Robust synchronization criteria for recurrent neural networks via linear feedback

被引：12
作者：
Huang, Xia [1 ,2 ]
Lam, James [3 ]
Cao, Jinde [1 ]
Xu, Shengyuan [4 ]
机构：
[1] SE Univ, Dept Math, Nanjing 210096, Peoples R China
[2] Shandong Univ Sci & Technol, Coll Informat & Elect Engn, Qingdao 266510, Peoples R China
[3] Univ Hong Kong, Dept Engn Mech, Hong Kong, Peoples R China
[4] Univ Sci & Technol, Dept Automat, Nanjing 210094, Peoples R China
来源：
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS | 2007年 / 17卷 / 08期
基金：
中国国家自然科学基金;
关键词：
robust synchronization; recurrent neural networks; Lyapunov-Krasovskii function; linear matrix inequality;
D O I：
10.1142/S0218127407018713
中图分类号：
O1 [数学];
学科分类号：
0701 ; 070101 ;
摘要：
In this paper, the robust synchronization problem is addressed for recurrent neural networks with time-varying delay by linear feedback control. Robustness in the present paper is referred to as the allowance of parameters mismatch between the drive system and the response system. Sufficient conditions for robust synchronization with a synchronization error bound, expressed as linear matrix inequality (LMI), are derived based on Lyapunov-Krasovskii functionals. Both delay-dependent and delay-independent conditions are obtained. Two examples are given to illustrate the results.
引用
收藏
页码：2723 / 2738
页数：16
相关论文
共 36 条
[1]   Synchronization of Rossler and Chen chaotic dynamical systems using active control [J].
Agiza, HN ;
Yassen, MT .
PHYSICS LETTERS A, 2001, 278 (04) :191-197
[2]   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
[3]   Sequential synchronization of two Lorenz systems using active control [J].
Bai, EW ;
Lonngren, KE .
CHAOS SOLITONS & FRACTALS, 2000, 11 (07) :1041-1044
[4]   The synchronization of chaotic systems [J].
Boccaletti, S ;
Kurths, J ;
Osipov, G ;
Valladares, DL ;
Zhou, CS .
PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS, 2002, 366 (1-2) :1-101
[5]   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
[6]   Adaptive synchronization of neural networks with or without time-varying delay [J].
Cao, JD ;
Lu, JQ .
CHAOS, 2006, 16 (01)
[7]   Synchronization criteria of Lur'e systems with time-delay feedback control [J].
Cao, JD ;
Li, HX ;
Ho, DWC .
CHAOS SOLITONS & FRACTALS, 2005, 23 (04) :1285-1298
[8]   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
[9]   Stability in Cohen-Grossberg-type bidirectional associative memory neural networks with time-varying delays [J].
Cao, Jinde ;
Song, Qiankun .
NONLINEARITY, 2006, 19 (07) :1601-1617
[10]   Global synchronization of coupled delayed neural networks and applications to chaotic CNN models [J].
Chen, GR ;
Zhou, J ;
Liu, ZR .
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2004, 14 (07) :2229-2240
1234