| Presentation | 2005-06-23 Analysis for Characteristics of GA-based Learning to Binary Neural Networks Tatsuya HIRANE, Hidehiro NAKANO, Arata MIYAUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we analyze characteristics of GA-based learning to Binary Neural Networks (BNNs). First, we consider coding methods for the BNN, and discuss necessary size of genes in GA for learning. Next, we compare various selection methods in GA. The learning results can be obtained in the less number of generations due to selection methods and parameters, and the quality of the results can be the almost same as conventional ones. These results can be verified by numerical experiments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Binary Neural Network / GA / ETL / Learning |
| Paper # | NLP2005-21 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2005/6/16(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 | Nonlinear Problems (NLP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis for Characteristics of GA-based Learning to Binary Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | Binary Neural Network |
| Keyword(2) | GA |
| Keyword(3) | ETL |
| Keyword(4) | Learning |
| 1st Author's Name | Tatsuya HIRANE |
| 1st Author's Affiliation | Musashi Institute of Technology() |
| 2nd Author's Name | Hidehiro NAKANO |
| 2nd Author's Affiliation | Musashi Institute of Technology |
| 3rd Author's Name | Arata MIYAUCHI |
| 3rd Author's Affiliation | Musashi Institute of Technology |
| Date | 2005-06-23 |
| Paper # | NLP2005-21 |
| Volume (vol) | vol.105 |
| Number (no) | 125 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |