A fast method for rule extraction in neural networks

Author

Grau, M. Abad ; Molinero, L. Hernández

Author_Institution

Dept. de Lenguajes u Sistemas, Granada Univ., Spain

Volume

3

fYear

1998

fDate

4-9 May 1998

Firstpage

2334

Abstract

Most methods for finding regularities or rule extraction based data start out from the idea that the representation of the data must evolve from a distributed representation of the information to a more localised representation which will represent the skeleton of the network. This idea involves the problem of needing long training times imposed by the backpropagation algorithm, as well as the errors deriving from incorrect elimination of connections and units in order to extract the structure of the network. The method proposed here, which I call direct method for structural learning, allows the appropriate learning and pruning to be achieved in a very short time due to the fact that it starts with a non-skeletal local representation of the network

Keywords

generalisation (artificial intelligence); learning (artificial intelligence); neural nets; direct method for structural learning; localised representation; neural networks; nonskeletal local representation; pruning; regularities; rule extraction; Computer errors; Computer networks; Cost function; Data mining; Intelligent networks; Neural networks; Skeleton; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.687226

Filename

687226