6533b861fe1ef96bd12c565a

RESEARCH PRODUCT

Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

José D. Martín-guerreroJoan Vila-francésJavier Calpe-maravillaAntonio J. Serrano-lópezGustau Camps-vallsEmilio Soria-olivas

subject

Artificial neural networkComputer sciencebusiness.industryTime delay neural networkCognitive NeuroscienceActivation functionRectifier (neural networks)PerceptronFuzzy logicComputer Science ApplicationsArtificial IntelligenceMultilayer perceptronFeedforward neural networkPruning (decision trees)Artificial intelligenceTypes of artificial neural networksbusiness

description

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.

yearjournalcountryeditionlanguage
2006-03-01Neurocomputing
https://doi.org/10.1016/j.neucom.2005.04.013