| Presentation | 1996/2/3 A Wavelet Neural Network with Evolutionally Generated Structure Nobuaki UEDA, Kunikazu KOBAYASHI, Toyoshi TORIOKA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A new learning algorithm for wavelet neural networks is proposed. It is combined genetic algorithms and backpropagation algorithm. We encode each network as one individual and generate a population. According to the fitness calculated by error and the number of hidden units, the better individuals are put into genetic operations. Their parameters are updated by backpropagation algorithm. The validity of the proposed algorithm was confirmed through computer simulations. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | wavelet / function approximation / genetic algorithm / backpropagation |
| Paper # | NC95-111 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1996/2/3(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Wavelet Neural Network with Evolutionally Generated Structure |
| Sub Title (in English) | |
| Keyword(1) | wavelet |
| Keyword(2) | function approximation |
| Keyword(3) | genetic algorithm |
| Keyword(4) | backpropagation |
| 1st Author's Name | Nobuaki UEDA |
| 1st Author's Affiliation | Fac. of Engineering, Yamaguchi University() |
| 2nd Author's Name | Kunikazu KOBAYASHI |
| 2nd Author's Affiliation | Fac. of Engineering, Yamaguchi University |
| 3rd Author's Name | Toyoshi TORIOKA |
| 3rd Author's Affiliation | Fac. of Engineering, Yamaguchi University |
| Date | 1996/2/3 |
| Paper # | NC95-111 |
| Volume (vol) | vol.95 |
| Number (no) | 506 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |