{"updated":"2025-01-21T00:54:25.733893+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00128529","sets":["6504:8089:8094"]},"path":["8094"],"owner":"1","recid":"128529","title":["確率的考察に基づくブール関数学習則の最適化"],"pubdate":{"attribute_name":"公開日","attribute_value":"1995-09-20"},"_buckets":{"deposit":"79bbab76-72fb-4330-aeaa-69c331f57a8b"},"_deposit":{"id":"128529","pid":{"type":"depid","value":"128529","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"確率的考察に基づくブール関数学習則の最適化","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"確率的考察に基づくブール関数学習則の最適化"},{"subitem_title":"Optimum Learning Rules for Boolean functions based on Bayesian Statistics","subitem_title_language":"en"}]},"item_type_id":"22","publish_date":"1995-09-20","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":"早稲田大学 理工学部 工業経営学科"},{"subitem_text_value":"早稲田大学 理工学部 工業経営学科"},{"subitem_text_value":"早稲田大学 理工学部 工業経営学科"}]},"item_22_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Industrial Engineering and Management, School of Science and Engineering, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Department of Industrial Engineering and Management, School of Science and Engineering, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Department of Industrial Engineering and Management, School of Science and Engineering, Waseda University","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/128529/files/KJ00001334808.pdf"},"date":[{"dateType":"Available","dateValue":"1995-09-20"}],"format":"application/pdf","filename":"KJ00001334808.pdf","filesize":[{"value":"185.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"3f193a4c-fc5a-4930-b568-571ddbe62f85","displaytype":"detail","licensetype":"license_note"}]},"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":"Littlestoneは線形分離可能なブール関数(特に単調連言形,単調選言形)を対象として,リテラルの重み更新による学習アルゴリズムWINNOW1[3]を提案した.しかし計算論的な立場が強いため,重みの更新法についての理論的根拠が希薄であった.これに対し野村らは統計的決定論の立場から最適性を考慮した予測アルゴリズム,重み更新アルゴリズム[1]を提案した.本研究はこの立場に基づき,学習対象を非単調連言形・選言形のクラスまで拡張した場合の学習アルゴリズムを最初に提案する.さらに学習対象をブール関数全体のクラスに対応するアルゴリズムを示し,これらのアルゴリズムの最適性についてベイズ統計学の立場から明らかにする.最後に概念学習の枠組みに適用した場合について論じる.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"176","bibliographic_titles":[{"bibliographic_title":"全国大会講演論文集"}],"bibliographicPageStart":"175","bibliographicIssueDates":{"bibliographicIssueDate":"1995-09-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"人工知能と認知科学","bibliographicVolumeNumber":"第51回"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-19T00:07:52.705954+00:00","id":128529,"links":{}}