404

← 1 2 3 →