- 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
Web of Science ® の 関連論文(Related Records®)ビュー
- Web of Science
- ISSN : 1532-4435
- DBLP ID : journals/jmlr/BaehrensSHKHM10
- Web of Science ID : WOS:000282522400002