September 6, 2021 Software Open Access

Stiller, Patrick; Zhdanov, Maksim; Rustamov, Jeyhun; Bethke, Friedrich; Hoffmann, Nico

JSON-LD (schema.org) Export

{
  "creator": [
    {
      "name": "Stiller, Patrick", 
      "@id": "https://orcid.org/0000-0003-1950-069X", 
      "@type": "Person"
    }, 
    {
      "name": "Zhdanov, Maksim", 
      "@type": "Person"
    }, 
    {
      "name": "Rustamov, Jeyhun", 
      "@type": "Person"
    }, 
    {
      "name": "Bethke, Friedrich", 
      "@type": "Person"
    }, 
    {
      "name": "Hoffmann, Nico", 
      "@type": "Person"
    }
  ], 
  "sameAs": [
    "https://www.hzdr.de/publications/Publ-33172"
  ], 
  "name": "Neural Solvers", 
  "inLanguage": {
    "name": "English", 
    "alternateName": "eng", 
    "@type": "Language"
  }, 
  "@id": "https://doi.org/10.14278/rodare.1194", 
  "@context": "https://schema.org/", 
  "contributor": [], 
  "datePublished": "2021-09-06", 
  "@type": "SoftwareSourceCode", 
  "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>", 
  "url": "https://rodare.hzdr.de/record/1194", 
  "keywords": [
    "PINNs", 
    "PDEs", 
    "Neural Solver", 
    "Scalable AI"
  ], 
  "identifier": "https://doi.org/10.14278/rodare.1194", 
  "license": "https://creativecommons.org/licenses/by/1.0/legalcode", 
  "version": "0.1"
}