A low-complexity fuzzy activation function for artificial neural networks
Emilio Soria‐Olivas, José D. Martín‐Guerrero, Gustau Camps‐Valls, Antonio José Serrano-López, Javier Calpe‐Maravilla, Luis Gómez‐Chova · IEEE Transactions on Neural Networks · 2003
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.