Convergence and periodicity of solutions for a discrete-time network model of two neurons

被引：28

作者：

Yuan, ZH

Huang, LH

Chen, YM ^{[1
]}

机构：

[1] Wilfrid Laurier Univ, Dept Math, Waterloo, ON N2L 3C5, Canada

[2] Hunan Univ, Coll Math & Econometr, Changsha 410082, Hunan, Peoples R China

来源：

MATHEMATICAL AND COMPUTER MODELLING | 2002年 / 35卷 / 9-10期

基金：

中国国家自然科学基金;

关键词：

difference system; neural network; piecewise constant argument; convergence; periodicity;

D O I：

10.1016/S0895-7177(02)00061-4

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Considered is a class of difference systems with McCulloch-Pitts nonlinearity, which includes the discrete version of an artificial neural network of two neurons with piecewise constant argument. Some interesting results are obtained for the convergence and periodicity of solutions of the systems. Most importantly, multiple periodic solutions exist. Our results have potential applications in neural networks. (C) 2002 Elsevier Science Ltd. All rights reserved.

引用

页码：941 / 950

页数：10

共 22 条

[1] OSCILLATORY AND PERIODIC-SOLUTIONS OF DELAY DIFFERENTIAL-EQUATIONS WITH PIECEWISE CONSTANT ARGUMENT [J].