Comments on″Capacity Analysis of the Asymptotically Stable Multi-Valued Exponential Bidirectinal Associative Memory″

被引：0
|
作者：
CHEN LeiYANG GengXU Bihuan College of ComputerNanjing University of Posts and TelecommunicationsNanjing China Institute of Computer TechnologyNanjing University of Posts and TelecommunicationsNanjing China College of ScienceNanjing University of Posts and TelecommunicationsNanjing China [1 ,2 ,1 ,2 ,3 ,1 ,210046 ,2 ,210046 ,3 ,210046 ]
机构：
来源：
南京邮电大学学报(自然科学版) | 2011年 / 31卷 / 03期
关键词：
Associative memory; asymptotical stability; convergence; neural network;
D O I：
10.14132/j.cnki.1673-5439.2011.03.019
中图分类号：
TP183 [人工神经网络与计算];
学科分类号：
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.
引用
收藏
页码：90 / 93
页数：4
相关论文
共 3 条
  • [1] Chen Z Y,Kwong C P.Recurrent correlation associative mem-ories with multiple-value. IEEE International Confer-ence on neural networks . 1994
  • [2] WANG C C,HWANG S M,LEE J P.Capacity analysis of the as- ymptotically stable multivalued exponential bidirectional associative memory. IEEE Transactions on Systems Man and Cybernetics . 1996
  • [3] Chiueh T D,Goodman R M.Recurrent correlation associative memories. IEEE ACM Transactions on Networking . 1991
1