A low-complexity fuzzy activation function for artificial neural networks

E Soria-Olivas; J D Martin-Guerrero; G Camps-Valls; A J Serrano-Lopez; J Calpe-Maravilla; L Gomez-Chova

doi:10.1109/TNN.2003.820444

A low-complexity fuzzy activation function for artificial neural networks

IEEE Trans Neural Netw. 2003;14(6):1576-9. doi: 10.1109/TNN.2003.820444.

Authors

E Soria-Olivas¹, J D Martin-Guerrero, G Camps-Valls, A J Serrano-Lopez, J Calpe-Maravilla, L Gomez-Chova

Affiliation

¹ Dept. of Enginyeria Electronica, Univ. de Valencia, Spain.

PMID: 18244604
DOI: 10.1109/TNN.2003.820444

Abstract

A novel fuzzy-based activation function for artificial neural networks is proposed. This approach provides easy hardware implementation and straightforward interpretability in the basis of IF-THEN rules. Backpropagation learning with the new activation function also has low computational complexity. Several application examples ( XOR gate, chaotic time-series prediction, channel equalization, and independent component analysis) support the potential of the proposed scheme.