← Search

Evi Sijben

1 accepted papers

2020

Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

NeurIPS 2020poster

Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid gam…

Cited by 231SourcePDFScholar