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

[21] Robust exponential stability of recurrent neural networks with multiple time-varying delays [J].

Zhang, Huaguang ;

Wang, Zhanshan ;

Liu, Derong .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2007, 54 (08) :730-734

[22] Complete stability of delayed recurrent neural networks with Gaussian activation functions [J].

Liu, Peng ;

Zeng, Zhigang ;

Wang, Jun .

NEURAL NETWORKS, 2017, 85 :21-32

[23] Multiple μ-stability of neural networks with unbounded time-varying delays [J].

Wang, Lili ;

Chen, Tianping .

NEURAL NETWORKS, 2014, 53 :109-118

[24] Multiple μ-stability analysis of complex-valued neural networks with unbounded time-varying delays [J].

Rakkiyappan, R. ;

Velrnurugan, G. ;

Cao, Jinde .

NEUROCOMPUTING, 2015, 149 :594-607

[25] Dynamical stability analysis of delayed recurrent neural networks with ring structure [J].

Zhang, Huaguang ;

Huang, Yujiao ;

Cai, Tiaoyang ;

Wang, Zhanshan .

INTERNATIONAL JOURNAL OF MODERN PHYSICS B, 2014, 28 (19)

[26] Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions [J].

Bao, Gang ;

Zeng, Zhigang .

NEUROCOMPUTING, 2012, 77 (01) :101-107

[27] Global asymptotical stability analysis for a kind of discrete-time recurrent neural network with discontinuous activation functions [J].

Bao, Gang ;

Zeng, Zhigang .

NEUROCOMPUTING, 2016, 193 :242-249

[28] Stability Analysis of Multiple Equilibria for Recurrent Neural Networks with Discontinuous Mexican-Hat-Type Activation Function [J].

Nie, Xiaobing ;

Zheng, Wei Xing ;

Lu, Jinhu .

2015 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2015, :569-572

[29] Multiple μ-stability analysis for memristor-based complex-valued neural networks with nonmonotonic piecewise nonlinear activation functions and unbounded time-varying delays [J].

Tan, Manchun ;

Xu, Desheng .

NEUROCOMPUTING, 2018, 275 :2681-2701

[30] Multistability and multiperiodicity of delayed bidirectional associative memory neural networks with discontinuous activation functions [J].

Huang, Yujiao ;

Zhang, Huaguang ;

Wang, Zhanshan .

APPLIED MATHEMATICS AND COMPUTATION, 2012, 219 (03) :899-910

← 1 2 3 4 5 →