Data · dataset · 2021
Neural Solvers
Listed in RODARE
Neural Solvers are neural network-based solvers for partial differential equations and inverse problems.
Description
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.
Links
Where it is published
- RODARE record rodare.hzdr.de/record/1194 ↗
landing page · from rodare hzdr de
- DOI doi.org/10.14278/rodare.1194 ↗
DOI / persistent id · from rodare hzdr de
Catalogue records · 1
- InvenioRDM API rodare.hzdr.de/api/records/1194 ↗
metadata API · from rodare hzdr de
Topics
- From keywords
- Computer Science & AI
- Inferred from text
- Machine learning 75%
Provenance · 1 source records, 8 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| RODARE | 1194 | 14 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | |
| concepts[field].anzsrc:group:4611 | enrichment · rodare hzdr de | taxonomy-embedding@1.1.0 | title+keywords+description (75%) |
| concepts[field].local:field:computer-science-ai | mapping · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | |
| description | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | /metadata/description |
| publication_date | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | |
| title | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | /metadata/title |
| updated_date | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 | |
| version_label | source · rodare hzdr de | connector:rodare_hzdr_de@1.0.0 |