Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf
1 PublicationNeural Solvers
Stiller, P.; Zhdanov, M.; Rustamov, J.; Bethke, F.; Hoffmann, N.
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.
Keywords: PINNs; PDEs; Neural Solver; Scalable AI
Related publications
- URL: https://arxiv.org/pdf/2009.03730.pdf compiled/created this (Id 33172) publication
-
Software in the HZDR data repository RODARE
Publication date: 2021-09-06 Open access
DOI: 10.14278/rodare.1193
Versions: 10.14278/rodare.1194
License: CC-BY-1.0
Downloads
Permalink: https://www.hzdr.de/publications/Publ-33172
Publ.-Id: 33172