New delay-dependent stability criteria for recurrent neural networks with time-varying delays

被引：50
|
作者：
Yang, Bin [1 ]
Wang, Rui [2 ]
Shi, Peng [3 ,4 ]
Dimirovski, Georgi M. [5 ,6 ]
机构：
[1] Dalian Univ Technol, Sch Control Sci & Engn, Dalian 116024, Peoples R China
[2] Dalian Univ Technol, Sch Aeronaut & Astronaut, State Key Lab Struct Anal Ind Equipment, Dalian 116024, Peoples R China
[3] Harbin Engn Univ, Coll Automat, Harbin 150001, Peoples R China
[4] Victoria Univ, Coll Engn & Sci, Melbourne, Vic 8001, Australia
[5] Dogus Univ, Sch Engn, TR-34722 Istanbul, Turkey
[6] Univ St Cyril & Methudius, Sch FEIT, MK-1000 Skopje, Macedonia
来源：
NEUROCOMPUTING | 2015年 / 151卷
基金：
澳大利亚研究理事会; 中国国家自然科学基金;
关键词：
Recurrent neural networks; Stability; Lyapunov-Krasovskii functional; Time-varying delays; GLOBAL EXPONENTIAL STABILITY; ROBUST STABILITY; SYSTEMS;
D O I：
10.1016/j.neucom.2014.10.048
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This work is concerned with the delay-dependentstability problem for recurrent neural networks with time-varying delays. A new improved delay-dependent stability criterion expressed in terms of linear matrix inequalities is derived by constructing a dedicated Lyapunov-Krasovskii functional via utilizing Wirtinger inequality and convex combination approach. Moreover, a further improved delay-dependent stability criterion is established by means of a new partitioning method for bounding conditions on the activation function and certain new activation function conditions presented. Finally, the application of these novel results to an illustrative example from the literature has been investigated and their effectiveness is shown via comparison with the existing recent ones. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码：1414 / 1422
页数：9
相关论文
共 50 条
  • [21] New delay-dependent criterion for the stability of recurrent neural networks with time-varying delay
    Zhang HuaGuang
    Wang ZhanShan
    SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2009, 52 (06): : 942 - 948
  • [22] New delay-dependent stability criteria for impulsive neural networks with time-varying delay
    Ji Yan
    Liu Ximei
    Wang Longjin
    PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 3075 - 3079
  • [23] New delay-dependent criterion for the stability of recurrent neural networks with time-varying delay
    ZHANG HuaGuang WANG ZhanShan School of Information Science and Engineering Northeastern University Shenyang China
    ScienceinChina(SeriesF:InformationSciences), 2009, 52 (06) : 942 - 948
  • [24] Improved delay-dependent exponential stability criteria for discrete-time recurrent neural networks with time-varying delays
    Zhang, Baoyong
    Xu, Shengyuan
    Zou, Yun
    NEUROCOMPUTING, 2008, 72 (1-3) : 321 - 330
  • [25] New delay-dependent criterion for the stability of recurrent neural networks with time-varying delay
    ZHANG HuaGuang & WANG ZhanShan School of Information Science and Engineering
    Science China(Information Sciences), 2009, (06) : 942 - 948
  • [26] New delay-dependent criterion for the stability of recurrent neural networks with time-varying delay
    HuaGuang Zhang
    ZhanShan Wang
    Science in China Series F: Information Sciences, 2009, 52 : 942 - 948
  • [27] Delay-dependent asymptotic stability for neural networks with time-varying delays
    Liao, Xiaofeng
    Yang, Xiaofan
    Zhang, Wei
    DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2006, 2006
  • [28] Analysis on delay-dependent stability for neural networks with time-varying delays
    Kwon, O. M.
    Park, Ju H.
    Lee, S. M.
    Cha, E. J.
    NEUROCOMPUTING, 2013, 103 : 114 - 120
  • [29] Delay-dependent asymptotic stability of neural networks with time-varying delays
    Xu, Shengyuan
    Lam, James
    Ho, Daniel W. C.
    INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2008, 18 (01): : 245 - 250
  • [30] Delay-Dependent Stability Criteria for Reaction-Diffusion Neural Networks With Time-Varying Delays
    Ma, Qian
    Feng, Gang
    Xu, Shengyuan
    IEEE TRANSACTIONS ON CYBERNETICS, 2013, 43 (06) : 1913 - 1920
12345