Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/31603
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | VANPOUCKE, Danny E.P. | - |
dc.contributor.author | van Knippenberg, Onno S. J. | - |
dc.contributor.author | Hermans, Ko | - |
dc.contributor.author | Bernaerts, Katrien V. | - |
dc.contributor.author | Mehrkanoon, Siamak | - |
dc.date.accessioned | 2020-08-06T10:31:07Z | - |
dc.date.available | 2020-08-06T10:31:07Z | - |
dc.date.issued | 2020 | - |
dc.date.submitted | 2020-08-04T17:37:38Z | - |
dc.identifier.citation | Journal of applied physics, 128 (5) (Art N° 054901) | - |
dc.identifier.issn | 0021-8979 | - |
dc.identifier.uri | http://hdl.handle.net/1942/31603 | - |
dc.description.abstract | Machine learning is quickly becoming an important tool in modern materials design. Where many of its successes are rooted in huge datasets, the most common applications in academic and industrial materials design deal with datasets of at best a few tens of data points. Harnessing the power of machine learning in this context is, therefore, of considerable importance. In this work, we investigate the intricacies introduced by these small datasets. We show that individual data points introduce a significant chance factor in both model training and quality measurement. This chance factor can be mitigated by the introduction of an ensemble-averaged model. This model presents the highest accuracy, while at the same time, it is robust with regard to changing the dataset size. Furthermore, as only a single model instance needs to be stored and evaluated, it provides a highly efficient model for prediction purposes, ideally suited for the practical materials scientist. | - |
dc.description.sponsorship | D.E.V.P. and K.V.B. acknowledge the project D-NL-HIT carried out in the framework of INTERREG-Program DeutschlandNederland, which is co-financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat, and the provinces of Limburg, Gelderland, Noord-Brabant, and Overijssel. The computational resources and services used in this work were provided by the VSC (Flemish Supercomputer Center) and funded by the Research Foundation Flanders (FWO) and the Flemish Government—Department EWI. | - |
dc.language.iso | en | - |
dc.publisher | AMER INST PHYSICS | - |
dc.rights | © 2020 Author(s). | - |
dc.subject.other | Multitarget Optimization | - |
dc.subject.other | Information | - |
dc.subject.other | Regression | - |
dc.subject.other | Discovery | - |
dc.subject.other | Diamond | - |
dc.title | Small data materials design with machine learning: When the average model knows best | - |
dc.type | Journal Contribution | - |
dc.identifier.issue | 5 | - |
dc.identifier.volume | 128 | - |
local.bibliographicCitation.jcat | A1 | - |
local.publisher.place | 1305 WALT WHITMAN RD, STE 300, MELVILLE, NY 11747-4501 USA | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
local.bibliographicCitation.artnr | 054901 | - |
local.type.programme | VSC | - |
dc.identifier.doi | 10.1063/5.0012285 | - |
dc.identifier.isi | WOS:000559809200001 | - |
dc.identifier.eissn | - | |
local.provider.type | CrossRef | - |
local.uhasselt.uhpub | yes | - |
item.accessRights | Restricted Access | - |
item.validation | ecoom 2021 | - |
item.contributor | VANPOUCKE, Danny E.P. | - |
item.contributor | van Knippenberg, Onno S. J. | - |
item.contributor | Hermans, Ko | - |
item.contributor | Bernaerts, Katrien V. | - |
item.contributor | Mehrkanoon, Siamak | - |
item.fulltext | With Fulltext | - |
item.fullcitation | VANPOUCKE, Danny E.P.; van Knippenberg, Onno S. J.; Hermans, Ko; Bernaerts, Katrien V. & Mehrkanoon, Siamak (2020) Small data materials design with machine learning: When the average model knows best. In: Journal of applied physics, 128 (5) (Art N° 054901). | - |
crisitem.journal.issn | 0021-8979 | - |
crisitem.journal.eissn | 1089-7550 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
AvgModel_printed.pdf Restricted Access | Published version | 2.62 MB | Adobe PDF | View/Open Request a copy |
WEB OF SCIENCETM
Citations
16
checked on Jul 18, 2024
Page view(s)
52
checked on Sep 7, 2022
Download(s)
6
checked on Sep 7, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.