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

登録内容を編集ファイル形式で保存
 
 
ダウンロード電子メール
  Projection and Projectability

Corfield, D. (2009). Projection and Projectability. In J., Quiñonero-Candela, M., Sugiyama, A., Schwaighofer, & N., Lawrence (Eds.), Dataset Shift in Machine Learning (pp. 29-38). Cambridge, MA, USA: MIT Press.

Item is

基本情報

表示: 非表示:
アイテムのパーマリンク: https://hdl.handle.net/21.11116/0000-0003-09BC-0 版のパーマリンク: https://hdl.handle.net/21.11116/0000-0003-09BD-F
資料種別: 書籍の一部

ファイル

表示: ファイル

作成者

表示:
非表示:
 作成者:
Corfield, D1, 2, 著者           
所属:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

内容説明

表示:
非表示:
キーワード: -
 要旨: This chapter shows how the problem of dataset shift has been addressed by different philosophical schools under the concept of “projectability.” When philosophers tried to formulate scientific reasoning with the resources of predicate logic and a Bayesian inductive logic, it became evident how vital background knowledge is to allow us to project confidently into the future, or to a different place, from previous experience. To transfer expectations from one domain to another, it is important to locate robust causal mechanisms. An important debate concerning these attempts to characterize background knowledge is over whether it can all be captured by probabilistic statements. Having placed the problem within the wider philosophical perspective, the chapter turns to machine learning, and addresses a number of questions: Have machine learning theorists been sufficiently creative in their efforts to encode background knowledge? Have the frequentists been more imaginative than the Bayesians, or vice versa? Is the necessity of expressing background knowledge in a probabilistic framework too restrictive? Must relevant background knowledge be handcrafted for each application, or can it be learned?

資料詳細

表示:
非表示:
言語:
 日付: 2009
 出版の状態: 出版
 ページ: -
 出版情報: -
 目次: -
 査読: -
 識別子(DOI, ISBNなど): DOI: 10.7551/mitpress/9780262170055.001.0001
 学位: -

関連イベント

表示:

訴訟

表示:

Project information

表示:

出版物 1

表示:
非表示:
出版物名: Dataset Shift in Machine Learning
種別: 書籍
 著者・編者:
Quiñonero-Candela, J, 編集者
Sugiyama, M, 編集者
Schwaighofer, A, 編集者
Lawrence, ND, 編集者
所属:
-
出版社, 出版地: Cambridge, MA, USA : MIT Press
ページ: - 巻号: - 通巻号: 2 開始・終了ページ: 29 - 38 識別子(ISBN, ISSN, DOIなど): ISBN: 978-0-262-17005-5