most citedInterpreting Classifiers through Attribute Interactions in Datasets

31 citations · 31 across the 1 of their papers we have counts for

collaborators

1 paper

stat.ML2017★ 31 cited

Interpreting Classifiers through Attribute Interactions in Datasets

Andreas Henelius, Kai Puolamäki, Antti Ukkonen

In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions. Attribute interactions in classification…