WEKO3
アイテム
Visualizing and Understanding Policy Networks of Computer Go
https://ipsj.ixsq.nii.ac.jp/records/210674
https://ipsj.ixsq.nii.ac.jp/records/2106746e0bf3a1-eae8-425e-8565-92c502078703
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-JNL6204022.pdf (5.4 MB)
|
Copyright (c) 2021 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | Journal(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2021-04-15 | |||||||||
| タイトル | ||||||||||
| タイトル | Visualizing and Understanding Policy Networks of Computer Go | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Visualizing and Understanding Policy Networks of Computer Go | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | [一般論文] computer Go, deep learning, visualization, policy network, grad-CAM | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||
| 資源タイプ | journal article | |||||||||
| 著者所属 | ||||||||||
| The University of Electro-Communication | ||||||||||
| 著者所属 | ||||||||||
| The University of Electro-Communication | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| The University of Electro-Communication | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| The University of Electro-Communication | ||||||||||
| 著者名 |
Yuanfeng, Pang
× Yuanfeng, Pang
× Takeshi, Ito
|
|||||||||
| 著者名(英) |
Yuanfeng, Pang
× Yuanfeng, Pang
× Takeshi, Ito
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Deep learning for the game of Go achieved considerable success with the victory of AlphaGo against Ke Jie in May 2017. Thus far, there is no clear understanding of why deep learning performs so well in the game of Go. In this paper, we introduce visualization techniques used in image recognition that provide insights into the function of intermediate layers and the operation of the Go policy network. When used as a diagnostic tool, these visualizations enable us to understand what occurs during the training process of policy networks. Further, we introduce a visualization technique that performs a sensitivity analysis of the classifier output by occluding portions of the input Go board, and revealing parts that important for predicting the next move. Further, we attempt to identify important areas through Grad-CAM and combine it with the Go board to provide explanations for next move decisions. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.29(2021) (online) DOI http://dx.doi.org/10.2197/ipsjjip.29.347 ------------------------------ |
|||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Deep learning for the game of Go achieved considerable success with the victory of AlphaGo against Ke Jie in May 2017. Thus far, there is no clear understanding of why deep learning performs so well in the game of Go. In this paper, we introduce visualization techniques used in image recognition that provide insights into the function of intermediate layers and the operation of the Go policy network. When used as a diagnostic tool, these visualizations enable us to understand what occurs during the training process of policy networks. Further, we introduce a visualization technique that performs a sensitivity analysis of the classifier output by occluding portions of the input Go board, and revealing parts that important for predicting the next move. Further, we attempt to identify important areas through Grad-CAM and combine it with the Go board to provide explanations for next move decisions. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.29(2021) (online) DOI http://dx.doi.org/10.2197/ipsjjip.29.347 ------------------------------ |
|||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AN00116647 | |||||||||
| 書誌情報 |
情報処理学会論文誌 巻 62, 号 4, 発行日 2021-04-15 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 1882-7764 | |||||||||
