Rule extraction from a multilayer perceptron with staircase activation functions

Author

Bologna, Guido

Author_Institution

Machine Learning Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia

Volume

3

fYear

2000

fDate

2000

Firstpage

419

Abstract

We tackle the problem of rule extraction from multilayer perceptrons. Our approach consists of characterising discriminant hyper-plane frontiers built by a special neural network model, denoted as a discretized interpretable multilayer perceptron (DIMLP). Rules are extracted in polynomial time with respect to the size of the problem. Further, the degree of matching between extracted rules and neural network responses is 100%. We apply DIMLP to five data sets of the public domain in which for some of them it gives better average predictive accuracy than standard multilayer perceptrons and C4.5 decision trees

Keywords

computational complexity; data mining; learning (artificial intelligence); multilayer perceptrons; pattern classification; computational complexity; learning; multilayer perceptron; pattern classification; polynomial time; rule extraction; rule matching; staircase activation functions; Accuracy; Australia; Classification tree analysis; Data mining; Decision trees; Machine learning; Multilayer perceptrons; Neural networks; Neurons; Polynomials;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861344

Filename

861344