“The Mythos of Model Interpretability” (2018), by Zachary C. Lipton. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.
The Mythos of Model Interpretability
Zachary C. Lipton · June 1, 2018 · Computer Science
Abstract
In machine learning, the concept of interpretability is both important and slippery.
Free PDF DOI: 10.1145/3233231
Read papers like this every day in Nerdi
Three real papers a day, always with the original abstract. Free on iPhone.