Name
Abstract | ||
|---|---|---|
A novel fuzzy-based activation function for artificial neural networks is proposed. This approach provides easy hardware implemen- tation 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. Index Terms—Activation function, fuzzy logic, rule extraction. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/TNN.2003.820444 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
if-then rule,chaotic time-series prediction,easy hardware implementation,xor gate,application example,new activation function,proposed scheme,channel equalization,artificial neural network,activation function,low-complexity fuzzy activation function,computational complexity,independent component analysis,indexing terms,fuzzy logic,transfer functions,backpropagation | Interpretability,Rectifier (neural networks),Neuro-fuzzy,Computer science,Activation function,Fuzzy logic,XOR gate,Artificial intelligence,Backpropagation,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
14 | 6 | 1045-9227 |
Citations | PageRank | References |
16 | 1.57 | 1 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| E. Soria | 1 | 200 | 13.22 |
| J. D. Martin-Guerrero | 2 | 25 | 2.52 |
| Camps-Valls, G. | 3 | 441 | 29.69 |
| Antonio José Serrano-López | 4 | 22 | 2.51 |
| Javier Calpe-Maravilla | 5 | 92 | 11.69 |
| L Gomez-Chova | 6 | 16 | 1.57 |