articleProceedings of the National Academy of SciencesOct 16, 2019BRONZE OA

Definitions, methods, and applications in interpretable machine learning

University of California, Berkeley · Allen Institute for Brain Science · +2 more institutions

PubMed
Indexed inarxivcrossrefpubmed

Abstract

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the predictive, descriptive, relevant (PDR) framework for…

No related works found for this paper.

Funding