Publication Type

Book Chapter

Version

acceptedVersion

Publication Date

1-2000

Abstract

Supervised Adaptive Resonance Theory is a family of neural networks that performs incremental supervised learning of recognition categories (pattern classes) and multidimensional maps of both binary and analog patterns. This chapter highlights that the supervised ART architecture is compatible with IF-THEN rule-based symbolic representation. Specifi­cally, the knowledge learned by a supervised ART system can be readily translated into rules for interpretation. Similarly, a priori domain knowl­edge in the form of IF-THEN rules can be converted into a supervised ART architecture. Not only does initializing networks with prior knowl­edge improve predictive accuracy and learning efficiency, the inserted symbolic knowledge can also be refined and enhanced by the supervised ART learning algorithm. By preserving symbolic rule form during learn­ing, the rules extracted from a supervised ART system can be compared directly with the originally inserted rules.

Keywords

Choice Function, Category Node, Confidence Factor, Category Choice, Fuzzy ARTMAP

Discipline

Computer and Systems Architecture | Databases and Information Systems | OS and Networks

Research Areas

Data Science and Engineering

Publication

Innovations in ART Neural Networks

Volume

43

Editor

JAIN, Lakhmi C.; LAZZERINI, Beatrice; HALICI, Ugur

First Page

55

Last Page

86

ISBN

9783790824698

Identifier

10.1007/978-3-7908-1857-4_4

Publisher

Springer Link

Additional URL

https://doi.org/10.1007/978-3-7908-1857-4_4

Download

Share

COinS