Physics Informed Neural Networks (PINNs) have recently been found to be effective PDE solvers. This talk will focus on how traditional PINN architectures along with physics-inspired regularizers fail to retrieve the intended solution when training data is noisy and how this problem can be solved using Gaussian Process based smoothing techniques.
Instructor: Avik Roy, NCSA Postdoctoral Research Associate
Session Date: February 22, 2023