首页 | 本学科首页   官方微博 | 高级检索  
     检索      

Comments on ″Capacity Analysis of the Asymptotically Stable Multi-Valued Exponential Bidirectinal Associative Memory″
基金项目:The project is supported by the National Natural Science Foundation of China (60873231 and 60973046); Major State Basic Research Development Pro-gram of China (2011CB302903); Natural Science Foundation of Jiangsu Province(BK2009426); Research and Innovation Plan for College Graduates of Jiangsu Province(CX10B_195Z) ; the Scientific Research Foundation of Nanjing University of Posts and Telecommunications(NY210043)
摘    要:Asymptotical stability is an important property of the associative memory neural networks.In this comment,we demonstrate that the asymptotical stability analyses of the MV ECAM and MV-eBAM in the asynchronous update mode by Wang et al are not rigorous,and then we modify the errors and further prove that the two models are all asymptotically stable in both synchronous and asynchronous update modes.

关 键 词:Associative  memory  asymptotical  stability  convergence  neural  network

Comments on ″Capacity Analysis of the Asymptotically Stable Multi-Valued Exponential Bidirectinal Associative Memory″
Authors:CHEN Lei    YANG Geng  XU Bi-huan
Institution:CHEN Lei1,2,YANG Geng1,XU Bi-huan3 ( 1.College of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210046,China 2.Institute of Computer Technology,China 3.College of Science,China )
Abstract:Asymptotical stability is an important property of the associative memory neural networks.In this comment,we demonstrate that the asymptotical stability analyses of the MV ECAM and MV eBAM in the asynchronous update mode by Wang et al are not rigorous,and then we modify the errors and further prove that the two models are all asymptotically stable in both synchronous and asynchronous update modes.
Keywords:Associative memory  asymptotical stability  convergence  neural network  
本文献已被 CNKI 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