带递归的模糊感知器有限收敛性  

Finite convergence for recurrent fuzzy perceptron

作　　者：刘燕[1,2] 杨洁[1] 李龙[3] 

机构地区：[1]大连理工大学数学科学学院,辽宁大连116024 [2]大连工业大学信息科学与工程学院,辽宁大连116034 [3]衡阳师范学院数学与计算科学系,湖南衡阳421008

出　　处：《大连理工大学学报》2011年第6期933-936,共4页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(1087122010926144)

摘　　要：模糊感知器的主要功能是通过权值的学习来判别样本所属的类别.对一种基于模糊逻辑运算的带递归的模糊感知器进行了研究,其网络结构类似于内部运算基于加法-乘法的传统感知器,并加入了动态递归项.设定网络的初始权值均为常数0,证明了若训练样本的输入向量维数为2,在样本模糊可分条件下,学习算法有限收敛,即有限步后权值的训练停止;若训练样本的输入向量维数大于2,在稍强的条件下,学习算法也有限收敛.The main function of fuzzy perceptron is to discriminate which categories the samples are in by weight learning.An algorithm for a recurrent fuzzy perceptron based on fuzzy logic is presented,and the network structure of the recurrent fuzzy perceptron is similar to traditional perceptron based on addition-production,and the dynamic recursion term is added.Initial weights of network are set to be constant zero,in the case where the dimension of the input vectors is two and the training examples are separable,its finite convergence is proved,i.e.,the training procedure for the network weights will stop in finite steps,and when the dimension is greater than two,stronger conditions are needed to guarantee the finite convergence.

关 键 词：模糊感知器 递归 有限收敛性 模糊可分 

分 类 号：O159[理学—数学] TP183[理学—基础数学]