Global exponential stability for discrete-time neural networks with variable delays

被引：72
作者：
Chen, Wu-Hua [1 ]
Lu, Xiaomei [1 ]
Liang, Dong-Ying [1 ]
机构：
[1] Guangxi Univ, Coll Math & Informat Sci, Nanning 530004, Guangxi, Peoples R China
来源：
PHYSICS LETTERS A | 2006年 / 358卷 / 03期
基金：
中国国家自然科学基金;
关键词：
neural networks; discrete-time systems; variable delays; globally exponential stability; delay-dependent criteria; M-matrix;
D O I：
10.1016/j.physleta.2006.05.014
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
This Letter provides new exponential stability criteria for discrete-time neural networks with variable delays. The main technique is to reduce exponential convergence estimation of the neural network solution to that of one component of the corresponding solution by constructing Lyapunov function based on M-matrix. By introducing the tuning parameter diagonal matrix, the delay-independent and delay-dependent exponential stability conditions have been unified in the same mathematical formula. The effectiveness of the new results are illustrated by three examples. (c) 2006 Elsevier B.V. All rights reserved.
引用
收藏
页码：186 / 198
页数：13
相关论文
共 17 条
[1]   On exponential stability and periodic solutions of CNNs with delays [J].
Cao, J .
PHYSICS LETTERS A, 2000, 267 (5-6) :312-318
[2]   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
[3]   Global exponential stability and periodicity of recurrent neural networks with time delays [J].
Cao, JD ;
Wang, J .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2005, 52 (05) :920-931
[4]   New results concerning exponential stability and periodic solutions of delayed cellular neural networks [J].
Cao, JD .
PHYSICS LETTERS A, 2003, 307 (2-3) :136-147
[5]   Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays [J].
Cao, JD ;
Wang, J .
NEURAL NETWORKS, 2004, 17 (03) :379-390
[6]   Periodic oscillation and exponential stability of delayed CNNs [J].
Cao, JD .
PHYSICS LETTERS A, 2000, 270 (3-4) :157-163
[7]   New delay-dependent exponential stability criteria for neural networks with variable delays [J].
Chen, WH ;
Lu, XM .
PHYSICS LETTERS A, 2006, 351 (1-2) :53-58
[8]   Delay-dependent exponential stability of neural networks with variable delays [J].
Chen, WH ;
Guan, ZH ;
Lu, XM .
PHYSICS LETTERS A, 2004, 326 (5-6) :355-363
[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]   Global stability and existence of periodic solutions of discrete delayed cellular neural networks [J].
Li, YK .
PHYSICS LETTERS A, 2004, 333 (1-2) :51-61
12