ESTIMATION OF ATTRACTION DOMAIN AND EXPONENTIAL CONVERGENCE RATE OF CONTINUOUS FEEDBACK ASSOCIATIVE MEMORY  

作　　者：周冬明 曹进德 李继彬 

机构地区：[1]Department of Information and Electronic Science, Yunnan University, Kunming 650091, P R China [2]Adult Education College, Yunnan University, Kunming 650091, P R China [3]Center for Nonlinear Science Studies, Kunming University of Science and Technology, Kunming 650093, P R China

出　　处：《Applied Mathematics and Mechanics(English Edition)》2001年第3期320-325,共6页应用数学和力学（英文版）

基　　金：theNaturalScienceFoundationofYunnanProvinceChina! ( 1999F0 0 17M)

摘　　要：Analytical techniques and Liapunov method were used for the estimation of the attraction domain of memory patterns and local exponential stability of neural networks. The results were used to design efficient continuous feedback associative memory neural networks. The neural network synthesis procedure ensured the gain of large exponential convergence rate without reduction of the attraction domain.Analytical techniques and Liapunov method were used for the estimation of the attraction domain of memory patterns and local exponential stability of neural networks. The results were used to design efficient continuous feedback associative memory neural networks. The neural network synthesis procedure ensured the gain of large exponential convergence rate without reduction of the attraction domain.

关 键 词：Asymptotic stability Convergence of numerical methods Fault tolerant computer systems Matrix algebra Recurrent neural networks 

分 类 号：O175[理学—数学] TP183[理学—基础数学]