Dynamical stability analysis of multiple equilibrium points in time-varying delayed recurrent neural networks with discontinuous activation functions

被引：67

作者：

Huang, Yujiao ^{[1
]}

Zhang, Huaguang ^{[1
]}

Wang, Zhanshan ^{[1
]}

机构：

[1] Northeastern Univ, Sch Informat Sci & Engn, Shenyang 110819, Liaoning, Peoples R China

来源：

NEUROCOMPUTING | 2012年 / 91卷

基金：

中国国家自然科学基金;

关键词：

Recurrent neural network; Discontinuous activation function; Multistability; ROBUST EXPONENTIAL STABILITY; GLOBAL CONVERGENCE; ASSOCIATIVE MEMORY; MULTISTABILITY; MULTIPERIODICITY; ATTRACTIVITY;

D O I：

10.1016/j.neucom.2012.02.016

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper is concerned with the dynamical stability analysis of multiple equilibrium points in recurrent neural networks with time-varying delays and discontinuous activation functions. Based on the decomposition of state space, some sufficient conditions for the existence of multiple equilibrium points are established, which ensure that n-dimensional recurrent neural networks with k-level discontinuous activation functions can have k(n) equilibrium points. Under these conditions, the equilibrium points are locally exponentially stable. Moreover, some conditions for the existence of sets of stable equilibrium points and unstable equilibrium points are derived for recurrent neural networks without delay and with discontinuous activation functions. Finally, three examples are given to illustrate the effectiveness of the results. (C) 2012 Elsevier B.V. All rights reserved.

引用

页码：21 / 28

页数：8

共 50 条

[41] New exponential synchronization criteria for time-varying delayed neural networks with discontinuous activations [J].

Cai, Zuowei ;

Huang, Lihong ;

Zhang, Lingling .

NEURAL NETWORKS, 2015, 65 :105-114

[42] Multistability analysis of competitive neural networks with Gaussian-wavelet-type activation functions and unbounded time-varying delays [J].

Nie, Xiaobing ;

Liang, Jinling ;

Cao, Jinde .

APPLIED MATHEMATICS AND COMPUTATION, 2019, 356 :449-468

[43] Exponential state estimation for Markovian jumping neural networks with mixed time-varying delays and discontinuous activation functions [J].

Wu, Huaiqin ;

Wang, Leifei ;

Wang, Yu ;

Niu, Peifeng ;

Fang, Bolin .

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2016, 7 (04) :641-652

[44] A Study of Exponential Stability of Multiple Equilibria in Delayed Recurrent Neural Networks [J].

Zeng, Zhigang ;

Zheng, Wei Xing .

2012 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 2012), 2012, :2083-2086

[45] A new approach to stability analysis of discrete-time recurrent neural networks with time-varying delay [J].

Song, Chunwei ;

Gao, Huijun ;

Zheng, Wei Xing .

NEUROCOMPUTING, 2009, 72 (10-12) :2563-2568

[46] Improved delay-dependent stability conditions for recurrent neural networks with multiple time-varying delays [J].

Chen, Yonggang ;

Fei, Shumin ;

Li, Yongmin .

NONLINEAR DYNAMICS, 2014, 78 (02) :803-812

[47] Coexistence and local Mittag-Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions [J].

Huang, Yu-Jiao ;

Chen, Shi-Jun ;

Yang, Xu-Hua ;

Xiao, Jie .

CHINESE PHYSICS B, 2019, 28 (04)

[48] Multiple types of synchronization analysis for discontinuous Cohen-Grossberg neural networks with time-varying delays [J].

Li, Jiarong ;

Jiang, Haijun ;

Hu, Cheng ;

Yu, Zhiyong .

NEURAL NETWORKS, 2018, 99 :101-113

[49] New stability criteria for recurrent neural networks with interval time-varying delay [J].

Bai, Yong-Qiang ;

Chen, Jie .

NEUROCOMPUTING, 2013, 121 :179-184

[50] Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginarytype activation functions [J].

黄玉娇 ;

胡海根 .

Chinese Physics B, 2015, 24 (12) :275-283

← 1 2 3 4 5 →