Provably Robust Model-Centric Explanations for Critical Decision-Making

no code implementations • 26 Oct 2021 • Cecilia G. Morales, Nicholas Gisolfi, Robert Edman, James K. Miller, Artur Dubrawski

We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be gleaned from LIME and SHAP, popular data-centric explanation tools in Artificial Intelligence (AI).

Decision Making