Integrating Machine Learning with Physics-Based Modeling — mentioned by jedbrown

Tue, 21 Jul 2020 19:43:44 GMT

These methods are really interesting for high-dimensional PDE (like HJB), but there's a ton of skepticism about the applicability of NN models for solving the more common PDE that arise in physical sciences and engineering. The tests are rarely equivalent, in that standard PDE technology can move to new domains, boundary conditions, materials, etc., without new training phases. If one needs to solve many nearby problems, there are many established techniques for leveraging that similarity. There is active research on ML to refine these techniques, but it isn't a silver bullet. Far more…

Paper and discussion history. A mention is not an endorsement.

Integrating Machine Learning with Physics-Based Modeling · HackerPapers discussions

Integrating Machine Learning with Physics-Based Modeling — mentioned by jedbrown