Author/Authors :
E.، Soria-Olivas, نويسنده , , J.D.، Martin-Guerrero, نويسنده , , G.، Camps-Valls, نويسنده , , A.J.، Serrano-Lopez, نويسنده , , J.، Calpe-Maravilla, نويسنده , , L.، Gomez-Chova, نويسنده ,
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.
