no code implementations • 23 Jun 2022 • Ryma Boumazouza, Fahima Cheikh-Alili, Bertrand Mazure, Karim Tabia
The ever increasing complexity of machine learning techniques used more and more in practice, gives rise to the need to explain the predictions and decisions of these models, often used as black-boxes.
no code implementations • 23 Jun 2022 • Ryma Boumazouza, Fahima Cheikh-Alili, Bertrand Mazure, Karim Tabia
In this paper titled A Model-Agnostic SAT-based approach for Symbolic Explanation Enumeration we propose a generic agnostic approach allowing to generate different and complementary types of symbolic explanations.
no code implementations • 20 Jun 2022 • Ryma Boumazouza, Fahima Cheikh-Alili, Bertrand Mazure, Karim Tabia
In this paper titled A Symbolic Approach for Counterfactual Explanations we propose a novel symbolic approach to provide counterfactual explanations for a classifier predictions.
no code implementations • 12 Jul 2013 • Éric Grégoire, Jean-Marie Lagniez, Bertrand Mazure
ExtractingMUCs(MinimalUnsatisfiableCores)fromanunsatisfiable constraint network is a useful process when causes of unsatisfiability must be understood so that the network can be re-engineered and relaxed to become sat- isfiable.