{"created":"2025-01-19T01:29:11.798112+00:00","updated":"2025-01-19T11:24:30.615578+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229811","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"229811","title":["系列信号の長期的依存関係を学習するための自己・相互注意機構を用いたリザバーコンピューティングの提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"a539e6e4-7581-4832-b349-ca98892cd752"},"_deposit":{"id":"229811","pid":{"type":"depid","value":"229811","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"系列信号の長期的依存関係を学習するための自己・相互注意機構を用いたリザバーコンピューティングの提案","author_link":["618181","618182","618180"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"系列信号の長期的依存関係を学習するための自己・相互注意機構を用いたリザバーコンピューティングの提案"}]},"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":"2023-02-16","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":"東大"},{"subitem_text_value":"東大"},{"subitem_text_value":"東大"}]},"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/229811/files/IPSJ-Z85-6B-05.pdf","label":"IPSJ-Z85-6B-05.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-6B-05.pdf","filesize":[{"value":"499.9 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"4cf3d4b7-75b0-4e16-81d4-e1892c859bf4","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小西, 文昂"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"廣瀬, 明"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"夏秋, 嶺"}],"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":"自然言語処理タスクにおいて著しい性能向上と学習時間の短縮に成功したTransformerは、近年、時系列データの予測など様々な系列データに対して適用されている。本論文は、再帰型ニューラルネットワークの一種であるリザバーコンピューティングに、Transformerの重要な構成要素となっている自己注意機構(self-attention)と相互注意機構(cross-attention)を組み込むことによって、系列信号フィルタリングのための長期的な依存関係を捉えることができるモデルを提案する。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"20","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"19","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229811,"links":{}}