Séminaire Probabilités et Statistiques
Some statistical insights into physics-informed neural networks
Oct. 2023
Intervenant : Claire Boyer
Institution : Univ. Paris-Sorbonne
Heure : 15h45 - 16h45
Lieu : 3L15

Physics-informed neural networks (PINNs) combine the expressiveness of neural networks with the interpretability of physical modeling. Their good practical performance has been demonstrated both in the context of solving partial differential equations and in the context of hybrid modeling, which consists of combining an imperfect physical model with noisy observations. However, most of their theoretical properties remain to be established. We offer some statistical guidelines into the proper use of PINNs.

All (past and future) events