論文

査読有り
2010年6月

How to Explain Individual Classification Decisions

JOURNAL OF MACHINE LEARNING RESEARCH
  • David Baehrens
  • ,
  • Timon Schroeter
  • ,
  • Stefan Harmeling
  • ,
  • Motoaki Kawanabe
  • ,
  • Katja Hansen
  • ,
  • Klaus-Robert Mueller

11
開始ページ
1803
終了ページ
1831
記述言語
英語
掲載種別
研究論文(学術雑誌)
出版者・発行元
MICROTOME PUBL

After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the question what is the most likely label of a given unseen data point. However, most methods will provide no answer why the model predicted a particular label for a single instance and what features were most influential for that particular instance. The only method that is currently able to provide such explanations are decision trees. This paper proposes a procedure which (based on a set of assumptions) allows to explain the decisions of any classification method.

Web of Science ® 被引用回数 : 222

リンク情報
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000282522400002&DestApp=WOS_CPL
URL
http://portal.acm.org/citation.cfm?id=1859912
URL
http://dblp.uni-trier.de/db/journals/jmlr/jmlr11.html#journals/jmlr/BaehrensSHKHM10
ID情報
  • ISSN : 1532-4435
  • DBLP ID : journals/jmlr/BaehrensSHKHM10
  • Web of Science ID : WOS:000282522400002

エクスポート
BibTeX RIS