LIP6 1998/012: Rapport de Recherche
27 pages - Mars/March 1998 - Document en anglais.
PostScript : 53 Ko /Kb
Contact : par mail / e-mail
Thème/Team: Apprentissage et Acquisition de Connaissances
Titre français : Sélection de Variables et Réseaux de Neurones
Titre anglais : Feature Selection with Neural Networks
Abstract : Features gathered from the observation of a phenomenon are not all equally informative: some of them may be noisy, correlated or irrelevant. Feature selection aims at selecting a feature set that is relevant for a given task. This problem is complex and remains an important issue in many domains. In the field of neural networks, feature selection has been studied for the last ten years and classical as well as original methods have been employed. This paper is a review of neural network approaches to feature selection. We first briefly introduce baseline statistical methods used in regression and classification. We then describe families of methods which have been developed specifically for neural networks. Representative methods are then compared on different test problems.
Key-words : Feature Selection, Subset selection, Variable Sensitivity, Sequential Search
Publications internes LIP6 1998 / LIP6 research reports 1998
Éditorial / Editor