A NEURAL-NETWORK THAT SELF-ORGANIZES TO PERFORM 3 OPERATIONS RELATED TO PRINCIPAL COMPONENT ANALYSIS

被引：11

作者：

MATSUOKA, K

KAWAMOTO, M

机构：

来源：

NEURAL NETWORKS | 1994年 / 7卷 / 05期

关键词：

NEURAL NETWORK; SELF-ORGANIZATION; HEBBIAN RULE; ANTI-HEBBIAN RULE; PRINCIPAL COMPONENT ANALYSIS;

D O I：

10.1016/0893-6080(94)90097-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The self-organization of a linear, single-layer neural network is mathematically analyzed, in which a regular Hebbian rule and an anti-Hebbian rule are used for the adaptation of the connection weights between constituent units. It is shown that three mathematical functions related to principal component analysis are acquired by giving three different sets of learning parameters to the same model.

引用

页码：753 / 765

页数：13

共 8 条

[1]

FOLDIAK P, 1989, JUN P IJCNN INT JOIN, V1, P401

[2]

KOHONEN T, 1984, SEF ORG ASS MEMORY

[3] DYNAMICS OF LEARNING IN LINEAR FEATURE-DISCOVERY NETWORKS [J].