User login

Navigation

You are here

Exact imposition of boundary conditions in physics-informed neural networks

N. Sukumar's picture

We recently proposed a method that uses distance fields to exactly impose boundary conditions in physics-informed neural networks (PINN).  This contribution is available as an arXiv preprint.

Comments

Nice work, but I think an important and very similar work is left out: https://arxiv.org/abs/2006.08472 

Seems the link is not correctly reflected: 

Rao C, Sun H, Liu Y. Physics informed deep learning for computational elastodynamics without labeled data. arXiv preprint arXiv:2006.08472. 2020 Jun 10.

 

Subscribe to Comments for "Exact imposition of boundary conditions in physics-informed neural networks"

More comments

Syndicate

Subscribe to Syndicate