Orateur invité

Prof. Patrick Gallinari

ISIR / Sorbonne Université et Criteo AI Lab

Titre de l'exposé : Physics-Aware Deep Learning: Incorporating Prior Knowledge in Machine Learning and Generalizing Across Environments

Résumé

Deep learning has recently gained traction in modeling complex physical processes across industrial and scientific fields. This rapidly evolving interdisciplinary field presents new challenges for machine learning. In this talk, I will focus on deep learning approaches for modeling dynamic physical systems and illustrate three main challenges: incorporating prior physical knowledge into learning models, generalizing learning models to multiple environments, and enabling models to operate continuously in space and time. This presentation will feature applications from various domains. 

Biographie

Patrick Gallinari is a professor at Sorbonne University and a distinguished researcher at Criteo AI Lab - Paris. His research centers around statistical learning and deep learning, with applications in various fields like semantic data processing and complex data analysis. A few years ago, he initiated a research topic on physics-aware machine learning and co-authored seminal work in this area. Gallinari leads the MLIA (Machine Learning and Information Access) research group, which specifically focuses on statistical learning and deep learning.