Description
Date depot: 10 février 2023
Titre: Domain generalization for Physics Based Deep Learning
Directeur de thèse:
Patrick GALLINARI (ISIR (EDITE))
Encadrant :
Jean-Noel VITTAUT (LIP6)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Intelligence artificielle
Resumé: The thesis will explore developments in physics based deep learning aimed at learning complex dynamics characterizing physical processes in earth science. The main investigation concerns the ability of these models to generalize to different contexts including different initial and border conditions and different parameterizations of the dynamics.
Résumé dans une autre langue: The thesis will explore developments in physics based deep learning aimed at learning complex dynamics characterizing physical processes in earth science. The main investigation concerns the ability of these models to generalize to different contexts including different initial and border conditions and different parameterizations of the dynamics.
Doctorant.e: Kassai Armand