Dynamical behavior of delayed Hopfield neural networks with discontinuous activations

被引:45
作者
Wang, Jiafu [1 ]
Huang, Lihong [1 ]
Guo, Zhenyuan [1 ]
机构
[1] Hunan Univ, Coll Math & Econometr, Changsha 410082, Hunan, Peoples R China
基金
中国国家自然科学基金;
关键词
Delayed neural network; Discontinuous dynamical system; Periodic solution; Global asymptotic stability; Leray-Schauder alternative theorem; GLOBAL EXPONENTIAL STABILITY; PERIODIC-SOLUTIONS; EXISTENCE; TIME; CONVERGENCE;
D O I
10.1016/j.apm.2008.03.023
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In this paper, a general class of neural networks with arbitrary constant delays is studied, whose neuron activations are discontinuous and may be unbounded or nonmonotonic. Based on the Leray-Schauder alternative principle and generalized Lyapunov approach, conditions are given under which there is a unique equilibrium of the neural network, which is globally asymptotically stable. Moreover, the existence and global asymptotic stability of periodic solutions are derived, where the neuron inputs are periodic. The obtained results extend previous works not only on delayed neural networks with Lipschitz continuous neuron activations, but also on delayed neural networks with discontinuous neuron activations. (C) 2008 Elsevier Inc. All rights reserved.
引用
收藏
页码:1793 / 1802
页数:10
相关论文
共 26 条
[1]  
[Anonymous], 1939, Duke Math. J.
[2]  
Aubin J., 1984, DIFFERENTIAL INCLUSI
[3]  
Aubin J.-P., 1990, Set-Valued Analysis
[4]   An analog scheme for fixed point computation .1. Theory [J].
Borkar, VS ;
Soumyanath, K .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1997, 44 (04) :351-355
[5]   NEURAL NETWORK FOR QUADRATIC OPTIMIZATION WITH BOUND CONSTRAINTS [J].
BOUZERDOUM, A ;
PATTISON, TR .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (02) :293-304
[6]   Existence and stability of periodic solutions for Hopfield neural network equations with periodic input [J].
Dong, QX ;
Matsui, K ;
Huang, XK .
NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2002, 49 (04) :471-479
[7]  
DUGUNDJI J, 1986, MONOGRAFIE MATEMARYC, V123
[8]  
Filippov A. F., 1988, Differential Equations with Discontinuous Righthand Sides
[9]   Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations [J].
Forti, A ;
Grazzini, A ;
Nistri, P ;
Pancioni, L .
PHYSICA D-NONLINEAR PHENOMENA, 2006, 214 (01) :88-99
[10]   Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain [J].
Forti, M ;
Nistri, P ;
Papini, D .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (06) :1449-1463