{"created":"2021-03-01T06:17:20.457737+00:00","id":792,"links":{},"metadata":{"_buckets":{"deposit":"ee520778-a948-4077-a95d-3120f22d2b8d"},"_deposit":{"id":"792","owners":[],"pid":{"revision_id":0,"type":"depid","value":"792"},"status":"published"},"_oai":{"id":"oai:repository.dl.itc.u-tokyo.ac.jp:00000792","sets":["6:32:33","9:10:14"]},"item_2_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Inverse Model Learning by USing Extended Feedback System"}]},"item_2_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1995-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicPageEnd":"357","bibliographicPageStart":"349","bibliographicVolumeNumber":"78","bibliographic_titles":[{"bibliographic_title":"電子情報通信学会論文誌. D-II, 情報・システム, II-情報処理"}]}]},"item_2_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"対象システムの目標出力を与えたとき，それを実現するシステムへの入力を求める問題は逆問題と呼ばれている．対象システムの特性が未知であるとき，対象システムの入出力を観測し，神経回路等の学習要素を用いて，対象システムの逆モデルを学習することによって， 逆問題を解くシステムが研究されている．逆モデルの学習法として，いくつかの手法が提案されているが ，いずれも問題を抱えている。反復解法と乱数による初期値探索と組み合わせることによって，連続な非線形システムの逆 問題の解を得ることができる．逆問題の解法システムとして，初期値探索機構を付加した反復解法を行 う拡張フィードバック系と逆モデルの複合システムを提案する．従来法では正確な逆モデルを得ることが難しい対象システムについても，反復解法システムによって得た解を逆モデルの教師信号として利用することにより，正確な逆モデルの獲得が可能である．更に，逆問題の求解計算時においては，逆モデルの出力を反復計算の初期値とすることにより，高速に解を得ることが可能である．多項式関数について，逆 モデルを獲得する数値実験を行い，提案した手法の評価を行う．","subitem_description_type":"Abstract"}]},"item_2_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"3041","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Oyama, Eimei"}]},{"nameIdentifiers":[{"nameIdentifier":"3042","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Tachi, Susumu"}]}]},"item_2_publisher_20":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"電子情報通信学会"}]},"item_2_relation_25":{"attribute_name":"関係URI","attribute_value_mlt":[{"subitem_relation_type_id":{"subitem_relation_type_id_text":"http://www.ieice.org/eng/","subitem_relation_type_select":"URI"}}]},"item_2_rights_12":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"copyright©1995 IEICE, 許諾番号07RB0130"}]},"item_2_source_id_10":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN1007132X","subitem_source_identifier_type":"NCID"}]},"item_2_source_id_8":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"09151923","subitem_source_identifier_type":"ISSN"}]},"item_2_subject_15":{"attribute_name":"日本十進分類法","attribute_value_mlt":[{"subitem_subject":"007","subitem_subject_scheme":"NDC"}]},"item_2_text_4":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"機械技術研究所"},{"subitem_text_value":"東京大学工学部"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大山, 英明"}],"nameIdentifiers":[{"nameIdentifier":"3039","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"舘, 暲"}],"nameIdentifiers":[{"nameIdentifier":"3040","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2017-05-30"}],"displaytype":"detail","filename":"tachi_1995_036c.pdf","filesize":[{"value":"589.9 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"tachi_1995_036c.pdf","url":"https://repository.dl.itc.u-tokyo.ac.jp/record/792/files/tachi_1995_036c.pdf"},"version_id":"12445e55-a6a7-43c0-a4bb-c01fc4a808fe"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"神経回路","subitem_subject_scheme":"Other"},{"subitem_subject":"逆問題","subitem_subject_scheme":"Other"},{"subitem_subject":"逆モデル","subitem_subject_scheme":"Other"},{"subitem_subject":"複合逆問題解法システム","subitem_subject_scheme":"Other"},{"subitem_subject":"反復解法","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"拡張フィードバック系による逆モデル学習","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"拡張フィードバック系による逆モデル学習"}]},"item_type_id":"2","owner":"1","path":["14","33"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-01-06"},"publish_date":"2017-01-06","publish_status":"0","recid":"792","relation_version_is_last":true,"title":["拡張フィードバック系による逆モデル学習"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-19T03:41:52.045129+00:00"}