Software Open Access
Stiller, Patrick; Zhdanov, Maksim; Rustamov, Jeyhun; Bethke, Friedrich; Hoffmann, Nico
{ "@id": "https://doi.org/10.14278/rodare.1194", "name": "Neural Solvers", "keywords": [ "PINNs", "PDEs", "Neural Solver", "Scalable AI" ], "datePublished": "2021-09-06", "creator": [ { "@id": "https://orcid.org/0000-0003-1950-069X", "name": "Stiller, Patrick", "@type": "Person" }, { "name": "Zhdanov, Maksim", "@type": "Person" }, { "name": "Rustamov, Jeyhun", "@type": "Person" }, { "name": "Bethke, Friedrich", "@type": "Person" }, { "name": "Hoffmann, Nico", "@type": "Person" } ], "version": "0.1", "license": "https://creativecommons.org/licenses/by/1.0/legalcode", "description": "<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>", "sameAs": [ "https://www.hzdr.de/publications/Publ-33172" ], "@context": "https://schema.org/", "inLanguage": { "alternateName": "eng", "name": "English", "@type": "Language" }, "identifier": "https://doi.org/10.14278/rodare.1194", "@type": "SoftwareSourceCode", "contributor": [], "url": "https://rodare.hzdr.de/record/1194" }
All versions | This version | |
---|---|---|
Views | 466 | 466 |
Downloads | 14 | 14 |
Data volume | 21.9 MB | 21.9 MB |
Unique views | 376 | 376 |
Unique downloads | 14 | 14 |