Presentation | 1997/3/17 Structure Determination of Neural Networks Using Genetic Algorithm and Structual Learning Kazuhiko Nishino, Masumi Ishikawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose the integrated learning method combining structual learning good at local search and genetic algorithm good at global search. The combination of genetic algorithm and structual learning is expected to have both large local search capability and large local search capability. The optimum structure search of recrrent networks which have especially large serach space is tried using artificial time series data and gas furnace data. The effectiveness of the proposed metheod is well demonstrated. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | genetic algorithm / structual learning / recurrent network |
Paper # | NC96-119 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/3/17(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) | Structure Determination of Neural Networks Using Genetic Algorithm and Structual Learning |
Sub Title (in English) | |
Keyword(1) | genetic algorithm |
Keyword(2) | structual learning |
Keyword(3) | recurrent network |
1st Author's Name | Kazuhiko Nishino |
1st Author's Affiliation | Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology() |
2nd Author's Name | Masumi Ishikawa |
2nd Author's Affiliation | Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology |
Date | 1997/3/17 |
Paper # | NC96-119 |
Volume (vol) | vol.96 |
Number (no) | 583 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |