The Mythos of Model Interpretability
Communications of the ACM2018Vol. 16(10), pp. 31–43
Citations Over TimeTop 1% of 2018 papers
Abstract
In machine learning, the concept of interpretability is both important and slippery.
Related Papers
- → On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)(2024)13,136 cited
- → Methods for interpreting and understanding deep neural networks(2017)2,639 cited
- → Deep Inside Convolutional Networks: Visualising Image Classification\n Models and Saliency Maps(2013)4,905 cited
- → Towards A Rigorous Science of Interpretable Machine Learning(2017)3,111 cited