{"created":"2025-01-19T00:51:29.580672+00:00","updated":"2025-01-20T03:26:26.388257+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00184013","sets":["1164:2822:9120:9274"]},"path":["9274"],"owner":"11","recid":"184013","title":["［招待講演］機械学習で切り開く新しいリソグラフイ・DFM技術"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-10-30"},"_buckets":{"deposit":"51e8c68b-8718-4aeb-b759-d363852aebbf"},"_deposit":{"id":"184013","pid":{"type":"depid","value":"184013","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"［招待講演］機械学習で切り開く新しいリソグラフイ・DFM技術","author_link":["405538","405539"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"［招待講演］機械学習で切り開く新しいリソグラフイ・DFM技術"},{"subitem_title":"[Invited Lecture] Innovative Applications of Machine Learning in Lithography and DFM","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"招待講演","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2017-10-30","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東芝メモリ株式会社"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Toshiba Memory Corp.","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/184013/files/IPSJ-EMB17046025.pdf","label":"IPSJ-EMB17046025.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-EMB17046025.pdf","filesize":[{"value":"250.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"42"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"437e0555-c89e-4898-9089-8b4c831b35c6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"松縄, 哲明"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tetsuaki, Matsunawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12149313","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-868X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"半導体デバイスの歩留り向上のために，いかに製造不良を抑えるか．半導体の製造現場は日々この課題と戦っている．製造不良を減らすためには，リソグラフイシミュレーションで予め不良になりそうな回路パターンを見つけ出し，製造プロセスのばらつきに頑強なパターンへと修正する DFM (Design for Manufacturability : 製造容易性設計） 技術が不可欠である．近年，リソグラフイ ･ DFM 分野に機械学習を応用することで，シミュレーション時間の短縮や精度向上などを実現した事例が次々と報告されている．例えば Hotspot とよばれる不良になりやすい回路パターンを高速に検出する技術は，パターン認識のアルゴリズムを活用できることから注目を集めており，最新の研究では深層学習の有効性も示されている．そこで本講演では，はじめに機械学習を用いた DFM 技術におけるいくつかの応用例を概観した後，最近の研究事例として，コンタクトパターンの製造性向上に必要な補助パターンを機械学習を用いて効率的に配置する手法について紹介する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Lithography and DFM (Design for Manufacturability) technologies are essential for improving manufacturing yield of semiconductor devices. Machine learning based techniques have recently been shown to be effective for calibrating predictive models, and they have successfully been applied in lithography and DFM field. One of the major applications is a fast lithography hotspot detection which is a technique to detect lower fidelity patterns on wafers in a short runtime. Machine learning based hotspot detection method has eagerly been studied in recent years because many techniques in pattern recognition area can effectively be utilized. This paper presents an overview of several applications in DFM, and introduces a new machine learning based method to generate sub-resolution assist features for improving manufacturing yield of contact patterns.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1","bibliographic_titles":[{"bibliographic_title":"研究報告組込みシステム（EMB）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2017-10-30","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"25","bibliographicVolumeNumber":"2017-EMB-46"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":184013,"links":{}}