{"id":29349,"updated":"2025-01-19T23:34:44.742209+00:00","links":{},"created":"2025-01-18T22:59:13.383137+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00029349","sets":["1164:2240:2278:2280"]},"path":["2280"],"owner":"11","recid":"29349","title":["対称操作導入BP学習方程式の内挿外挿精度の改善手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2001-07-25"},"_buckets":{"deposit":"1ab92622-dcdf-4cce-86c8-d4f8c402ff82"},"_deposit":{"id":"29349","pid":{"type":"depid","value":"29349","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"対称操作導入BP学習方程式の内挿外挿精度の改善手法","author_link":["459007","459004","459006","459005","459009","459008"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"対称操作導入BP学習方程式の内挿外挿精度の改善手法"},{"subitem_title":"An improvement technique for inter/extrapolate - precision, on use of symmetric operations in the BP learning","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2001-07-25","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"宮崎大学工学部電気電子工学科"},{"subitem_text_value":"宮崎大学工学部電気電子工学科"},{"subitem_text_value":"宮崎大学工学部電気電子工学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The faculty of engineering, Miyazaki University","subitem_text_language":"en"},{"subitem_text_value":"The faculty of engineering, Miyazaki University","subitem_text_language":"en"},{"subitem_text_value":"The faculty of engineering, Miyazaki University","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/29349/files/IPSJ-HPC01087009.pdf","label":"IPSJ-HPC01087009"},"date":[{"dateType":"Available","dateValue":"2003-07-25"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC01087009.pdf","filesize":[{"value":"45.4 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"14"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"174bfdcd-d2ff-405e-b4ce-d204a7578231","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2001 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"王, 謙軼"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渡邉, 隆由貴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"青山, 智夫"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Qianyi, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takayuki, Watanabe","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoo, Aoyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10463942","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":"学習データに対称性が存在するとき、BP学習方程式の結果にその対称性が反映される必要がある。しかし現実のBP方程式の結果は一定区間の連続入力データに対し、前記必要性を満さない。これをBP方程式の「非対称性」という。データ処理によって被処理データ中に見いだされた本質が、そのデータから生成された近似関数であっても変化するのは望ましくない。この欠点を除去した対称BP学習方程式の導出は可能である。しかし過大な計算時間と解への収束性に問題が残る。その現実的解決策としてBP方程式の収束解に対し対称操作を施す。この解は対称BP学習方程式の解の一候補である。その解の内挿外挿精度を検討した。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose a criterion in the neural-computing that is; when symmetrical property is found in the leaning data, the results, they may be a neural network, from the computing should also satisfy the property for all input data except the learning data. However, BP-learning equation does not satisfy the property. We call the fault as \"unsymmetrical character of BP-learning.\" It is inappropriate that the property in a subject is deformed by data processing. We eliminate the fault and can derive an equation; however, attainability towards one solution would not be assured because of many conditions that prevent the convergence-path in numerical calculation, and they bring excess CPU time. To avoid the trouble, we wish to adopt a correction method for the results from the BP-learning equation. The corrected result is a kind solution of the symmetrical BP-learning equation. We discussed the precision for inter/extrapolations of the corrected one.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"54","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告ハイパフォーマンスコンピューティング（HPC）"}],"bibliographicPageStart":"49","bibliographicIssueDates":{"bibliographicIssueDate":"2001-07-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"77(2001-HPC-087)","bibliographicVolumeNumber":"2001"}]},"relation_version_is_last":true,"weko_creator_id":"11"}}