Novel delay-probability-distribution-dependent mean square stability analysis for stochastic neural networks

详细信息    查看官网全文

• 英文论文题名：Novel delay-probability-distribution-dependent mean square stability analysis for stochastic neural networks
• 论文作者：LUO Jinnan ; TIAN Wenhong ; ZHONG Shouming ; SHI Kaibo ; WANG Wenqin
• 英文论文作者：LUO Jinnan ; TIAN Wenhong ; ZHONG Shouming ; SHI Kaibo ; WANG Wenqin ; School of Information and Software Engineering ; University of Electronic Science and Technology of China ; School of Mathematical Sciences ; University of Electronic Science and Technology of China ; School of Information Science and Engineering ; Chengdu University ; School of Sciences ; Tianjin Polytechnic University
• 年：2017
• 作者机构：School of Information and Software Engineering,University of Electronic Science and Technology of China;School of Mathematical Sciences,University of Electronic Science and Technology of China;School of Information Science and Engineering,Chengdu University;School of Sciences,Tianjin Polytechnic University;
• 英文论文关键词：Stochastic neural networks ; Probability-distribution ; Multiple delays
• 会议召开时间：2017-07-26
• 会议录名称：第36届中国控制会议论文集（B）
• 英文会议录名称：Proceedings of the 36th Chinese Control Conference（B）
• 语种：英文
• 分类号：TP183
• 学会代码：KZLL
• 会议名称：第36届中国控制会议
• 会议地点：中国辽宁大连
• 主办单位：中国自动化学会控制理论专业委员会
• 学会名称：中国自动化学会控制理论专业委员会
• 页数：6
• 文件大小：219k
• 原文格式：D
• 会议级别：全国

摘要

In this paper, the delay-probability-distribution-dependent stability problem for stochastic neural networks with various time-varying delays is investigated. By considering a new Lyapunov-Krasovskii functional(LKF) concluding more delaypartitioning term and combining free weight matrices and stochastic processing techniques, an improved delay-probabilitydistribution-dependent condition is built in terms of linear matrix inequality(LMI) so that the system is mean square stable.Finally, a numerical example is given to verify the effectiveness the proposed criterion.
In this paper, the delay-probability-distribution-dependent stability problem for stochastic neural networks with various time-varying delays is investigated. By considering a new Lyapunov-Krasovskii functional(LKF) concluding more delaypartitioning term and combining free weight matrices and stochastic processing techniques, an improved delay-probabilitydistribution-dependent condition is built in terms of linear matrix inequality(LMI) so that the system is mean square stable.Finally, a numerical example is given to verify the effectiveness the proposed criterion.

引文

[1]L.O.Chua,L.Yang,“Cellular neural networks:Applications,”IEEE Trans.Circuits Syst.,vol.35,no.10,PP.1273–1290,1998.
    [2]C.K.Zhang,Y.He,L.Jiang,M.Wu,“Stability analysis for delayed neural networks considering both conservativeness and complexity,”IEEE Trans.Neural Netw.Learn.Syst.vol.27,no.7,PP.1486–1501,2016.
    [3]H.B.Zeng,J.H.Par K,J.W.Xia,S.P.Xiao,“Improved delaydependent stability criteria for T-S fuzzy systems with timevarying delay,”Appl.Math.and Comput.vol.235,PP.492–501,2014.
    [4]H.Huang,T.Huang,X.Chen,“Guaranteed H∞performance state estimation of delayed static neural networks,”IEEE Trans.Circuits Syst.Express Briefs,vol.60,no.6,PP.371–375,2013.
    [5]H.Shen,Z.G.Wu,J.H.Park,“Reliable mixed passive and H∞filtering for semi-Markov jump systems with randomly occurring uncertainties and sensor failures,”Int J.Robust Nonlin.,vol.25,PP.3231–3251,2015
    [6]Z.C.Li,Y.Bai,C.Z.Huang,Y.F.Cai,“Novel delaypartitioning stabilization approach for networked control system via Wirtinger-based inequalities,”ISA Trans.,vol.61,PP.75–86,2016.
    [7]W.Kang,S.M.Zhong,J.Cheng,“Relaxed passivity conditions for discrete-time stochastic delayed neural networks,”Int J.Mach.Learn.Cyb.,vol.7,no.2,PP.205–216,2016.
    [8]M.Z.Luo,S.M.Zhong,“New delay-distribution-dependent stability analysis for discrete-time stochastic neural networks with randomly time-varying delays,”Neurocomputing,vol.116,PP.30–37,2013.
    [9]H.B.Bao,J.D.Cao,“Delay-distribution-dependent state estimation for discrete-time stochastic neural networks with random delay,”Neural Netw.,vol.24,PP.19–28,2011.
    [10]S.Muralisankar,A.Manivannan,P.Balasubramaniam,“Mean square delay dependent-probability-distribution stability analysis of neutral type stochastic neural networks,”ISA Trans.,vol.58,PP.11–19,2015.
    [11]J.K.Tian,W.J.Xiong,F.Xu,“Improved delay-partitioning method to stability analysis for neural networks with discrete and distributed time-varying delays,”Appl.Math.and Comput.vol.223,PP.152–164,2014.
    [12]C.Peng,Y.C.Tian,“Delay-dependent robust stability criteria for uncertain systems with interval time-varying delay,”J.Comput.Appl.Math.vol.214,no.2,PP.480–494,2008.
    [13]S.Y.Xu,J.Lam,“A new approach to exponential stability analysis of neural networks with time-varying delays,”Neural Netw.vol.19,PP.76–83,2006.
    [14]T.P.Zhang,B.Fang,Y.Yuan,Y.Y.Tang,Z.W.Shang,D.H.Li,F.N.Lang,“Multiscale facial structure representation for face recognition under varying illumination,”Pattern Recogn.vol.42,no.2,PP.251–258,2009.
    [15]T.P.Zhang,B.Fang,Y.Y.Tang,G.H.He,J.Wen,“Topology preserving non-negative matrix factorization for face recognition,”IEEE Trans.Image Processing.vol.17,no.4,PP.574–584,2008.