Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

How to explain individual classification decisions

 
: Baehrens, D.; Schroeter, T.; Harmeling, S.; Kawanabe, M.; Hansen, K.; Müller, K.-R.

Journal of Machine Learning Research 11 (2010), pp.1803-1831
ISSN: 1533-7928
ISSN: 1532-4435
English
Journal Article
Fraunhofer FIRST ()

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.

: http://publica.fraunhofer.de/documents/N-143882.html