日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

  Quantization Functionals and Regularized Principal Manifolds

Smola, A., Mika, S., & Schölkopf, B.(1998). Quantization Functionals and Regularized Principal Manifolds (NC2-TR-1998-028). London, UK: University of London, Royal Holloway College, NeuroCOLT 2.

Item is

基本情報

表示: 非表示:
資料種別: 報告書

ファイル

表示: ファイル

関連URL

表示:
非表示:
説明:
-
OA-Status:

作成者

表示:
非表示:
 作成者:
Smola, AJ, 著者           
Mika, S, 著者
Schölkopf, B1, 著者           
所属:
1External Organizations, ou_persistent22              

内容説明

表示:
非表示:
キーワード: -
 要旨: Many settings of unsupervised learning can be viewed as quantization problems, namely of minimizing the expected quantization error subject to some restrictions. This has the advantage that tools known from the theory of (supervised) risk minimization like regularization can be readily applied to unsupervised settings. Moreover, one may show that this setting is very closely related to both, principal curves with a length constraint and the generative topographic map. Experimental results demonstrate the feasibility of the proposed method. In a companion paper we show that uniform convergence bounds can be given for algorithms such as a modified variant of the principal curves problem.

資料詳細

表示:
非表示:
言語:
 日付: 1998-09
 出版の状態: 出版
 ページ: 9
 出版情報: London, UK : University of London, Royal Holloway College, NeuroCOLT 2
 目次: -
 査読: -
 識別子(DOI, ISBNなど): BibTex参照ID: 1869
Reportnr.: NC2-TR-1998-028
 学位: -

関連イベント

表示:

訴訟

表示:

Project information

表示:

出版物

表示: