Teaching

List of teaching. Tutorials have their dedicated section as well here.

Formal verification of symbolic and connectionist AI: a way toward higher quality software

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.

Post-Hoc and By-design explanation methods

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.

Interprétabilité des réseaux de neurones

J’ai donné ce cours sur l’interprétabilité des réseaux de neurones aux élèves du master SETI en février 2023. Il se concentre sur le domaine de la vision par ordinateur, et prend le temps de donner un contexte social et juridique aux étudiants.

Frailties of AI - Paris Saclay AI Master

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.

Theory and Practice of Formal Verification of Machine Learning

Since 2020, I regularly teach formal verification of machine learning programs to students of the SETI master.