Exponential stability of Cohen-Grossberg neural networks

被引：227

作者：

Wang, L

Zou, XF ^{[1
]}

机构：

[1] Mem Univ Newfoundland, Dept Math & Stat, St John, NF A1C 5S7, Canada

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

来源：

NEURAL NETWORKS | 2002年 / 15卷 / 03期

基金：

加拿大自然科学与工程研究理事会;

关键词：

exponential stability; componentwise exponential stability; neural networks; Liapunov function/functional; comparison; quasi-monotonicity;

D O I：

10.1016/S0893-6080(02)00025-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Exponential stabilities of the Cohen-Grossberg neural network with and without delays are analyzed. By Liapunov functions/functionals, sufficient conditions are obtained for general exponential stability, while by using a comparison result from the theory of monotone dynamical systems, componentwise exponential stability is also discussed. All results are established without assuming any symmetry of the connection matrix, and the differentiability and monotonicity of the activation functions. (C) 2002 Published by Elsevier Science Ltd.

引用

页码：415 / 422

页数：8

共 19 条

[1]

Belair J., 1993, Journal of Dynamics and Differential Equations, V5, P607, DOI 10.1007/BF01049141

[2] A note on stability of analog neural networks with time delays [J].

Cao, YJ ;

Wu, QH .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (06) :1533-1535

[3] ABSOLUTE STABILITY OF GLOBAL PATTERN-FORMATION AND PARALLEL MEMORY STORAGE BY COMPETITIVE NEURAL NETWORKS [J].

COHEN, MA ;

GROSSBERG, S .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :815-826

[4] A CONDITION FOR GLOBAL CONVERGENCE OF A CLASS OF SYMMETRICAL NEURAL CIRCUITS [J].

FORTI, M ;

MANETTI, S ;

MARINI, M .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1992, 39 (06) :480-483

[5] ON GLOBAL ASYMPTOTIC STABILITY OF A CLASS OF NONLINEAR-SYSTEMS ARISING IN NEURAL-NETWORK THEORY [J].

FORTI, M .

JOURNAL OF DIFFERENTIAL EQUATIONS, 1994, 113 (01) :246-264

[6] STABILITY IN ASYMMETRIC HOPFIELD NETS WITH TRANSMISSION DELAYS [J].

GOPALSAMY, K ;

HE, XZ .

PHYSICA D-NONLINEAR PHENOMENA, 1994, 76 (04) :344-358

[7] On equilibria, stability, and instability of hopfield neural networks [J].

Guan, ZH ;

Chen, GR ;

Qin, Y .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02) :534-540

[8] CONVERGENT ACTIVATION DYNAMICS IN CONTINUOUS-TIME NETWORKS [J].

HIRSCH, MW .

NEURAL NETWORKS, 1989, 2 (05) :331-349

[9] 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

[10] Results concerning the absolute stability of delayed neural networks [J].

Joy, M .

NEURAL NETWORKS, 2000, 13 (06) :613-616

← 1 2 →