{"created":"2021-03-01T06:07:13.430733+00:00","id":3466,"links":{},"metadata":{"_buckets":{"deposit":"854f989e-67a6-4a7b-9aaa-e8a831d84c00"},"_deposit":{"id":"3466","owners":[],"pid":{"revision_id":0,"type":"depid","value":"3466"},"status":"published"},"_oai":{"id":"oai:niigata-u.repo.nii.ac.jp:00003466","sets":["423:424:425","453:454"]},"item_5_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Learning Regular Languages via Recurrent Higher-Order Neural Network"}]},"item_5_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1996-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicPageEnd":"907","bibliographicPageStart":"899","bibliographicVolumeNumber":"J79-D-II","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"},{"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","bibliographic_titleLang":"en"}]}]},"item_5_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"正規言語の学習は，有限オートマトンの獲得と等価な問題である．ニューラルネットワークにより正規言語の学習を行う場合，それが有限オートマトンの任意の状態遷移関数を実現できる必要がある．本論文ではまず，Gilesら[5]の提案した相互結合型ニューラルネットワークが，受理系の状態表現を局所的にすることで任意の状態遷移関数を実現できることを示す．しかし，局所的な状態表現を学習によって獲得することは現時点では困難である．そこで，任意の論理関数が実現できる階層型高次結合ニューラルネットワークの出力を入力に帰還させることで，そのような状態表現が与えられても任意の状態遷移関数が実現できる再帰型高次結合ニューラルネットワークを提案する．階層型高次結合ニューラルネットワークは最大次数までの高次結合を含むが，これが任意の論理関数を実現できるためには最大次数の高次結合が必要十分であることを示す．また，再帰型高次結合ニューラルネットワークを対象としたこう配法による学習アルゴリズムを導出する．最後に，いくつかの正規言語を例題として実験を行い，本モデルがGilesらのモデルに対し学習成功率の点で勝っていることを示す．","subitem_description_type":"Abstract"}]},"item_5_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"43154","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Tanaka, Ken"}]},{"nameIdentifiers":[{"nameIdentifier":"43155","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Kumazawa, Itsuo"}]},{"nameIdentifiers":[{"nameIdentifier":"43156","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Ogawa, Hidemitsu"}]}]},"item_5_publisher_7":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"電子情報通信学会"}]},"item_5_relation_31":{"attribute_name":"異版である","attribute_value_mlt":[{"subitem_relation_type":"isVersionOf","subitem_relation_type_id":{"subitem_relation_type_id_text":"http://www.ieice.org/jpn/trans_online/","subitem_relation_type_select":"URI"}}]},"item_5_rights_15":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"copyright©1996 IEICE"}]},"item_5_select_19":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_select_item":"publisher"}]},"item_5_source_id_11":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN1007132X","subitem_source_identifier_type":"NCID"}]},"item_5_source_id_9":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"09151923","subitem_source_identifier_type":"ISSN"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田中, 賢"}],"nameIdentifiers":[{"nameIdentifier":"43151","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"熊沢, 逸夫"}],"nameIdentifiers":[{"nameIdentifier":"43152","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"小川, 英光"}],"nameIdentifiers":[{"nameIdentifier":"43153","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":"2019-07-30"}],"displaytype":"detail","filename":"J79-D-2(5)_899-907.pdf","filesize":[{"value":"1.7 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"J79-D-2(5)_899-907.pdf","url":"https://niigata-u.repo.nii.ac.jp/record/3466/files/J79-D-2(5)_899-907.pdf"},"version_id":"e306db19-b3e6-4314-8154-a801e4229937"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"再帰型ニューラルネットワーク","subitem_subject_scheme":"Other"},{"subitem_subject":"高次結合ニューラルネットワーク","subitem_subject_scheme":"Other"},{"subitem_subject":"正規言語","subitem_subject_scheme":"Other"},{"subitem_subject":"有限オートマトン","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":"再帰型高次結合ニューラルネットワークによる正規言語の学習","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"再帰型高次結合ニューラルネットワークによる正規言語の学習"},{"subitem_title":"再帰型高次結合ニューラルネットワークによる正規言語の学習","subitem_title_language":"en"}]},"item_type_id":"5","owner":"1","path":["454","425"],"pubdate":{"attribute_name":"公開日","attribute_value":"2008-10-27"},"publish_date":"2008-10-27","publish_status":"0","recid":"3466","relation_version_is_last":true,"title":["再帰型高次結合ニューラルネットワークによる正規言語の学習"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-15T03:36:36.396085+00:00"}