Function Approximation Performance of Fuzzy Neural Networks
| Cím | Function Approximation Performance of Fuzzy Neural Networks |
| Közlemény típusa | Journal Article |
| Kiadás éve | 2010 |
| Szerzők | Lovassy, R., L. T. Kóczy, and L. Gál |
| Folyóirat | Acta Polytechnica Hungarica, Journal of Applied Sciences |
| Évfolyam | 7 |
| Kötet | 4 |
| Oldalszám | 25-38 |
| Kiadás dátuma | 2010 |
| Kiadás nyelve | English |
| ISSN Number | 1785-8860 |
| Összefoglalás | In this paper we propose a Multilayer Perceptron Neural Network (MLP NN) consisting of fuzzy flip-flop neurons based on various fuzzy operations applied in order to approximate real life application, two input trigonometric functions furthermore two and six dimensional benchmark problems. The Bacterial Memetic Algorithm with Modified Operator Execution Order algorithm (BMAM) is proposed for Fuzzy Neural Networks (FNN) training. The simulation results showed that various FNN types delivered very good function approximation results. |