FUZZY ART PROPERTIES

被引：60

作者：

HUANG, JX

GEORGIOPOULOS, M

HEILEMAN, GL

机构：

[1] UNIV CENT FLORIDA,DEPT ELECT & COMP ENGN,ORLANDO,FL 32816

[2] UNIV NEW MEXICO,ALBUQUERQUE,NM 87131

来源：

NEURAL NETWORKS | 1995年 / 8卷 / 02期

关键词：

NEURAL NETWORK; PATTERN RECOGNITION; CLUSTERING; LEARNING; ADAPTIVE RESONANCE THEORY; FUZZY SET THEORY; FUZZY ART;

D O I：

10.1016/0893-6080(94)00073-U

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents some important properties of the Fuzzy ART neural network algorithm introduced by Carpenter, Grossberg, and Rosen. The properties described in the paper are distinguished into a number of categories. These include template, access, and reset properties, as well as properties related to the number of list presentations needed for weight stabilization. These properties provide numerous insights as to how Fuzzy ART operates. Furthermore, the effects of the Fuzzy ART parameters alpha and rho on the functionality of the algorithm are clearly illustrated.

引用

页码：203 / 213

页数：11

共 8 条

[1] ARTMAP - SUPERVISED REAL-TIME LEARNING AND CLASSIFICATION OF NONSTATIONARY DATA BY A SELF-ORGANIZING NEURAL NETWORK [J].