|
|||||
|
|
| 训练模式的摄动对最大-乘积型模糊联想记忆网络的影响 | |
| 引用本文： | 曾水玲,徐蔚鸿,杨静宇. 训练模式的摄动对最大-乘积型模糊联想记忆网络的影响[J]. 计算机应用, 2007, 27(2): 346-348 |
| 作者姓名： | 曾水玲 徐蔚鸿 杨静宇 |
| 作者单位： | 吉首大学,数学与计算机科学学院,湖南,吉首,416000;长沙理工大学,计算机与通信工程学院,湖南,长沙,410077;南京理工大学,计算机科学与技术学院,江苏,南京,416000 |
| 基金项目： | 国家自然科学基金 , 湖南省自然科学基金 |
| 摘 要： | 首先建立了前馈型模糊联想记忆网络对训练模式摄动的鲁棒性概念,分析了最大-乘积型模糊联想记忆网络(Max-Product FAM),发现当采用模糊赫布学习算法时它的鲁棒性好,但采用另一学习算法时鲁棒性较差.最后用实验验证了理论结果. |
| 关 键 词： | 模糊联想记忆网络 学习算法 训练模式对 摄动 鲁棒性 |
| 文章编号： | 1001-9081(2007)02-0346-03 |
| 收稿时间： | 2006-08-29 |
| 修稿时间： | 2006-08-29 |
Influences of perturbations of training pattern pairs on max-product fuzzy associative memory |
|
| ZENG Shui-ling,XU Wei-hong,YANG Jing-yu. Influences of perturbations of training pattern pairs on max-product fuzzy associative memory[J]. Journal of Computer Applications, 2007, 27(2): 346-348 | |
| Authors: | ZENG Shui-ling XU Wei-hong YANG Jing-yu |
| Abstract: | 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. |
| Keywords: | fuzzy associative memory network learning algorithm pattern pair perturbation robustness |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《计算机应用》浏览原始摘要信息 | |
| 点击此处可从《计算机应用》下载全文 | |