Improved free-weighting matrix approach for stability analysis of discrete-time recurrent neural networks with time-varying delay

被引：55

作者：

Wu, Min ^{[1
]}

Liu, Fang ^{[1
]}

Shi, Peng ^{[2
]}

He, Yong ^{[1
]}

Yokoyama, Ryuichi ^{[3
]}

机构：

[1] Cent S Univ, Sch Informat Sci & Engn, Changsha 410083, Peoples R China

[2] Univ Glamorgan, Facil Adv Technol, Pontypridd CF37 1DL, M Glam, Wales

[3] Waseda Univ, Grad Sch Environm & Energy Engn 513, Tokyo 1620041, Japan

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS | 2008年 / 55卷 / 07期

基金：

中国国家自然科学基金;

关键词：

discrete-time recurrent neural networks; time-varying delay; delay-dependent stability; Lyapunov function; linear matrix inequalities (LMIs);

D O I：

10.1109/TCSII.2008.921597

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper deals with the problem of exponential stability for a class of discrete-time recurrent neural networks with time-varying delay by employing an improved free-weighting matrix approach. The relationship among the time-varying delay, its upper bound and their difference is taken into account. As a result, a new and less conservative delay-dependent stability criterion is obtained without ignoring any useful terms on the difference of a Lyapunov function, which is expressed in terms of linear matrix inequalities. Finally, numerical examples are given to demonstrate the effectiveness of the proposed techniques.

引用

页码：690 / 694

页数：5

共 30 条

[1] Global robust stability analysis of neural networks with discrete time delays [J].

Arik, S .

CHAOS SOLITONS & FRACTALS, 2005, 26 (05) :1407-1414

[2] On the global asymptotic stability of delayed cellular neural networks [J].

Arik, S ;

Tavsanoglu, V .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (04) :571-574

[3] 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

[4] 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

[5]

Chen B, 2006, INT J INNOV COMPUT I, V2, P293

[6] Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations [J].

Chen, Hsin-Chieh ;

Hung, Yung-Ching ;

Chen, Chang-Kuo ;

Liao, Teh-Lu ;

Chen, Chun-Kuo .

CHAOS SOLITONS & FRACTALS, 2006, 29 (05) :1100-1108

[7] Global exponential stability for discrete-time neural networks with variable delays [J].

Chen, Wu-Hua ;

Lu, Xiaomei ;

Liang, Dong-Ying .

PHYSICS LETTERS A, 2006, 358 (03) :186-198

[8]

Fekih A, 2007, INT J INNOV COMPUT I, V3, P1073

[9] LEARNING THE INITIAL-STATE OF A 2ND-ORDER RECURRENT NEURAL-NETWORK DURING REGULAR-LANGUAGE INFERENCE [J].

FORCADA, ML ;

CARRASCO, RC .

NEURAL COMPUTATION, 1995, 7 (05) :923-930

[10] Further improvement of free-weighting matrices technique for systems with time-varying delay [J].

He, Yong ;

Wang, Qing-Guo ;

Xie, Lihua ;

Lin, Chong .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2007, 52 (02) :293-299

← 1 2 3 →