Software Open Access
Neural Solvers
Stiller, Patrick;
Zhdanov, Maksim;
Rustamov, Jeyhun;
Bethke, Friedrich;
Hoffmann, Nico
Neural Solvers are neural network-based solvers for partial differential equations and inverse problems. The framework implements scalable physics-informed neural networks Physics-informed neural networks allow strong scaling by design. Therefore, we have developed a framework that uses data parallelism to accelerate the training of physics-informed neural networks significantly. To implement data parallelism, we use the Horovod framework, which provides near-ideal speedup on multi-GPU regimes.
Files
(1.6 MB)
| Name | Size | |
|---|---|---|
|
NeuralSolvers-v.0.1.zip
md5:e5c607ca66ca5486779e58f186e84d5b |
1.6 MB | Download |
1,397
36
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 1,397 | 1,397 |
| Downloads | 36 | 36 |
| Data volume | 56.2 MB | 56.2 MB |
| Unique views | 1,183 | 1,183 |
| Unique downloads | 35 | 35 |
- Publication date:
- September 6, 2021
- DOI:
-
- Keyword(s):
- PINNs PDEs Neural Solver Scalable AI
- Related identifiers:
- Compiled by:
https://arxiv.org/pdf/2009.03730.pdf - Identical to:
https://www.hzdr.de/publications/Publ-33172 - Communities:
- License (for files):
- Creative Commons Attribution 1.0 Generic