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 • 18 Feb 2016 • Jean Francois Baget, Salem Benferhat, Zied Bouraoui, Madalina Croitoru, Marie-Laure Mugnier, Odile Papini, Swan Rocher, Karim Tabia
We propose a general framework for inconsistency-tolerant query answering within existential rule setting.