AIAI Seminar - 04/10/21 - Joao Marques-Silva

Title: 

Formal Reasoning Methods in Explainable AI

Abstract:

The expected applications of machine learning (ML) in safety critical applications hinge on systems that are robust in their operation and that can be trusted. This talk overviews recent efforts on applying automated reasoning tools in explaining non-interpretable (black-box) ML models. Concretely, the talk details the computation of rigorous explanations of black-box models, and how these serve for assessing the quality of widely used heuristic explanation approaches. The talk also overviews duality properties between different kinds of rigorous explanations. Finally, the talk briefly overviews ongoing work on mapping tractable explainability.