Reduction of symbolic rules from artificial neural networks using sensitivity analysis

Author

Viktor, HL ; Engelbrecht, AP ; Cloete, I.

Author_Institution

Dept. of Comput. Sci., Stellenbosch Univ., South Africa

Volume

4

fYear

1995

fDate

Nov/Dec 1995

Firstpage

1788

Abstract

This paper shows how sensitivity analysis identifies and eliminates redundant conditions from the rules extracted from trained neural networks, by eliminating irrelevant inputs. This leads to a reduction in the number and size of the rules. The reduced rule set accurately and minimally reflect the classification problems presented. Also, the elimination of redundant input units significantly reduces the combinatorics of the rule extraction algorithm. The resultant rule set compares favorably with traditional symbolic machine learning algorithms

Keywords

equivalence classes; learning (artificial intelligence); neural nets; pattern classification; sensitivity analysis; classification problems; combinatorics; rule extraction algorithm; symbolic machine learning algorithms; symbolic rules reduction; trained neural networks; Africa; Artificial neural networks; Combinatorial mathematics; Computer science; Data mining; Logistics; Machine learning algorithms; Neural networks; Sensitivity analysis; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1995. Proceedings., IEEE International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-2768-3

Type

conf

DOI

10.1109/ICNN.1995.488892

Filename

488892