{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00029708","sets":["1164:2240:2301:2303"]},"path":["2303"],"owner":"1","recid":"29708","title":["並列誤差逆伝搬学習法の解析的な学習時間評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"1997-10-17"},"_buckets":{"deposit":"de75f6a3-d0c2-4e82-99cf-7b0fbf765dad"},"_deposit":{"id":"29708","pid":{"type":"depid","value":"29708","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"並列誤差逆伝搬学習法の解析的な学習時間評価","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"並列誤差逆伝搬学習法の解析的な学習時間評価"},{"subitem_title":"Theoretical Learning Speed Evaluation of Parallel Back Propagation Algorithms","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1997-10-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"北陸先端科学技術大学院大学情報科学研究科"},{"subitem_text_value":"北陸先端科学技術大学院大学情報科学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science, Japan Advanced Institute of Science and Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Japan Advanced Institute of Science and 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/29708/files/IPSJ-HPC97068010.pdf"},"date":[{"dateType":"Available","dateValue":"1999-10-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC97068010.pdf","filesize":[{"value":"570.7 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":"8cb3d8b3-96bb-4c40-8fa0-9b1dc42ed4de","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1997 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山森, 一人"},{"creatorName":"堀口, 進"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kunihito, Yamamori","creatorNameLang":"en"},{"creatorName":"Susumu, Horiguchi","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":"ニューラルネットワークを用いた情報処理は制御やパターン認識などの分野で広く応用されている．しかし，問題が大規模化するにしたがってニューラルネットワークの学習に必要な時間が膨大になる．近年，大規模ニューラルネットワークの学習を並列計算機を用いて高速化する研究が盛んに行われるようになった．しかしながら，これらの並列化手法は並列計算機のアーキテクチャに強く依存している場合が多く，誤差逆伝搬学習法の並列化性能については十分に検討されていない．本論文では，誤差逆伝搬法が持つ3種類の並列性を利用した並列学習モデルを解析し，その並列学習速度について詳しく検討する．これらの並列学習に関する解析結果を用いて実際の並列計算機上へ各モデルを実装し，並列学習法の性能評価を行う．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Multilayer neural network with back-propagation learning requires enormous computation times for large scale problems. To reduce computation times, several parallel learning algorithms have been proposed. However, most of parallel algorithms were specified for particular parallel computers. Performance analyses of parallel back-propagation algorithms have not been investigated sufficiently. This paper addresses the theoretical performances of parallel back-propagation algorithms. We classify parallel back-propagation algorithms into three models; unit parallel model, learning-set parallel model and pass parallel model. Then, their parallel performances are analyzed theoretically. To confirm theoretical performance estimations, these parallel models are implemented on parallel computer nCUBE/2. It is seen that the learning-set parallel model is most suitable for parallel computers by theoretical analyses and experimental results.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"62","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":"57","bibliographicIssueDates":{"bibliographicIssueDate":"1997-10-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"99(1997-HPC-068)","bibliographicVolumeNumber":"1997"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T22:59:29.174278+00:00","updated":"2025-01-22T17:25:15.224272+00:00","id":29708}