Rademacher penalization applied to fuzzy ARTMAP and boosted ARTMAP

Author

Verzi, Stephen J. ; Heileman, Gregory L. ; Georgiopoulus, Michael ; Healy, Michael J.

Author_Institution

Dept. of Comput. Sci., New Mexico Univ., Albuquerque, NM, USA

Volume

2

fYear

2001

fDate

2001

Firstpage

1191

Abstract

We deal with the performance bounding of fuzzy ARTMAP and other ART-based neural network architectures, such as boosted ARTMAP, according to the theory of structural risk minimization. Structural risk minimization research indicates a trade-off between training error and hypothesis complexity. This trade-off directly motivated boosted ARTMAP. In this paper, we present empirical evidence for boosted ARTMAP as a viable learning technique, in general, in comparison to fuzzy ARTMAP and other ART-based neural network architectures. We also show direct empirical evidence for decreased hypothesis complexity in conjunction with the improved empirical performance for boosted ARTMAP as compared with fuzzy ARTMAP. Application of the Rademacher penalty to boosted ARTMAP on a specific learning problem further indicates its utility as compared with fuzzy ARTMAP

Keywords

ART neural nets; computational complexity; fuzzy neural nets; learning (artificial intelligence); minimisation; neural net architecture; Rademacher penalty; boosted ARTMAP; complexity; fuzzy ARTMAP; learning; neural network architectures; structural risk minimization; Computer science; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Labeling; Machine learning algorithms; Neural networks; Risk management; Supervised learning; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-7044-9

Type

conf

DOI

10.1109/IJCNN.2001.939530

Filename

939530