Document Type
Article
Department or Administrative Unit
Computer Science
Publication Date
12-2012
Abstract
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.
Recommended Citation
SASU, Lucian M.; ANDONIE, Răzvan. Function Approximation with ARTMAP Architectures. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, [S.l.], v. 7, n. 5, p. 957-967, sep. 2014. ISSN 1841-9844. Available at: . doi: https://doi.org/10.15837/ijccc.2012.5.1355.
Journal
International Journal of Computers Communications & Control
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Rights
Copyright © 2006-2012 by CCC Publications
Comments
This article was originally published Open Access in International Journal of Computers Communications & Control . The full-text article from the publisher can be found here.