A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
Geometrical Selection of Important Inputs with Feedforward Neural Networks
[chapter]
1998
Artificial Neural Nets and Genetic Algorithms
Preserved Fulltext
In this paper, we introduce a method that allows to evaluate efficiently the "importance" of each coordinate of the input vector of a neural network. This measurement can be used to obtain informations about the studied data. It can also be used to suppress irrelevant inputs in order to speed up the classification process conducted by the network.
doi:10.1007/978-3-7091-6492-1_118
dblp:conf/icannga/Rossi97
fatcat:qz22kl4cwzdttch6f5rqymz23m