List of teaching.
Tutorials have their dedicated section as well
here.
AI software – both symbolic and connectionist – pervasiveness in our societies is a fact. Its very dissemination raises important questions from the perspective of software engineering. As AI software malfunctions have dire consequences on individuals and societies, it is expected that AI software will aim for high software quality. The field of formal methods successfully transferred techniques and tools into some of the most critical industries. The goal of this course is to provide an accurate perspective of formal methods applied to AI software. Following real-world industrial examples, we will present how the use of formal methods can help AI developers assess the quality of their software, ranging from adversarial robustness to automated neural network fixing and explainable AI with guarantees.
J’ai donné ce cours au master SETI en février 2024. Il porte sur deux grandes familles d’approches de techniques d’interprétabilité des IA:
les approches post-hoc qui consistent à attribuer à un programme déjà existant les parties salientes d’une entrée les approches par construction qui étudient des architectures de programmes plus aisément interprétables Sur le modèle de mes précédents cours au sein du SETI, il comporte une partie pratique.
This is the material for a course I gave at the Université Paris-Saclay AI master course for Fairness in Artificial Intelligence. Altough the course was online, interactions between students, professors and me were really interesting and sparked new questions, especially on the question of dataset quality assessment.