WEKO3
-
RootNode
アイテム
Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression
https://ipsj.ixsq.nii.ac.jp/records/91279
https://ipsj.ixsq.nii.ac.jp/records/91279f85fa040-dfbd-43f0-b0a5-3321fb2d8192
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-TOM0601016.pdf (278.3 kB)
|
Copyright (c) 2013 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | Trans(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2013-03-12 | |||||||
| タイトル | ||||||||
| タイトル | Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression | |||||||
| タイトル | ||||||||
| 言語 | en | |||||||
| タイトル | Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | [オリジナル論文] multivariate analysis, dimensionality reduction, generalized eigenvalue problem, pairwise expression, kernel method, clustering, semi-supervised learning, regularization | |||||||
| 資源タイプ | ||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||
| 資源タイプ | journal article | |||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属 | ||||||||
| Graduate School of Information Science and Engineering, Tokyo Institute of Technology | ||||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属 | ||||||||
| Graduate School of Information Science and Technologies, the University of Tokyo／NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| Graduate School of Information Science and Engineering, Tokyo Institute of Technology | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| Graduate School of Information Science and Technologies, the University of Tokyo / NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者名 |
Akisato, Kimura
Masashi, Sugiyama
Hitoshi, Sakano
Hirokazu, Kameoka
× Akisato, Kimura Masashi, Sugiyama Hitoshi, Sakano Hirokazu, Kameoka
|
|||||||
| 著者名(英) |
Akisato, Kimura
Masashi, Sugiyama
Hitoshi, Sakano
Hirokazu, Kameoka
× Akisato, Kimura Masashi, Sugiyama Hitoshi, Sakano Hirokazu, Kameoka
|
|||||||
| 論文抄録 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | It is well known that dimensionality reduction based on multivariate analysis methods and their kernelized extensions can be formulated as generalized eigenvalue problems of scatter matrices, Gram matrices or their augmented matrices. This paper provides a generic and theoretical framework of multivariate analysis introducing a new expression for scatter matrices and Gram matrices, called Generalized Pairwise Expression (GPE). This expression is quite compact but highly powerful. The framework includes not only (1) the traditional multivariate analysis methods but also (2) several regularization techniques, (3) localization techniques, (4) clustering methods based on generalized eigenvalue problems, and (5) their semi-supervised extensions. This paper also presents a methodology for designing a desired multivariate analysis method from the proposed framework. The methodology is quite simple: adopting the above mentioned special cases as templates, and generating a new method by combining these templates appropriately. Through this methodology, we can freely design various tailor-made methods for specific purposes or domains. | |||||||
| 論文抄録(英) | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | It is well known that dimensionality reduction based on multivariate analysis methods and their kernelized extensions can be formulated as generalized eigenvalue problems of scatter matrices, Gram matrices or their augmented matrices. This paper provides a generic and theoretical framework of multivariate analysis introducing a new expression for scatter matrices and Gram matrices, called Generalized Pairwise Expression (GPE). This expression is quite compact but highly powerful. The framework includes not only (1) the traditional multivariate analysis methods but also (2) several regularization techniques, (3) localization techniques, (4) clustering methods based on generalized eigenvalue problems, and (5) their semi-supervised extensions. This paper also presents a methodology for designing a desired multivariate analysis method from the proposed framework. The methodology is quite simple: adopting the above mentioned special cases as templates, and generating a new method by combining these templates appropriately. Through this methodology, we can freely design various tailor-made methods for specific purposes or domains. | |||||||
| 書誌レコードID | ||||||||
| 収録物識別子タイプ | NCID | |||||||
| 収録物識別子 | AA11464803 | |||||||
| 書誌情報 |
情報処理学会論文誌数理モデル化と応用（TOM） 巻 6, 号 1, p. 136-145, 発行日 2013-03-12 |
|||||||
| ISSN | ||||||||
| 収録物識別子タイプ | ISSN | |||||||
| 収録物識別子 | 1882-7780 | |||||||
| 出版者 | ||||||||
| 言語 | ja | |||||||
| 出版者 | 情報処理学会 | |||||||
