{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214812","sets":["6504:10735:10808"]},"path":["10808"],"owner":"44499","recid":"214812","title":["CGCNNを用いた材料特性値予測モデルにおけるハイパパラメータ最適化による効果"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"b7b2fd6b-9622-4691-8ba4-0461d1191fbf"},"_deposit":{"id":"214812","pid":{"type":"depid","value":"214812","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"CGCNNを用いた材料特性値予測モデルにおけるハイパパラメータ最適化による効果","author_link":["552777","552778","552780","552779"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"CGCNNを用いた材料特性値予測モデルにおけるハイパパラメータ最適化による効果"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2021-03-04","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"産業技術総合研究所/パナソニック"},{"subitem_text_value":"産業技術総合研究所/パナソニック"},{"subitem_text_value":"パナソニック"},{"subitem_text_value":"パナソニック"}]},"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/214812/files/IPSJ-Z83-2C-02.pdf","label":"IPSJ-Z83-2C-02.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-28"}],"format":"application/pdf","filename":"IPSJ-Z83-2C-02.pdf","filesize":[{"value":"738.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"ddb88d25-43d7-4b4a-a591-8705c83f9000","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"西川, 由理"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小澤, 順"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"網井, 圭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤井, 幹也"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，材料インフォマティクス分野で，Crystal Graph Convolutional Neural Network (CGCNN) をはじめ深層学習に基づく特性値予測モデルの開発が進んでいる．一方，機械学習のハイパパラメータ探索に関する技術開発も進んでおり，中でもOptunaは複数の計算プロセスで探索条件を共有しながら並列にベイズ最適化を行う機能を有する．  本研究では，CGCNNを用いた材料データベースMaterials Projectの学習時にOptunaを適用し，公開モデルと比較した特性値予測誤差の改善効果，およびCGCNNの開発者らが適用したランダムサーチと比べた探索効率の評価について報告する．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"12","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"11","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":214812,"updated":"2025-01-19T16:27:25.226255+00:00","links":{},"created":"2025-01-19T01:15:36.508434+00:00"}