Multiple ψ-Type Stability and Its Robustness for Recurrent Neural Networks With Time-Varying Delays

被引：26
作者：
Zhang, Fanghai [1 ]
Zeng, Zhigang [1 ]
机构：
[1] Huazhong Univ Sci & Technol, Guangdong Prov Key Lab Digital Mfg Equipment, Key Lab Image Proc & Intelligent Control Educ,Sch, Guangdong HUST Ind Technol Res Inst,Minist China, Wuhan 430074, Hubei, Peoples R China
来源：
IEEE TRANSACTIONS ON CYBERNETICS | 2019年 / 49卷 / 05期
关键词：
Multiple psi-type stability; recurrent neural networks (RNNs); robustness; time-varying delays; GLOBAL EXPONENTIAL STABILITY; LINEAR ACTIVATION FUNCTIONS; ASYMPTOTIC STABILITY; LAGRANGE STABILITY; MU-STABILITY; FINITE-TIME; MULTISTABILITY; CONVERGENCE; SYNCHRONIZATION; SYSTEMS;
D O I：
10.1109/TCYB.2018.2813979
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, the psi-type stability and robustness of recurrent neural networks are investigated by using the differential inequality. By utilizing psi-type functions combined with the inequality techniques, some sufficient conditions ensuring psi-type stability and robustness are derived for linear neural networks with time-varying delays. Then, by choosing appropriate Lipschitz coefficient in subregion, some algebraic criteria of the multiple psi-type stability and robust boundedness are established for the delayed neural networks with time-varying delays. For special cases, several criteria are also presented by selecting parameters with easy implementation. The derived results cover both psi-type mono-stability and multiple psi-type stability. In addition, these theoretical results contain exponential stability, polynomial stability, and mu-stability, and they also complement and extend some previous results. Finally, two numerical examples are provided to illustrate the effectiveness of the proposed criteria.
引用
收藏
页码：1803 / 1815
页数：13
相关论文
共 55 条
[1]  
Aubin J., 1984, Differential Inclusions: Set-Valued Maps and Viability Theory
[2]   Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions [J].
Bao, Gang ;
Zeng, Zhigang .
NEUROCOMPUTING, 2012, 77 (01) :101-107
[3]   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
[4]   Global robust stability of delayed recurrent neural networks [J].
Cao, JD ;
Huang, DS ;
Qu, YZ .
CHAOS SOLITONS & FRACTALS, 2005, 23 (01) :221-229
[5]   Global μ-stability of delayed neural networks with unbounded time-varying delays [J].
Chen, Tianping ;
Wang, Lili .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (06) :1836-1840
[6]   Multistability of complex-valued neural networks with time-varying delays [J].
Chen, Xiaofeng ;
Zhao, Zhenjiang ;
Song, Qiankun ;
Hu, Jin .
APPLIED MATHEMATICS AND COMPUTATION, 2017, 294 :18-35
[7]   Multistability in recurrent neural networks [J].
Cheng, Chang-Yuan ;
Lin, Kuang-Hui ;
Shih, Chih-Wen .
SIAM JOURNAL ON APPLIED MATHEMATICS, 2006, 66 (04) :1301-1320
[8]   Multistability for Delayed Neural Networks via Sequential Contracting [J].
Cheng, Chang-Yuan ;
Lin, Kuang-Hui ;
Shih, Chih-Wen ;
Tseng, Jui-Pin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (12) :3109-3122
[9]   CELLULAR NEURAL NETWORKS - APPLICATIONS [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290
[10]  
Clarke F.H., 1998, Nonsmooth analysis and control theory, DOI 10.1007/b97650
123456