Explaining Classifiers Under Constraints

Explore the intricacies of explaining classifiers under constraints in this 25-minute lecture presented by Leila Amgoud and Emiliano Lorini from ANITI Toulouse. Delve into the challenges and methodologies associated with interpreting machine learning models, particularly focusing on classifiers operating within specific limitations or constraints. Gain insights into the importance of explainable AI and how it impacts the reliability and trustworthiness of classification systems. Discover techniques for enhancing the interpretability of complex models while maintaining their performance under various constraints.