Letters: Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

Authors:
E. Soria-Olivas;J. D. Martín-Guerrero;A. J. Serrano-López;J. Calpe-Maravilla;J. Vila-Francés;G. Camps-Valls
Affiliations:
Dept. Enginyeria Electrònica, Universitat de València, Spain;Dept. Enginyeria Electrònica, Universitat de València, Spain;Dept. Enginyeria Electrònica, Universitat de València, Spain;Dept. Enginyeria Electrònica, Universitat de València, Spain;Dept. Enginyeria Electrònica, Universitat de València, Spain;Dept. Enginyeria Electrònica, Universitat de València, Spain
Venue:
Neurocomputing
Year:
2006

Citing 5
Cited 0

Adaptive filter theory (3rd ed.)

Adaptive filter theory (3rd ed.)
Simultaneous optimization of neural network function and architecture algorithm

Decision Support Systems
The application of nonlinear structures to the reconstruction ofbinary signals

IEEE Transactions on Signal Processing
A low-complexity fuzzy activation function for artificial neural networks

IEEE Transactions on Neural Networks
Pruning algorithms-a survey

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

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. Martin, G. Camps, A. Serrano, J. Calpe, L. Gomez, 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.