Novel Stability Analysis for Recurrent Neural Networks with Multiple Delays via Line Integral-Type L-K Functional

被引：84

作者：

Liu, Zhenwei ^{[1
,2
]}

Zhang, Huaguang ^{[1
,2
]}

Zhang, Qingling ^{[3
]}

机构：

[1] Northeastern Univ, Coll Informat Sci & Engn, Sch Informat Sci & Engn, Shenyang 110004, Liaoning, Peoples R China

[2] Northeastern Univ, Key Lab Integrated Automat Proc Ind, Natl Educ Minist, Shenyang 110004, Liaoning, Peoples R China

[3] Northeastern Univ, Inst Syst Sci, Shenyang 110004, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2010年 / 21卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Augmented matrix-vector transformation; global asymptotical stability; line integral-type Lyapunov-Krasovskii (L-K) functional; multiple delays; recurrent neural networks (RNNs); GLOBAL EXPONENTIAL STABILITY; ASYMPTOTIC STABILITY; ROBUST STABILITY; CRITERIA;

D O I：

10.1109/TNN.2010.2054107

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 studies the stability problem of a class of recurrent neural networks (RNNs) with multiple delays. By using an augmented matrix-vector transformation for delays and a novel line integral-type Lyapunov-Krasovskii functional, a less conservative delay-dependent global asymptotical stability criterion is first proposed for RNNs with multiple delays. The obtained stability result is easy to check and improve upon the existing ones. Then, two numerical examples are given to verify the effectiveness of the proposed criterion.

引用

页码：1710 / 1718

页数：9

共 41 条

[1] Global asymptotic stability of a larger class of neural networks with constant time delay
Arik, S
[J]. PHYSICS LETTERS A, 2003, 311 (06) : 504 - 511
[2] Global asymptotic and robust stability of recurrent neural networks with time delays
Cao, JD
Wang, J
[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
Cao, JD
Wang, J
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2005, 52 (05) : 920 - 931
[4] Stability analysis of delayed cellular neural networks
Cao, JD
Zhou, DM
[J]. NEURAL NETWORKS, 1998, 11 (09) : 1601 - 1605
[5] Chen M., 1997, APPROXIMATE SOLUTION
[6] Global exponential stability of delayed Hopfield neural networks
Chen, TP
[J]. NEURAL NETWORKS, 2001, 14 (08) : 977 - 980
[7] Neurocomputing with time delay analysis for solving convex quadratic programming problems
Chen, YH
Fang, SC
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01): : 230 - 240
[8] CELLULAR NEURAL NETWORKS - APPLICATIONS
CHUA, LO
YANG, L
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10): : 1273 - 1290
[9] Cellular neural network approach to a class of communication problems
Fantacci, R
Forti, M
Marini, M
Pancani, L
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (12): : 1457 - 1467
[10] A SYNTHESIS PROCEDURE FOR HOPFIELD CONTINUOUS-TIME ASSOCIATIVE MEMORY
FARRELL, JA
MICHEL, AN
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (07): : 877 - 884

← 1 2 3 4 5 →