%0 Journal Article
%T Influences of perturbations of training pattern pairs on max-product fuzzy associative memory
训练模式的摄动对最大—乘积型模糊联想记忆网络的影响
%A ZENG Shui-ling
%A XU Wei-hong
%A YANG Jing-yu
%A
曾水玲
%A 徐蔚鸿
%A 杨静宇
%J 计算机应用
%D 2007
%I
%X A new concept was established in this paper that the robustness of a feed-forward fuzzy associative memory to perturbations of training pattern pair. Then a Max-Product-based Fuzzy Associative Memory (Max-Product FAM) was analyzed. Investigation reveals that such robustness of the memory is good when the fuzzy Hebbian learning algorithm is used, however is poor when another learning algorithm is employed. Finally, an experiment is given to testify the theoretical conclusion and illustrate practical application of Max-product FAM.
%K fuzzy associative memory network
%K learning algorithm
%K pattern pair
%K perturbation
%K robustness
模糊联想记忆网络
%K 学习算法
%K 训练模式对
%K 摄动
%K 鲁棒性
%K 训练模式
%K 摄动
%K 乘积
%K 模糊联想记忆网络
%K 影响
%K associative
%K memory
%K fuzzy
%K pattern
%K training
%K perturbations
%K 结果
%K 理论
%K 实验验证
%K 学习算法
%K 发现
%K 分析
%K 鲁棒性
%K 前馈
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=C0FC1C5BC6992179C4E672382975C39A&yid=A732AF04DDA03BB3&vid=DB817633AA4F79B9&iid=0B39A22176CE99FB&sid=C7DDDE86E6286CD9&eid=375BEEEA164CFE59&journal_id=1001-9081&journal_name=计算机应用&referenced_num=0&reference_num=10