You are here
A nonlocal physics-informed deep learning framework using the peridynamic differential operator
https://www.researchgate.net/publication/341816480_A_nonlocal_physics-in...
Dear iMechanica Community:
I am sharing with you our latest work on Physics-Informed Neural Networks (PINN) for the discovery of non-smooth problems with steep gradients (concentration) or singularity. To this end, we propose a nonlocal PINN architecture, inspired by the Peridynamic nonlocal theory, using the Peridynamic Differential Operator.
If you are interested in deep learning for non-smooth problems with discontinuity, steep gradients, or even singularity, please check our pre-print at:
https://www.researchgate.net/publication/341816480_A_nonlocal_physics-in...
Thanks,
Ehsan
Attachment | Size |
---|---|
![]() | 787.18 KB |
- haghighat's blog
- Log in or register to post comments
- 3009 reads
![Subscribe to Comments for "A nonlocal physics-informed deep learning framework using the peridynamic differential operator"](https://imechanica.org/misc/feed.png)
Comments
Library
Dear Ehsan,
Thanks for sharing your paper. What automatic differentiation library did you use ? Did you do numerical expermients with the common libraries?
Ashkan,