Exponential input-to-state stability for complex-valued memristor-based BAM neural networks with multiple time-varying delays

被引：38

作者：

Guo, Runan ^{[1
]}

Zhang, Ziye ^{[1
,2
]}

Liu, Xiaoping ^{[2
,3
]}

Lin, Chong ^{[4
]}

Wang, Haixia ^{[5
]}

Chen, Jian ^{[6
]}

机构：

[1] Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Peoples R China

[2] Lakehead Univ, Dept Elect Engn, Thunder Bay, ON P7B 5E1, Canada

[3] Shandong Jianzhu Univ, Sch Informat & Elect Engn, Jinan 250101, Shandong, Peoples R China

[4] Qingdao Univ, Inst Complex Sci, Qingdao 266071, Peoples R China

[5] Shandong Univ Sci & Technol, Key Lab Robot & Intelligent Technol Shandong Prov, Qingdao 266590, Peoples R China

[6] Qingdao Univ Technol, Coll Automat Engn, Qingdao 266555, Peoples R China

来源：

NEUROCOMPUTING | 2018年 / 275卷

基金：

中国博士后科学基金; 加拿大自然科学与工程研究理事会; 中国国家自然科学基金;

关键词：

Exponential input-to-state stability; Memristor-based BAM neural networks; Complex-valued systems; Multiple time-varying delays; Lyapunov functional; STABILIZATION; DISSIPATIVITY; CRITERIA; SYSTEMS; ISS;

D O I：

10.1016/j.neucom.2017.10.038

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, the exponential input-to-state stability (ISS) for complex-valued memristor-based bidirectional associative memory (BAM) neural networks with multiple time-varying delays is discussed. By constructing a novel Lyapunov functional and utilizing inequality techniques, a sufficient criterion of the exponential input-to-state stability for the considered system is firstly derived. Moreover, similar result is also obtained for delayed complex-valued BAM neural networks without memristors. Finally, two numerical examples are given to demonstrate the effectiveness of the obtained results. (C) 2017 Elsevier B.V. All rights reserved.

引用

页码：2041 / 2054

页数：14

共 50 条

[1] Robust stability of recurrent neural networks with ISS learning algorithm [J].

Ahn, Choon Ki .

NONLINEAR DYNAMICS, 2011, 65 (04) :413-419

[2] Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay [J].

Ahn, Choon Ki .

INFORMATION SCIENCES, 2010, 180 (23) :4582-4594

[3] Asymptotic Stability of Cohen-Grossberg BAM Neutral Type Neural Networks with Distributed Time Varying Delays [J].

Ali, M. Syed ;

Saravanan, S. ;

Rani, M. Esther ;

Elakkia, S. ;

Cao, Jinde ;

Alsaedi, Ahmed ;

Hayat, Tasawar .

NEURAL PROCESSING LETTERS, 2017, 46 (03) :991-1007

[4] Passivity of memristor-based BAM neural networks with different memductance and uncertain delays [J].

Anbuvithya, R. ;

Mathiyalagan, K. ;

Sakthivel, R. ;

Prakash, P. .

COGNITIVE NEURODYNAMICS, 2016, 10 (04) :339-351

[5]

[Anonymous], 1988, Differential Equations with Discontinuous Righthand Sides

[6] Functional differential inclusions and dynamic behaviors for memristor-based BAM neural networks with time-varying delays [J].

Cai, Zuowei ;

Huang, Lihong .

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2014, 19 (05) :1279-1300

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

CHUA, LO .

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

[8] Stochastic H2/H∞ control of nonlinear systems with time-delay and state-dependent noise [J].

Gao, Ming ;

Sheng, Li ;

Zhang, Weihai .

APPLIED MATHEMATICS AND COMPUTATION, 2015, 266 :429-440

[9] Matrix measure method for global exponential stability of complex-valued recurrent neural networks with time-varying delays [J].

Gong, Weiqiang ;

Liang, Jinling ;

Cao, Jinde .

NEURAL NETWORKS, 2015, 70 :81-89

[10] Existence, uniqueness, and exponential stability analysis for complex-valued memristor-based BAM neural networks with time delays [J].

Guo, Runan ;

Zhang, Ziye ;

Liu, Xiaoping ;

Lin, Chong .

APPLIED MATHEMATICS AND COMPUTATION, 2017, 311 :100-117

← 1 2 3 4 5 →