Interpretable machine learning: definitions, methods, and applications

Code

• github.com/csinva/hierarchical-dnn-interpretations
  pytorch★ 128
• github.com/laura-rieger/deep-explanation-penalization
  pytorch★ 128
• github.com/csinva/local-vae
  pytorch★ 3
• github.com/csinva/disentangled-attribution-curves
  none★ 0

Abstract

Official code for using / reproducing ACD (ICLR 2019) from the paper "Hierarchical interpretations for neural network predictions" https://arxiv.org/abs/1806.05337

Tasks

Reproductions