A survey on supervised learning by evolving multi-layer perceptrons

Author

Ribert, Arnaud ; Stocker, Emmanuel ; Lecourtier, Yves ; Ennaji, Abdel

Author_Institution

Fac. des Sci., Rouen Univ., Mont-Saint-Aignan, France

fYear

1999

fDate

1999

Firstpage

122

Lastpage

126

Abstract

This paper provides a guide to evolving-architecture neural networks for a beginner in multi-layer perceptrons. All the quoted methods aim at automatically fitting a neural network architecture to a particular classification task. Several kinds of evolving architectures are exposed. Some neural networks start small and become bigger and bigger during the learning, whereas others start over-dimensioned and undergo pruning. A last network category uses both methods alternately

Keywords

evolutionary computation; learning (artificial intelligence); multilayer perceptrons; neural net architecture; pattern classification; reconfigurable architectures; reviews; automatic task fitting; classification task; evolving multilayer perceptrons; evolving-architecture neural networks; network pruning; neural net architecture; over-dimensioned networks; supervised learning; survey; Backpropagation algorithms; Buildings; Convergence; Genetic algorithms; Logic testing; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Supervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Multimedia Applications, 1999. ICCIMA '99. Proceedings. Third International Conference on

Conference_Location

New Delhi

Print_ISBN

0-7695-0300-4

Type

conf

DOI

10.1109/ICCIMA.1999.798514

Filename

798514