Full metadata record
DC FieldValueLanguage
dc.contributor.authorMorand, Lukas-
dc.contributor.authorIraki, Tarek-
dc.contributor.authorDornheim, Johannes-
dc.contributor.authorLink, Norbert-
dc.contributor.authorHelm, Dirk-
dc.date.accessioned2021-11-10T13:24:22Z-
dc.date.available2021-11-10T13:24:22Z-
dc.date.issued2021-
dc.identifier.urihttps://fordatis.fraunhofer.de/handle/fordatis/219-
dc.identifier.urihttp://dx.doi.org/10.24406/fordatis/146-
dc.description.abstractThis publication contains three exemplary data sets generated via active learning and numerical simulations. The active learning approach used is query-by-committee. For comparison, data is also generated using classical sampling approachs. The first data set originates from a toy example that is based on an appoximated Dirac delta function, for which data was generated randomly and via query-by-committee. The second example is part of a parameter identification problem in materials modeling, for which data was generated via Latin Hypercube design, a knowledge-based approach and query-by-committee. The third example is about generating artificial bcc rolling textures, for which data was generated via Latin Hypercube design, query-by-committee and an extended query-by-committee approach that prevents sampling in regions out of scope.en
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddcDDC::500 Naturwissenschaften und Mathematik::530 Physik::531 Klassische Mechanik, Festkörpermechaniken
dc.subject.ddcDDC::600 Technik, Medizin, angewandte Wissenschaften::670 Industrielle Fertigung::671 Metallverarbeitung und Rohprodukte aus Metallen
dc.titleSets of exemplary microstructure-property data generated via active learning and numerical simulationsen
dc.typeTabular Dataen
dc.contributor.funderDeutsche Forschungsgemeinschaft DFGen
dc.relation.issupplementtohttp://publica.fraunhofer.de/dokumente/N-648561.html-
dc.relation.issupplementtohttps://doi.org/10.3389/fmats.2021.824441-
fordatis.groupMikroelektroniken
fordatis.instituteIWM Fraunhofer-Institut für Werkstoffmechaniken
fordatis.rawdatatrueen
fordatis.sponsorship.projectid415804944en
fordatis.sponsorship.projectnameMaßgeschneiderte Werkstoffeigenschaften durch Mikrostrukturoptimierung: Maschinelle Lernverfahren zur Modellierung und Inversion von Struktur-Eigenschafts-Beziehungen und deren Anwendung auf Blechwerkstoffeen
Appears in Collections:Fraunhofer-Institut für Werkstoffmechanik IWM



This item is licensed under a Creative Commons License Creative Commons