Optimal Brain Surgeon Variants for Feature Selection

Mohammed Attik 1 Laurent Bougrain 1 Frédéric Alexandre 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper presents three pruning algorithms based on Optimal Brain Surgeon (OBS) and Unit-Optimal Brain Surgeon (Unit-OBS). The first variant performs a backward selection by successively removing single weights from the input variables to the hidden units in a fully connected multilayer perceptron (MLP) for variable selection. The second one removes a subset of non-significant weights in one step. The last one combines the two properties presented above. Simulation results obtained on the Monk's problem illustrate the specificities of each method described in this paper according to the preserved variables and the preserved weights.
Type de document :
Communication dans un congrès
International Joint Conference on Neural Networks - IJCNN'04, 2004, Budapest, Hungary, 4 p, 2004
Liste complète des métadonnées

https://hal.inria.fr/inria-00099923
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 10:09:46
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48
Document(s) archivé(s) le : mercredi 29 mars 2017 - 13:19:39

Fichiers

Identifiants

  • HAL Id : inria-00099923, version 1

Collections

Citation

Mohammed Attik, Laurent Bougrain, Frédéric Alexandre. Optimal Brain Surgeon Variants for Feature Selection. International Joint Conference on Neural Networks - IJCNN'04, 2004, Budapest, Hungary, 4 p, 2004. 〈inria-00099923〉

Partager

Métriques

Consultations de la notice

208

Téléchargements de fichiers

38