Poster
Editing a classifier by rewriting its prediction rules
Shibani Santurkar · Dimitris Tsipras · Mahalaxmi Elango · David Bau · Antonio Torralba · Aleksander Madry
Keywords: [ Robustness ]
Abstract:
We propose a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our method requires virtually no additional data collection and can be applied to a variety of settings, including adapting a model to new environments, and modifying it to ignore spurious features.
Chat is not available.