Definitions, methods, and applications in interpretable machine learning

Explore this paper's citation graph

Summary

This work defines interpretability in the context of machine learning and introduces the predictive, descriptive, relevant (PDR) framework for discussing interpretations, and introduces 3 overarching desiderata for evaluation: predictive accuracy, descriptive accuracy, and relevancy.

Type
article
Published
2019-01-14
Cited by
1,856
References
112
Access
Open access

Keywords

Interpretability, Computer science, Artificial intelligence, Categorization, Machine learning

References

Cited by

Related papers