Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martín, G. Camps, A. Serrano, J. Calpe, L. Gómez, A low-complexity fuzzy activation function for artificial neural networks,...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2006-03, Vol.69 (7), p.909-912
Main Authors: Soria-Olivas, E., Martín-Guerrero, J.D., Serrano-López, A.J., Calpe-Maravilla, J., Vila-Francés, J., Camps-Valls, G.
Format: Article
Language:English
Subjects:
Fuzzy sigmoid
Multilayer perceptron
Pruning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martín, G. Camps, A. Serrano, J. Calpe, L. Gómez, A low-complexity fuzzy activation function for artificial neural networks, IEEE Trans. Neural Networks 14(6) (2003) 1576–1579]. Successful performance is obtained in standard function approximation and channel equalization problems. Pruning allows to reduce network complexity considerably, achieving a similar performance to that obtained by unpruned networks.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2005.04.013