Software Open Access
Stiller, Patrick; Zhdanov, Maksim; Rustamov, Jeyhun; Bethke, Friedrich; Hoffmann, Nico
{ "DOI": "10.14278/rodare.1194", "id": "1194", "abstract": "<p>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.</p>", "language": "eng", "publisher": "Rodare", "title": "Neural Solvers", "author": [ { "family": "Stiller, Patrick" }, { "family": "Zhdanov, Maksim" }, { "family": "Rustamov, Jeyhun" }, { "family": "Bethke, Friedrich" }, { "family": "Hoffmann, Nico" } ], "type": "article", "version": "0.1", "issued": { "date-parts": [ [ 2021, 9, 6 ] ] } }
All versions | This version | |
---|---|---|
Views | 350 | 350 |
Downloads | 12 | 12 |
Data volume | 18.7 MB | 18.7 MB |
Unique views | 276 | 276 |
Unique downloads | 12 | 12 |