Presentation | 2006-06-16 Learning Go using neural networks and generalization to unknown situation Yasuhiro OGATA, Noboru MURATA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The complexity of a Go game makes it hard to determine a preferable step. We used a three-layered perception to generate an agent predicting the best step in each stage of the game. Simply applying Neural Networks by inputting all phases would end up in too many parameters, requiring plenty of training data and learning time. We propose a method limiting the situation to some special phases, reducing the number of parameters and computation time. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Go / Neural Networks / three-layered Perceptron / Error Back Propagation / Learning Theory |
Paper # | NC2006-23 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2006/6/9(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) | Learning Go using neural networks and generalization to unknown situation |
Sub Title (in English) | |
Keyword(1) | Go |
Keyword(2) | Neural Networks |
Keyword(3) | three-layered Perceptron |
Keyword(4) | Error Back Propagation |
Keyword(5) | Learning Theory |
1st Author's Name | Yasuhiro OGATA |
1st Author's Affiliation | Waseda University() |
2nd Author's Name | Noboru MURATA |
2nd Author's Affiliation | Waseda University |
Date | 2006-06-16 |
Paper # | NC2006-23 |
Volume (vol) | vol.106 |
Number (no) | 102 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |