The Mythos of Model Interpretability

Zachary C. Lipton

2018Published

2.7KCitations

0References

journal articleType

Abstract

Supervised machine-learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world?

Journal: Queue

Publisher: Association for Computing Machinery (ACM)

View on DOI

Citations are the number of DOI-registered works in Crossref that cite this paper; references are how many works it cites. Full text is on the publisher site via the DOI link.