{"created":"2021-03-01T06:06:45.618593+00:00","id":3017,"links":{},"metadata":{"_buckets":{"deposit":"8c2c4ed9-9fe7-4b6e-a910-7cc33b0870f4"},"_deposit":{"id":"3017","owners":[],"pid":{"revision_id":0,"type":"depid","value":"3017"},"status":"published"},"_oai":{"id":"oai:niigata-u.repo.nii.ac.jp:00003017","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":"Recognizing Context Free Languages via Recurrent Higher-Order Neural Network"}]},"item_5_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1997-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicPageEnd":"979","bibliographicPageStart":"971","bibliographicVolumeNumber":"38","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"},{"bibliographic_title":"情報処理学会論文誌","bibliographic_titleLang":"en"}]}]},"item_5_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"文脈自由言語の認識や所属判定は, 機械翻訳の実現やプログラミング言語の実装など記号処理において不可欠な技術である. 文脈自由言語を認識する受理系には半無限長のスタックメモリが必要となるが, 有限状態の素子でこれを構成するには無限個の素子が必要となる. また文脈自由言語の所属判定では, 語長 n の文の判定に O(n^3) の時間計算量を必要とし, 逐次的な計算機では解析時間が急激に増加することも問題となる. 本論文では, 再帰型高次結合ニューラルネットワークを用い, これらの問題が解決できることを示す. まず, 閾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, 任意の決定性文脈自由言語を認識できることを示す. また, 閾値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を語長に応じて必要なだけ組み合わせることで, 任意の非決定性文脈自由言語に対する所属判定を O(n^2) の時間計算量で実行できることを示す. これらの結果より, 提案したこューラルネツトワークモデルが形式言語の認識や所属判定における多くの問題を解決できる特性を持つことを明らかにする.","subitem_description_type":"Abstract"},{"subitem_description":"The recognition of context free languages and the determination of its belonging are the essential problem in the symbol processing. In the recognition of any context free languages, the acceptor must realize infinite stack memory. It is impossible to construct infinite stack memory with the elements of finite states. Moreover, the determination of its belongings requires O (n^3) time complexity. In this paper, we show that RHON (Recurrent Higher-Order Neural Network) can avoid these problems. First of all, we show that RHON composed of finite neurons with linear output function can recognize any deterministic context free languages. Secondly, we show that any non-deterministic context free languages can be determined its belonging using the combination of RHON with threshold output function. Our results show the efficiency of our model for symbol processing.","subitem_description_type":"Abstract"}]},"item_5_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"40426","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Tanaka, Ken"}]},{"nameIdentifiers":[{"nameIdentifier":"40427","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Kumazawa, Itsuo"}]}]},"item_5_publisher_7":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会"}]},"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://ci.nii.ac.jp/naid/110002721549","subitem_relation_type_select":"URI"}}]},"item_5_rights_15":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"一般社団法人情報処理学会"},{"subitem_rights":"本文データは学協会の許諾に基づきCiNiiから複製したものである"}]},"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":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_5_source_id_9":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03875806","subitem_source_identifier_type":"ISSN"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田中, 賢"}],"nameIdentifiers":[{"nameIdentifier":"40424","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"熊沢, 逸夫"}],"nameIdentifiers":[{"nameIdentifier":"40425","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":"110002721549.pdf","filesize":[{"value":"884.8 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"110002721549.pdf","url":"https://niigata-u.repo.nii.ac.jp/record/3017/files/110002721549.pdf"},"version_id":"de0ff93f-8400-4060-bae3-c9713eb54808"}]},"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文脈自由言語の認識","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文脈自由言語の認識"},{"subitem_title":"再帰型高次結合ニューラルネットワークによる文脈自由言語の認識","subitem_title_language":"en"}]},"item_type_id":"5","owner":"1","path":["454","425"],"pubdate":{"attribute_name":"公開日","attribute_value":"2012-08-31"},"publish_date":"2012-08-31","publish_status":"0","recid":"3017","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文脈自由言語の認識"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-15T03:36:12.974549+00:00"}