[PDF][PDF] The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.
ZC Lipton - Queue, 2018 - dl.acm.org
Queue, 2018•dl.acm.org
The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both
important and slippery. Page 1 acmqueue | may-june 2018 1 machine learning 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? Models should
be not only good, but also interpretable, yet the task of interpretation appears underspecified.
The academic literature has provided diverse and sometimes non-overlapping motivations …
important and slippery. Page 1 acmqueue | may-june 2018 1 machine learning 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? Models should
be not only good, but also interpretable, yet the task of interpretation appears underspecified.
The academic literature has provided diverse and sometimes non-overlapping motivations …
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?
ACM Digital Library