{"created":"2025-01-19T01:28:26.650458+00:00","updated":"2025-01-19T11:34:30.900527+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229347","sets":["6164:6165:6210:11423"]},"path":["11423"],"owner":"44499","recid":"229347","title":["Life-and-death Problem Prediction using Deep Convolutional Neural Network in the Game of Go"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-10"},"_buckets":{"deposit":"1d92cb3f-c11d-406b-868a-b5dcae18e000"},"_deposit":{"id":"229347","pid":{"type":"depid","value":"229347","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Life-and-death Problem Prediction using Deep Convolutional Neural Network in the Game of Go","author_link":["616587","616586","616585","616588","616583","616584"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Life-and-death Problem Prediction using Deep Convolutional Neural Network in the Game of Go"},{"subitem_title":"Life-and-death Problem Prediction using Deep Convolutional Neural Network in the Game of Go","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"computer games","subitem_subject_scheme":"Other"},{"subitem_subject":"the game of Go","subitem_subject_scheme":"Other"},{"subitem_subject":"life-and-death problems","subitem_subject_scheme":"Other"},{"subitem_subject":"Deep Convolutional Neural Network","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2023-11-10","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Dong Hwa University, Taiwan"},{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Dong Hwa University, Taiwan"},{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Taipei University, Taiwan"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Dong Hwa University, Taiwan","subitem_text_language":"en"},{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Dong Hwa University, Taiwan","subitem_text_language":"en"},{"subitem_text_value":"Dept. Of Computer Science and Information Engineering, National Taipei University, Taiwan","subitem_text_language":"en"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/229347/files/IPSJ-GPWS2023014.pdf","label":"IPSJ-GPWS2023014.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GPWS2023014.pdf","filesize":[{"value":"628.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"18"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"7cf380cf-3a97-4653-a92b-17e8340dbcd6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shi-Jim, Yen"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Guan-Lun, Chen"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jr-Chang, Chen"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shi-Jim, Yen","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Guan-Lun, Chen","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jr-Chang, Chen","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"The life-and-death problem in Go is regarded as a very important research topic because it requires a completely correct response and often occurs during the game. The research on the life-and-death problem includes methods such as search trees and feature simulation. Deep Convolutional Neural Network (DCNN), which has been proven to be applied to the game of Go, can achieve a higher accuracy rate of predicting the next move and increase the strength of the Go program. This paper trains a DCNN model to predict correct moves for life-and-death problems in the game of Go. We use the classic life-and-death problems of Go, including 5925 questions in the training data and 96 questions in the test data. From these questions, 281444 game boards and 3496 game boards can be generated for training and testing. The experimental results show that the accuracy of DCNN answering the life-and-death problem is 96.90% for the first move, and the accuracy for the consecutive moves is 90.25%, and the predicted move has a high accuracy. This paper also studies adding the model of the life-and-death problem to the model for predicting the next move, trying to improve the accuracy of predicting the next move.","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The life-and-death problem in Go is regarded as a very important research topic because it requires a completely correct response and often occurs during the game. The research on the life-and-death problem includes methods such as search trees and feature simulation. Deep Convolutional Neural Network (DCNN), which has been proven to be applied to the game of Go, can achieve a higher accuracy rate of predicting the next move and increase the strength of the Go program. This paper trains a DCNN model to predict correct moves for life-and-death problems in the game of Go. We use the classic life-and-death problems of Go, including 5925 questions in the training data and 96 questions in the test data. From these questions, 281444 game boards and 3496 game boards can be generated for training and testing. The experimental results show that the accuracy of DCNN answering the life-and-death problem is 96.90% for the first move, and the accuracy for the consecutive moves is 90.25%, and the predicted move has a high accuracy. This paper also studies adding the model of the life-and-death problem to the model for predicting the next move, trying to improve the accuracy of predicting the next move.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"75","bibliographic_titles":[{"bibliographic_title":"ゲームプログラミングワークショップ2023論文集"}],"bibliographicPageStart":"73","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-10","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229347,"links":{}}