Skip to content
conftrace_

explanation penalization

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

contextual decomposition (1) neural network (1) explainable deep learning (1) prior knowledge (1) model alignment (1) model interpretability (1) deep learning (1) feature importance (1)

Papers

Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge ICML 2020