2 papers
cs.LG2026
Fairness of Classifiers in the Presence of Constraints between Features
Martin C. Cooper, Imane Bousdira
In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when…
cs.AI2024
Backward explanations via redefinition of predicates
Léo Saulières, Martin C. Cooper, Florence Dupin de Saint Cyr
History eXplanation based on Predicates (HXP), studies the behavior of a Reinforcement Learning (RL) agent in a sequence of agent's interactions with the environment (a history), t…