Programs as Black-Box Explanations

arXiv: Machine Learning, Volume abs/1611.07579, 2016.

Cited by: 35|Bibtex|Views109
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or model flexibility. However, it is not clear what kind of explanations, such as linear models, decision trees, and rule lists, are the appropriate family to consi...More

Code:

Data:

Your rating :
0

 

Tags
Comments