{"created":"2021-03-01T06:07:12.249160+00:00","id":3447,"links":{},"metadata":{"_buckets":{"deposit":"146b9ad9-a8b7-4a69-89dc-7f24aab187a8"},"_deposit":{"id":"3447","owners":[],"pid":{"revision_id":0,"type":"depid","value":"3447"},"status":"published"},"_oai":{"id":"oai:niigata-u.repo.nii.ac.jp:00003447","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":"On Computational Capability of Recurrent Higher Order Neural Networks"}]},"item_5_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2000-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicPageEnd":"710","bibliographicPageStart":"703","bibliographicVolumeNumber":"J83-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-パターン処理"},{"bibliographic_title":"電子情報通信学会論文誌. D-II, 情報・システム, II-パターン処理","bibliographic_titleLang":"en"}]}]},"item_5_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"有限個の連続値出力ニューロンからなるニューラルネットワークは，任意の決定性チューリング機械をシミュレートする能力をもつことが知られている．これまで，いくつかのシミュレートモデルが提案されているが，テープ部を実時間でシミュレートするには膨大な数のニューロンが必要となることが問題となる．本論文では，再帰型高次結合ニューラルネットワークが任意のチューリング機械をシミュレートできることを示し，シミュレート時間とこれに要するニューロン数の下限を明らかにする．まず，しきい値入出力関数と線形入出力関数を用いる有限個のニューロンからなる再帰型高次結合ニューラルネットワークが，任意の決定性チューリング機械を実時間でシミュレートでき，テープのシミュレートに要するニューロン数を6個まで削減できることを示す．また，のこぎり型関数を用いれば，シミュレートに要するニューロン数を4個に削減できることを示す．単純化されたこのシミュレートモデルは，将来ニューラルネットワークによる形式言語の学習を実現する上で有用な枠組みとなる．","subitem_description_type":"Abstract"}]},"item_5_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"43009","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Tanaka, Ken"}]},{"nameIdentifiers":[{"nameIdentifier":"43010","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Hasegawa, Daigo"}]}]},"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©2000 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":"AA11340957","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":"43007","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"長谷川, 大剛"}],"nameIdentifiers":[{"nameIdentifier":"43008","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":"J83-D-2(2)_703-710.pdf","filesize":[{"value":"1.8 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"J83-D-2(2)_703-710.pdf","url":"https://niigata-u.repo.nii.ac.jp/record/3447/files/J83-D-2(2)_703-710.pdf"},"version_id":"ca078aa4-b74f-4c8f-b7dc-add71896a9da"}]},"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":"チューリング機械","subitem_subject_scheme":"Other"},{"subitem_subject":"高次結合","subitem_subject_scheme":"Other"},{"subitem_subject":"形式言語","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の計算能力について","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の計算能力について"},{"subitem_title":"再帰型高次結合ニューラルネットワークの計算能力について","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":"3447","relation_version_is_last":true,"title":["再帰型高次結合ニューラルネットワークの計算能力について"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-15T03:36:36.748068+00:00"}