In this paper, we present a review of feature selection methods based on an analysis of the training set which have been applied to neural networks. This type of methods uses information theory concepts, interclass and intraclass distances or an analysis of fuzzy regions. Furthermore, a methodology that allows evaluating and comparing feature selection methods is carfully described. This methodology is applied to the 7 reviewed methods in a total of 15 different real world classification problems. We present an ordination of methods according to its performance and it is clearly concluded which method performs better and should be used. We also discuss the applicability and computational complexity of the methods.
展开▼
