English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  How to Explain Individual Classification Decisions

Baehrens, D., Schroeter, T., Harmeling, S., Kawanabe, M., Hansen, K., & Müller, K.-R. (2010). How to Explain Individual Classification Decisions. Journal of Machine Learning Research, 11, 1803-1831.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-BF74-6 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-759A-D
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Baehrens, D, Author
Schroeter, T, Author
Harmeling, S1, 2, Author              
Kawanabe, M, Author
Hansen, K, Author
Müller, K-R, Author              
Affiliations:
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              

Content

show
hide
Free keywords: -
 Abstract: 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.

Details

show
hide
Language(s):
 Dates: 2010-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 6670
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Journal of Machine Learning Research
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Brookline, MA : Microtome Publishing
Pages: - Volume / Issue: 11 Sequence Number: - Start / End Page: 1803 - 1831 Identifier: ISSN: 1532-4435
CoNE: https://pure.mpg.de/cone/journals/resource/111002212682020