Definitions, methods, and applications in interpretable machine learning.

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 discussing interpretations. The PDR framework provides 3 overarching desiderata for evalua

SUBMITTER: Murdoch WJ 

PROVIDER: S-EPMC6825274 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature