{"created":"2023-05-15T11:56:01.212956+00:00","id":1137,"links":{},"metadata":{"_buckets":{"deposit":"e931a774-3ea0-4aa7-94f2-eb20974e0a78"},"_deposit":{"created_by":3,"id":"1137","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"1137"},"status":"published"},"_oai":{"id":"oai:kyutech.repo.nii.ac.jp:00001137","sets":["8:24"]},"author_link":["5347","5348","5349","5350"],"control_number":"1137","item_21_alternative_title_18":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Comparison of Fundamental Elements for Parallel Distributed Processing Networks","subitem_alternative_title_language":"en"}]},"item_21_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1999-09-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicPageEnd":"112","bibliographicPageStart":"99","bibliographicVolumeNumber":"1","bibliographic_titles":[{"bibliographic_title":"バイオメディカル・ファジィ・システム学会誌"}]}]},"item_21_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"並列分散処理ネットワークの学習能力および汎化能力に影響を与える要因の1つは, 素子の入出力特性である.そこで本論文では, 従来の学習しきい素子を一般化することにより, 既に得られている基本学習距離素子と乗算型学習距離素子のほかに, 乗算型学習しきい素子と加算型学習距離素子とを新たに提案した.また, これらの素子で構成された階層型ネットワークに最急降下法を適用し, それぞれのネットワークの学習則を導いた.更に, 各素子について, 2入力1出力の3層ネットワークで2変数論理関数の学習の計算機シミュレーションを行い, 学習能力および汎化能力の比較検討を行った.その結果, 学習能力の面では, 乗算型学習距離素子を用いた場合が, 強化係数およびパラメータの初期値に対する学習の安定性, 学習精度, 学習速度のいずれにおいても, 最も優れていることが示された.汎化能力の面では, 基本学習距離素子が最も優れていることが示された. / In this paper, multiplication-type learning threshold element and addition-type learning distance element are newly proposed in addition to fundamental and multiplication-type learning distance elements presented already. Furthermore, computer simulation was performed for three layered network with two inputs and one output. Simulation results show that the most excellent is multiplication-type learning distance element in learning stability, lerning accuracy and learning rate, and is fundamental learning distance element in generalization abolity.","subitem_description_type":"Abstract"}]},"item_21_description_60":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"subitem_description":"Journal Article","subitem_description_type":"Other"}]},"item_21_publisher_7":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"バイオメディカル・ファジィ・システム学会"}]},"item_21_relation_66":{"attribute_name":"論文ID（NAID）","attribute_value_mlt":[{"subitem_relation_type":"isIdenticalTo","subitem_relation_type_id":{"subitem_relation_type_id_text":"110003930518","subitem_relation_type_select":"NAID"}}]},"item_21_rights_13":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"バイオメディカル・ファジィ・システム学会. 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_21_select_59":{"attribute_name":"査読の有無","attribute_value_mlt":[{"subitem_select_item":"yes"}]},"item_21_source_id_8":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1345-1537","subitem_source_identifier_type":"PISSN"}]},"item_21_text_36":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州工業大学工学部"},{"subitem_text_value":"川崎重工業株式会社"},{"subitem_text_value":"Department of Electrical Engineering, Faculty of Engineering, Kyushu Institute of Technology"},{"subitem_text_value":"Engineering Division, Rolling Stock Group, Kawasaki Heavy Industries, Ltd."}]},"item_21_text_64":{"attribute_name":"業績ID","attribute_value_mlt":[{"subitem_text_value":"1939C13C71EBF7294925756700275479"}]},"item_21_version_type_58":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"横井, 博一","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"5347","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"染井, 陽介","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"5348","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":"2009-02-24"}],"displaytype":"detail","filename":"yokoi_05.pdf","filesize":[{"value":"1.3 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"yokoi_05.pdf","url":"https://kyutech.repo.nii.ac.jp/record/1137/files/yokoi_05.pdf"},"version_id":"82733e11-55bf-479e-8844-fe08b0ef4a4c"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"並列分散処理","subitem_subject_scheme":"Other"},{"subitem_subject":"ニューラルネットワーク","subitem_subject_scheme":"Other"},{"subitem_subject":"学習","subitem_subject_scheme":"Other"},{"subitem_subject":"学習しきい素子","subitem_subject_scheme":"Other"},{"subitem_subject":"学習距離素子","subitem_subject_scheme":"Other"},{"subitem_subject":"parallel distributed neural network","subitem_subject_scheme":"Other"},{"subitem_subject":"processing","subitem_subject_scheme":"Other"},{"subitem_subject":"learning","subitem_subject_scheme":"Other"},{"subitem_subject":"learning theshold element","subitem_subject_scheme":"Other"},{"subitem_subject":"learning distance","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":"並列分散処理ネットワーク用基本素子の比較","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"並列分散処理ネットワーク用基本素子の比較","subitem_title_language":"ja"}]},"item_type_id":"21","owner":"3","path":["24"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2009-02-24"},"publish_date":"2009-02-24","publish_status":"0","recid":"1137","relation_version_is_last":true,"title":["並列分散処理ネットワーク用基本素子の比較"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2025-07-14T02:14:19.684867+00:00"}