{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00218580","sets":["1164:2735:10865:10962"]},"path":["10962"],"owner":"44499","recid":"218580","title":["混合Normal Inverse Gaussianモデルに対する変分ベイズとギブスサンプリングの比較"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-06-20"},"_buckets":{"deposit":"f03007bd-ef32-458a-9d18-3f97e68c622f"},"_deposit":{"id":"218580","pid":{"type":"depid","value":"218580","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"混合Normal Inverse Gaussianモデルに対する変分ベイズとギブスサンプリングの比較","author_link":["568809","568808"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"混合Normal Inverse Gaussianモデルに対する変分ベイズとギブスサンプリングの比較"}]},"item_type_id":"4","publish_date":"2022-06-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"工学院大学情報学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Informatics, Kogakuin University of Technology and Engineering","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/218580/files/IPSJ-MPS22138010.pdf","label":"IPSJ-MPS22138010.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS22138010.pdf","filesize":[{"value":"1.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"e2ad9f5d-cf84-4ce6-8143-1c4d48412c1a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 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":"竹川, 高志"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takashi, Takekawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"データのクラスタリングに，多変量正規分布による混合分布モデル (GMM) が広く用いられている．しかし，一般にデータは非対称性や非正規性を持つため，GMM によるクラスタリング性能は必ずしも十分ではない．GMM の欠点を補うため，非対称性と非正規性を考慮した Normal Inverse Gaussian (NIG) 分布の混合モデル (NIGMM) の定式化を行い，変分ベイズ (VB) とギブスサンプリング (GS) の実装を行った．同じモデルに対して VB と GS が異なる結果を示すため，クラスタリング性能，モデルエビデンス，WAIC，計算時間について評価を行った．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Mixture models for multivariate normal distributions (GMM) are widely used for data clustering. To compensate for the shortcomings of GMMs, we formulated a mixture model for normal Inverse Gaussian distribution (NIGMM) that takes asymmetry and non-normality into account. To evaluate the performance of NIGMM, we implemented fast variational Bayesian (VB) and Gibbs sampling (GS) solution using GPU parallelization. We evaluate these implementations for clustering performance, model evidence, WAIC, and computation time.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"4","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-06-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2022-MPS-138"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":218580,"updated":"2025-01-19T15:07:12.936045+00:00","links":{},"created":"2025-01-19T01:18:56.165374+00:00"}