IA : Auto-encodeurs
23 octobre 2025 @ 13 h 15 min – 15 h 45 min –
Campus Triolet, Bat 36, SC36.05
Gino Frazzoli – Institut de Science des Données de Montpellier
Approfondissez vos connaissances en Deep Learning à travers le prisme des auto-encodeurs, une technique encore aujourd’hui mise en œuvre dans l’industrie pour la compression de données et la détection d’anomalies.
IA, DeepLearning, Formation
Learning from unlearning : how can we design ML systems that aremore trustworthy ?
23 octobre 2025 @ 14 h 00 min – 15 h 00 min –
Amphi Moreau, B2. Campus St Priest
Machine Learning in Montpellier, Theory & Practice – Nicolas Papernot (Univ. Toronto)
Pour cette session exceptionnelle du séminaire ML-MTP, nous aurons l’honneur d’accueillir Nicolas Papernot, chercheur de renommée mondiale en IA de confiance et expert des questions de sécurité et de vie privée. Il a été l’un des pionniers de plusieurs axes de recherche majeurs, notamment les attaques adversariales sur les réseaux de neurones et le machine unlearning. Il est titulaire d’une Inria International Chair (2025–2027) associée à l’équipe PreMeDICaL.
IA & Experts
Learning from unlearning : how can we design ML systems that are more trustworthy ?
23 octobre 2025 @ 14 h 00 min –
Amphi Moreau, Building 2, St Priest campus
Machine Learning in Montpellier, Theory & Practice – Nicolas Papernot (Univ. Toronto)
The talk first illustrates the challenges of having end users trust that machine learning algorithms were deployed responsibly, i.e., in a trustworthy way, through a deep dive on the problem of unlearning. The need for machine unlearning, i.e., obtaining a model one would get without training on a subset of data, arises from privacy legislation and more recently as a potential solution to data poisoning or copyright claims. As we present different approaches to unlearning, it becomes clear that they fail to answer our motivating question: how can end users verify that unlearning was successful? Taking a step back, we draw lessons for the broader area of trustworthy machine learning and present ongoing research that lay the foundations for companies, regulators, and countries to be able to verify meaningful properties at the scale that is required for stable governance of AI algorithms, both nationally and internationally.
Machine Learning in Montpellier, Theory & Practice