On generalization error estimates of physics informed neural networks for approximating dispersive PDEs
Physics informed neural networks (PINNs) have recently been widely used for robust and accurate approximation of PDEs. We provide rigorous upper bounds on the generalization error of PINNs approximating solutions of the forward problem for several dispersive PDEs.
Journal / seriesSAM Research Report
PublisherSeminar for Applied Mathematics, ETH Zurich
SubjectDeep learning; Physics informed neural networks (PINNs); Dispersive PDEs
Organisational unit03851 - Mishra, Siddhartha / Mishra, Siddhartha
MoreShow all metadata