no code implementations • 25 Nov 2023 • Wanzhou Lei, Pavlos Protopapas, Joy Parikh
We introduce a generalizable approach that combines perturbation method and one-shot transfer learning to solve nonlinear ODEs with a single polynomial term, using Physics-Informed Neural Networks (PINNs).
no code implementations • 13 Feb 2022 • Levon Nurbekyan, Wanzhou Lei, Yunan Yang
We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems.