September 6, 2021 Software Open Access

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

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.14278/rodare.1194</identifier>
  <creators>
    <creator>
      <creatorName>Stiller, Patrick</creatorName>
      <givenName>Patrick</givenName>
      <familyName>Stiller</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-1950-069X</nameIdentifier>
    </creator>
    <creator>
      <creatorName>Zhdanov, Maksim</creatorName>
      <givenName>Maksim</givenName>
      <familyName>Zhdanov</familyName>
    </creator>
    <creator>
      <creatorName>Rustamov, Jeyhun</creatorName>
      <givenName>Jeyhun</givenName>
      <familyName>Rustamov</familyName>
    </creator>
    <creator>
      <creatorName>Bethke, Friedrich</creatorName>
      <givenName>Friedrich</givenName>
      <familyName>Bethke</familyName>
    </creator>
    <creator>
      <creatorName>Hoffmann, Nico</creatorName>
      <givenName>Nico</givenName>
      <familyName>Hoffmann</familyName>
    </creator>
  </creators>
  <titles>
    <title>Neural Solvers</title>
  </titles>
  <publisher>Rodare</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>PINNs</subject>
    <subject>PDEs</subject>
    <subject>Neural Solver</subject>
    <subject>Scalable AI</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-09-06</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://rodare.hzdr.de/record/1194</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsCompiledBy">https://arxiv.org/pdf/2009.03730.pdf</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsIdenticalTo">https://www.hzdr.de/publications/Publ-33172</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.14278/rodare.1193</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/matter</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/rodare</relatedIdentifier>
  </relatedIdentifiers>
  <version>0.1</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/1.0/legalcode">Creative Commons Attribution 1.0 Generic</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;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.&lt;/p&gt;</description>
  </descriptions>
</resource>