New global asymptotic stability of discrete-time recurrent neural networks with multiple time-varying delays in the leakage term and impulsive effects

被引：20

作者：

Balasundaram, K. ^{[1
]}

Raja, R. ^{[2
]}

Zhu, Quanxin ^{[3
,4
,5
]}

Chandrasekaran, S. ^{[6
]}

Zhou, Hongwei ^{[7
]}

机构：

[1] Sri Vijay Vidyalaya Coll Arts & Sci, Dept Math, Dharmapuri 636807, India

[2] Alagappa Univ, Ramanujan Ctr Higher Math, Karaikkudi 630004, Tamil Nadu, India

[3] Nanjing Normal Univ, Sch Math Sci, Nanjing 210023, Jiangsu, Peoples R China

[4] Nanjing Normal Univ, Inst Finance & Stat, Nanjing 210023, Jiangsu, Peoples R China

[5] Univ Bielefeld, Dept Math, D-33615 Bielefeld, Germany

[6] Khadir Mohideen Coll, Dept Math, Adirampattinam 614701, Thanjavur, India

[7] Nanjing Xiaozhuang Univ, Sch Math & Informat Technol, Nanjing 211171, Jiangsu, Peoples R China

来源：

NEUROCOMPUTING | 2016年 / 214卷

基金：

中国国家自然科学基金;

关键词：

Leakage delay; Asymptotic stability; Recurrent neural network; Delay-dependent; Linear matrix inequality; Impulse; Time-varying delay; EXPONENTIAL STABILITY; NEUTRAL-TYPE; DEPENDENT STABILITY; DISTRIBUTED DELAYS; PASSIVITY ANALYSIS; CRITERIA; ANALOGS;

D O I：

10.1016/j.neucom.2016.06.040

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 investigates the problem of discrete-time stochastic recurrent neural networks with multiple time-varying delays in the leakage terms and impulses. A new set of sufficient conditions are obtained by constructing an appropriate Lyapunov-Krasovskii functional combining with linear matrix inequality technique and free weighting matrix method. The obtained delay-dependent stability conditions are expressed in terms of linear matrix inequalities and it can be solved via some available software packages. Up to now, the asymptotic stability problem is studied for discrete-delay in the leakage terms. For the first time in our paper, we have considered distributed delays and impulses for such kind of networks. In addition, we have provided a numerical example to demonstrate the effectiveness of our obtained stability results for the theoretical section. (C) 2016 Elsevier B.V. All rights reserved.

引用

页码：420 / 429

页数：10

共 36 条

[1]

[Anonymous], 2001, ADAPT LEARN SYST SIG, DOI 10.1002/047084535X

[2] Global robust asymptotic stability analysis of uncertain switched Hopfield neural networks with time delay in the leakage term [J].

Balasubramaniam, P. ;

Vembarasan, V. ;

Rakkiyappan, R. .

NEURAL COMPUTING & APPLICATIONS, 2012, 21 (07) :1593-1616

[3]

Boyd S., 1994, SIAM STUDIES APPL MA

[4] 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

[5] 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

[6] 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

[7] Improved passivity analysis for neural networks with Markovian jumping parameters and interval time-varying delays [J].

Chen, Guoliang ;

Xia, Jianwei ;

Zhuang, Guangming .

NEUROCOMPUTING, 2015, 155 :253-260

[8] Delay-dependent stability for neutral-type neural networks with time-varying delays and Markovian jumping parameters [J].

Chen, Weimin ;

Wang, Lanning .

NEUROCOMPUTING, 2013, 120 :569-576

[9] Global Exponential Stability of Antiperiodic Solutions for Discrete-Time Neural Networks with Mixed Delays and Impulses [J].

Chen, Xiaofeng ;

Song, Qiankun .

DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2012, 2012

[10] Global exponential stability of fuzzy BAM neural networks with distributed delays and time-varying delays in the leakage terms [J].

Duan, Lian ;

Huang, Lihong .

NEURAL COMPUTING & APPLICATIONS, 2013, 23 :S171-S178

← 1 2 3 4 →