Function Approximation with ARTMAP Architectures

We analyze function approximation (regression) capability of Fuzzy ARTMAP (FAM) architectures - well-known incremental learning neural networks. We focus especially on the universal approximation property. In our experiments, we compare the regression performance of FAM networks with other standard...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computers, communications & control communications & control, 2012-12, Vol.7 (5), p.957
Main Authors: Sasu, Lucian M., Andonie, Răzvan
Format: Article
Language:English
Subjects:
Approximation
Mathematical analysis
Neural networks
Regression
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We analyze function approximation (regression) capability of Fuzzy ARTMAP (FAM) architectures - well-known incremental learning neural networks. We focus especially on the universal approximation property. In our experiments, we compare the regression performance of FAM networks with other standard neural models. It is the first time that ARTMAP regression is overviewed, both from theoretical and practical points of view.
ISSN:1841-9836
1841-9844
DOI:10.15837/ijccc.2012.5.1355