| 基于爱因斯坦t-模的模糊联想记忆的学习算法 |
| |
| 引用本文： | 程思蔚,徐蔚鸿,王勇,欧阳毅. 基于爱因斯坦t-模的模糊联想记忆的学习算法[J]. 计算机工程与应用, 2006, 42(15): 40-41,44 |
| |
| 作者姓名： | 程思蔚 徐蔚鸿 王勇 欧阳毅 |
| |
| 作者单位： | 长沙理工大学数学与计算科学学院,长沙,410076;长沙理工大学计算机与通信工程学院,长沙,410076;吉首大学数学与计算机系,湖南,吉首,416000;长沙理工大学计算机与通信工程学院,长沙,410076;长沙理工大学计算机与通信工程学院,长沙,410076;华中科技大学软件学院,广东,佛山,528234 |
| |
| 基金项目： | 浙江省湖州市自然科学基金;湖南省教委科研项目;长沙理工大学校科研和教改项目 |
| |
| 摘 要： | 为神经网络提供有效学习算法是神经网络研究的关键问题。文章利用t-模的伴随蕴涵算子,为基于Max和Tes合成的模糊联想记忆网络Max-TesFAM提供了一种新的学习算法,此处Tes是由爱因斯坦提出的一种t-模算子。从理论上严格证明了,只要Max-TesFAM能完整可靠地存储所给的多个模式对,则该新的学习算法一定能找到使得网络能完整可靠存储这些模式对的所有连接权矩阵的最大者。最后,用实验说明了所提出的学习算法的有效性。
|
| 关 键 词： | 伴随蕴涵算子 模糊联想记忆网络 学习算法 t-模 |
| 文章编号： | 1002-8331-（2006）15-0040-02 |
| 收稿时间： | 2006-03-01 |
| 修稿时间： | 2006-03-01 |
An Efficient Learning Algorithm for Fuzzy Associative Memory Based on Einstain's t-Norm |
| |
| Cheng Siwei,Xu Weihong,Wang Yong,Ouyang Yi. An Efficient Learning Algorithm for Fuzzy Associative Memory Based on Einstain's t-Norm[J]. Computer Engineering and Applications, 2006, 42(15): 40-41,44 |
| |
| Authors: | Cheng Siwei Xu Weihong Wang Yong Ouyang Yi |
| |
| Affiliation: | College of Mathematics and Computing Science,Changsha University of Science and Technology,Changsha 410076;College of Mathematics and Computer Science,Jishou University,Jishou,Hunan 416000;College of Computer and Communications Engineering,Changsha University of Science and Technology,Changsha 410076;College of Software,Huazhong University of Science and Technology,Foshan,Guangdong 528234 |
| |
| Abstract: | The key issue for research on a neural network is to find efficient learning algorithm for the network. Taking advantage of the concomitant implication operator of Tes,which is a t-norm and was presented by Einstein,a simple efficient learning algorithm is proposed for the fuzzy associative memory based on fuzzy composition of Max and Tes(Max-Tes FAM).It is proved theoretically that,for arbitrary given training pattern pairs,if the Max-Tes FAM has ability to store reliably them,then the proposed learning algorithm can find the maximum of all connected weight matrices which can ensure that the Max-Tes FAM stores reliably these pattern pairs.Finally an experiment is given to illustrate the effectivity of the presented learning algorithms. |
| |
| Keywords: | concomitant implication operator fuzzy associative memory learning algorithm t-norm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
