LEARNING IN A COMPETITIVE NETWORK

被引：10

作者：

BANZHAF, W

HAKEN, H

机构：

来源：

NEURAL NETWORKS | 1990年 / 3卷 / 04期

关键词：

Competitive learning; Hebbian learning; Neural networks; Pattern classification; Pattern recognition; Self-organization; Specialization; Unsupervised learning; Winner-take-all networks;

D O I：

10.1016/0893-6080(90)90025-G

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We consider the abilities of a recently published neural network model to recognize and classify arbitrary patterns. We introduce a learning scheme based on Hebb's rule which allows the system's neuronal cells to specialize on different patterns during learning. The rule which was originally introduced by Kohonen is appropriately modified and applied to the competitive network under study. A variant of the learning dynamics is then derived from an energy functional characterizing the specialization state of the network. Simulations are presented to demonstrate the specialization process for different pattern distributions. © 1990.

引用

页码：423 / 435

页数：13

共 28 条

[1]

Amari S., 1982, COMPETITION COOPERAT

[2]

[Anonymous], 1983, SYNERGETICS INTRO

[3] ART-2 - SELF-ORGANIZATION OF STABLE CATEGORY RECOGNITION CODES FOR ANALOG INPUT PATTERNS [J].