{"updated":"2025-01-22T07:19:14.674776+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00051147","sets":["1164:4402:4494:4498"]},"path":["4498"],"owner":"1","recid":"51147","title":["記憶に基づく学習への帰納学習の埋め込みについて"],"pubdate":{"attribute_name":"公開日","attribute_value":"1991-05-22"},"_buckets":{"deposit":"d3d416ac-9d19-472e-81c8-4b24a3a98c52"},"_deposit":{"id":"51147","pid":{"type":"depid","value":"51147","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"記憶に基づく学習への帰納学習の埋め込みについて","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"記憶に基づく学習への帰納学習の埋め込みについて"},{"subitem_title":"On Embedding an Inductive Learning Schema into a Memory - Based Learning System","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1991-05-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"長岡技術科学大学工学部 計画・経営系"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Planning and Management Science, Nagaoka University of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/51147/files/IPSJ-ICS91076007.pdf"},"date":[{"dateType":"Available","dateValue":"1993-05-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ICS91076007.pdf","filesize":[{"value":"1.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"25"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"dca50755-8479-4e02-81db-726b8534c4c1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1991 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"畝見, 達夫"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tatsuo, Unemi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11135936","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"粒度の小さな離散時系列データを対象とする「記憶に基づく学習」のメカニズムに帰納学習の手法を埋め込むための1つの枠組を提案する．対象となる問題は実数ベクトルを入力としシンボルを出力とする補強入力の遅れを伴う補強学習問題である．具体的には，我々が先に提案した「記憶に基づく時系列学習法」に埋め込むための，記憶されたデータに対する要素レベルの一般化と，時系列の分節化を提案する．これらの機構の組合せは低レベル記憶からのルール生成につながるものである．環境適応問題を用いた計算機シミュレーションにより帰納学習導入に伴う性能に変化が観察された．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes a framework to embed an inductive learning mechanism into a memory-based learning system for discrete time-sequence of small grain size. The learning task follows a reinforcement learning scenario, where the input is a vector of real numbers, the output is a symbol and the reinforcement is delayed. Concretely, we presents two methods, which are to generalize the memorized data elements, and to cluster the memorized sequences. Combination of these methods will lead to symbolic rule generation. The result of computer simulation shows the difference of performance caused by introducing inductive learning schema.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"10","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告知能と複雑系（ICS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"1991-05-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"42(1991-ICS-076)","bibliographicVolumeNumber":"1991"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:15:45.496829+00:00","id":51147,"links":{}}