Input-to-state stability of discrete-time memristive neural networks with two delay components

被引：9

作者：

Fu, Qianhua ^{[1
,2
]}

Cai, Jingye ^{[1
]}

Zhong, Shouming ^{[3
]}

Yu, Yongbin ^{[1
]}

Shan, Yaonan ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 610054, Sichuan, Peoples R China

[2] Xihua Univ, Sch Elect Engn & Elect Informat, Chengdu 610039, Sichuan, Peoples R China

[3] Univ Elect Sci & Technol China, Sch Math Sci, Chengdu 611731, Sichuan, Peoples R China

来源：

NEUROCOMPUTING | 2019年 / 329卷

基金：

中国国家自然科学基金;

关键词：

Discrete-time memristive neural Networks; Input-to-state stability; Two additive time-varying components; Dynamic delay interval; GLOBAL EXPONENTIAL STABILITY; VARYING DELAYS; SYNCHRONIZATION; PASSIVITY; SYSTEMS;

D O I：

10.1016/j.neucom.2018.10.017

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a dynamic delay interval method is utilized to deal with the input-to-state stability problem of discrete-time memristive neural networks (DMNNs) with two delay components. This method relaxes the restriction on upper and lower bounds of the DMNNs delay intervals, which extends the fixed interval of a time-varying delay to a dynamic one. First, a tractable model of DMNNs is obtained via using semidiscretization technique. Furthermore, by constructing several novel Lyapunov-Krasovskii functionals, free-weighting matrices and using some techniques such as Refined Jensen-based inequalities, mathematical induction, we obtain some new sufficient conditions in the form of linear matrix inequality to ensure that the considered DMNNs with two time-varying delays are input-to-state stable. The input-to-state stability criteria for the DMNNs with two time-invariant delays are also provided. Finally, two numerical examples are presented to demonstrate the effectiveness of our theoretical results. (C) 2018 Elsevier B.V. All rights reserved.

引用

页码：1 / 11

页数：11

共 48 条

[1]

[Anonymous], 1994, P IEEE

[2] Region stability analysis and tracking control of memristive recurrent neural network [J].

Bao, Gang ;

Zeng, Zhigang ;

Shen, Yanjun .

NEURAL NETWORKS, 2018, 98 :51-58

[3] Synchronization of memristor-based recurrent neural networks with two delay components based on second-order reciprocally convex approach [J].

Chandrasekar, A. ;

Rakkiyappan, R. ;

Cao, Jinde ;

Lakshmanan, S. .

NEURAL NETWORKS, 2014, 57 :79-93

[4] MEMRISTOR - MISSING CIRCUIT ELEMENT [J].

CHUA, LO .

IEEE TRANSACTIONS ON CIRCUIT THEORY, 1971, CT18 (05) :507-+

[5] Stability of interconnected impulsive systems with and without time delays, using Lyapunov methods [J].

Dashkovskiy, Sergey ;

Kosmykov, Michael ;

Mironchenko, Andrii ;

Naujok, Lars .

NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2012, 6 (03) :899-915

[6] SMALL GAIN THEOREMS FOR LARGE SCALE SYSTEMS AND CONSTRUCTION OF ISS LYAPUNOV FUNCTIONS [J].

Dashkovskiy, Sergey N. ;

Rueffer, Bjoern S. ;

Wirth, Fabian R. .

SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2010, 48 (06) :4089-4118

[7]

Ding S., 2016, IEEE T NEUR NET LEAR, V99, P1

[8] H∞ state estimation for memristive neural networks with time-varying delays: The discrete-time case [J].

Ding, Sanbo ;

Wang, Zhanshan ;

Wang, Jidong ;

Zhang, Huaguang .

NEURAL NETWORKS, 2016, 84 :47-56

[9] Dissipativity and passivity analysis for memristor-based neural networks with leakage and two additive time-varying delays [J].

Fu, Qianhua ;

Cai, Jingye ;

Zhong, Shouming ;

Yu, Yongbin .

NEUROCOMPUTING, 2018, 275 :747-757

[10] Exponential input-to-state stability for complex-valued memristor-based BAM neural networks with multiple time-varying delays [J].

Guo, Runan ;

Zhang, Ziye ;

Liu, Xiaoping ;

Lin, Chong ;

Wang, Haixia ;

Chen, Jian .

NEUROCOMPUTING, 2018, 275 :2041-2054

← 1 2 3 4 5 →