A new switching control for finite-time synchronization of memristor-based recurrent neural networks

被引：62
作者：
Gao, Jie [1 ,2 ,3 ]
Zhu, Peiyong [1 ]
Alsaedi, Ahmed [4 ]
Alsaadi, Fuad E. [5 ]
Hayat, Tasawar [4 ,6 ]
机构：
[1] Univ Elect Sci & Technol, Sch Math Sci, Chengdu 611731, Peoples R China
[2] Southwest Petr Univ, Coll Sci, Chengdu 610500, Peoples R China
[3] Southeast Univ, Dept Math, Nanjing 210096, Jiangsu, Peoples R China
[4] King Abdulaziz Univ, Dept Math, Jeddah 21589, Saudi Arabia
[5] King Abdulaziz Univ, Fac Engn, Dept Elect & Comp Engn, Jeddah, Saudi Arabia
[6] Quaid I Azam Univ, Dept Math, Islamabad 44000, Pakistan
来源：
NEURAL NETWORKS | 2017年 / 86卷
基金：
中国国家自然科学基金;
关键词：
Finite-time synchronization; Memristor-based neural networks; Switching control; EXPONENTIAL SYNCHRONIZATION; VARYING DELAYS; STABILITY; SYSTEMS; DESIGN; STABILIZATION;
D O I：
10.1016/j.neunet.2016.10.008
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, finite-time synchronization (FTS) of memristor-based recurrent neural networks (MNNs) with time-varying delays is investigated by designing a new switching controller. First, by using the differential inclusions theory and set-valued maps, sufficient conditions to ensure FTS of MNNs are obtained under the two cases of 0 < alpha < I and alpha = 0, and it is derived that alpha = 0 is the critical value of 0 < alpha < 1. Next, it is discussed deeply on the relation between the parameter alpha and the synchronization time. Then, a new controller with a switching parameter a is designed which can shorten the synchronization time. Finally, some numerical simulation examples are provided to illustrate the effectiveness of the proposed results. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码：1 / 9
页数：9
相关论文
共 40 条
[1]   Finite-time synchronization for memristor-based neural networks with time-varying delays [J].
Abdurahman, Abdujelil ;
Jiang, Haijun ;
Teng, Zhidong .
NEURAL NETWORKS, 2015, 69 :20-28
[2]   Memristor Bridge Synapse-Based Neural Network and Its Learning [J].
Adhikari, Shyam Prasad ;
Yang, Changju ;
Kim, Hyongsuk ;
Chua, Leon O. .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (09) :1426-1435
[3]  
[Anonymous], 1988, DIFFERENTIAL EQUATIO
[4]  
[Anonymous], 2009, SET VALUED ANAL
[5]   Exponential Synchronization of Coupled Stochastic Memristor-Based Neural Networks With Time-Varying Probabilistic Delay Coupling and Impulsive Delay [J].
Bao, Haibo ;
Park, Ju H. ;
Cao, Jinde .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (01) :190-201
[6]   Finite-time stability of continuous autonomous systems [J].
Bhat, SP ;
Bernstein, DS .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2000, 38 (03) :751-766
[7]   Finite-time stabilization control of memristor-based neural networks [J].
Cai, Zuowei ;
Huang, Lihong ;
Zhu, Mingxun ;
Wang, Dongshu .
NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2016, 20 :37-54
[8]   Neural Learning Circuits Utilizing Nano-Crystalline Silicon Transistors and Memristors [J].
Cantley, Kurtis D. ;
Subramaniam, Anand ;
Stiegler, Harvey J. ;
Chapman, Richard A. ;
Vogel, Eric M. .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (04) :565-573
[9]   Exponential H a filtering analysis for discrete-time switched neural networks with random delays using sojourn probabilities [J].
Cao JinDe ;
Rakkiyappan, R. ;
Maheswari, K. ;
Chandrasekar, A. .
SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2016, 59 (03) :387-402
[10]   Cluster synchronization in an array of hybrid coupled neural networks with delay [J].
Cao, Jinde ;
Li, Lulu .
NEURAL NETWORKS, 2009, 22 (04) :335-342
1234