PROPERTIES OF LEARNING IN ARTMAP

被引：18

作者：

GEORGIOPOULOS, M ^{[1
]}

HUANG, JX ^{[1
]}

HEILEMAN, GL ^{[1
]}

机构：

[1] UNIV NEW MEXICO,ALBUQUERQUE,NM 87131

来源：

NEURAL NETWORKS | 1994年 / 7卷 / 03期

关键词：

NEURAL NETWORK; PATTERN RECOGNITION; LEARNING; ADAPTIVE RESONANCE THEORY; ART1; ARTMAP;

D O I：

10.1016/0893-6080(94)90083-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we consider the ARTMAP architecture for situations requiring learning of many-to-one maps. It is shown that if ARTMAP is repeatedly presented with a list of input/output pairs, it establishes the required mapping in at most M(a) - 1 list presentations, where M(a) corresponds to the total number of ones in each one of the input patterns. Other useful properties, associated with the learning of the mapping represented by an arbitrary list of input/output pairs, are also examined, These properties reveal some of the characteristics of learning in ARTMAP when it is used as a tool in establishing an arbitrary mapping from a binary input space to a binary output space. The results presented in this paper are valid for the fast learning case, and for small beta(a) values, where beta(a) is a parameter associated with the adaptation of bottom-up weights in one of the ART1 modules of ARTMAP.

引用

页码：495 / 506

页数：12

共 8 条

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