Improved data structure and deep convolutional network design for haifu data learning in the game of mahjong

• Item type: National Convention(1)
• 公開日: 2018-03-13
• タイトル: Improved data structure and deep convolutional network design for haifu data learning in the game of mahjong
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 人工知能と認知科学
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東大
• 著者名: 高, 世祺; 奥谷, 文徳; 水上, 直紀; 川原, 圭博
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The accordance rate of haifu data is recognized as a benchmark for estimating the machine's learning ability. Traditional mahjong learning methods were mainly by human artificially extracting features and designing function blocks. Although there has been related researches in deep learning^[1] and CNN^[2] these two years, they still cannot exceed traditional methods' result due to their methods' limits. In this paper, based on previous CNN work, we built an improved data structure in order for not missing important information. For the deep neural network, we elaborately separate the information gained into different input parts and make the merge after some feature extraction. We show our result much better than the previous deep learning study, and also surpasses state-of-art traditional result^[3] on this task.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00349328
• 書誌情報: 第80回全国大会講演論文集; 巻 2018, 号 1, p. 61-62, 発行日 2018-03-13
• 出版者 / 言語: ja
• 出版者: 情報処理学会