首页 | 本学科首页   官方微博 | 高级检索  
     

THE STABILITY OF A KIND OF DISCRETE-TIME HOPFIELD NEURAL NETWORKS WITH ASYMPTOTICAL WEIGHTED MATRICES
引用本文:Guo Shujuan Ruan Jiong Tu Qingwei (Dept. of Informal Science,Jiangsu Polytechnic University,Changzhou 213164, Dept. of Math.,Fudan University,Shanghai 200433). THE STABILITY OF A KIND OF DISCRETE-TIME HOPFIELD NEURAL NETWORKS WITH ASYMPTOTICAL WEIGHTED MATRICES[J]. Annals of Differential Equations, 2006, 22(4): 489-495
作者姓名:Guo Shujuan Ruan Jiong Tu Qingwei (Dept. of Informal Science  Jiangsu Polytechnic University  Changzhou 213164   Dept. of Math.  Fudan University  Shanghai 200433)
作者单位:Dept. of Informal Science,Jiangsu Polytechnic University,Changzhou 213164; Dept. of Math.,Fudan University,Shanghai 200433
摘    要:In this paper, the authors analyze the stability of a kind of discrete-time Hopfield neural network with asymptotical weighted matrix, which can be expressed as the product of a positive definite diagonal matrix and a symmetric matrix. We obtain that it has asymptotically stable equilibriums if the network is updated asynchronously, and asymptotically stable equilibriums or vibrating final stage with 2 period if updated synchronously. To prove these, Lassale's invariance principle in difference equation is applied.

关 键 词:神经网络  Lassale恒定原理  不对称权重矩阵  平衡性

THE STABILITY OF A KIND OF DISCRETE-TIME HOPFIELD NEURAL NETWORKS WITH ASYMPTOTICAL WEIGHTED MATRICES
Guo Shujuan Ruan Jiong Tu Qingwei. THE STABILITY OF A KIND OF DISCRETE-TIME HOPFIELD NEURAL NETWORKS WITH ASYMPTOTICAL WEIGHTED MATRICES[J]. 微分方程年刊(英文版), 2006, 22(4): 489-495
Authors:Guo Shujuan Ruan Jiong Tu Qingwei
Affiliation:[1]Dept. of Informal Science, Jiangsu Polytechnic University, Changzhou 213164 [2]Dept. of Math., Fudan University, Shanghai 200433
Abstract:In this paper, the authors analyze the stability of a kind of discrete-time Hopfield neural network with asymptotical weighted matrix, which can be expressed as the product of a positive definite diagonal matrix and a symmetric matrix. We obtain that it has asymptotically stable equilibriums if the network is updated asynchronously, and asymptotically stable equilibriums or vibrating final stage with 2 period if updated synchronously. To prove these, Lassale's invariance principle in difference equation is applied.
Keywords:Hopfield neural network   Lassale's invariance principle   asymmetric weighted matrix   equilibriums   asymptotic stable   vibration
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号