Matches in SemOpenAlex for { <https://semopenalex.org/work/W2998428519> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2998428519 endingPage "109498" @default.
- W2998428519 startingPage "109498" @default.
- W2998428519 abstract "Abstract One of the most common criticisms of machine learning is an assumed inability for models to extrapolate, i.e. to identify extraordinary materials with properties beyond those present in the training data set. To investigate whether this is indeed the case, this work takes advantage of density functional theory calculated properties (bulk modulus, shear modulus, thermal conductivity, thermal expansion, band gap, and Debye temperature) to investigate whether machine learning is truly capable of predicting materials with properties that extend beyond previously seen values. We refer to these materials as extraordinary, meaning they represent the top 1% of values in the available data set. Interestingly, we show that even when machine learning is trained on a fraction of the bottom 99% we can consistently identify 3 4 of the highest performing compositions for all considered properties with a precision that is typically above 0.5. We explore model performance as the extrapolation distance is increased in various ways including, introduction of a gap, removal of certain elements, and removal of certain structure types. Moreover, we investigate a few different modeling choices and demonstrate how a classification approach can identify an equivalent amount of extraordinary compounds but with significantly fewer false positives than a regression approach. Finally, we discuss cautions and potential limitations in implementing such an approach to discover new record-breaking materials." @default.
- W2998428519 created "2020-01-10" @default.
- W2998428519 creator A5003301534 @default.
- W2998428519 creator A5008401924 @default.
- W2998428519 creator A5050610772 @default.
- W2998428519 creator A5056006831 @default.
- W2998428519 date "2020-03-01" @default.
- W2998428519 modified "2023-10-10" @default.
- W2998428519 title "Can machine learning find extraordinary materials?" @default.
- W2998428519 cites W1563453094 @default.
- W2998428519 cites W1865667476 @default.
- W2998428519 cites W1982598895 @default.
- W2998428519 cites W2112845989 @default.
- W2998428519 cites W2134329894 @default.
- W2998428519 cites W2151971404 @default.
- W2998428519 cites W2159357141 @default.
- W2998428519 cites W2262229344 @default.
- W2998428519 cites W2313966941 @default.
- W2998428519 cites W2331899405 @default.
- W2998428519 cites W2343462019 @default.
- W2998428519 cites W2347129741 @default.
- W2998428519 cites W2432215141 @default.
- W2998428519 cites W2464725281 @default.
- W2998428519 cites W2467249088 @default.
- W2998428519 cites W2509907061 @default.
- W2998428519 cites W2520500207 @default.
- W2998428519 cites W2758567842 @default.
- W2998428519 cites W2766856748 @default.
- W2998428519 cites W2778051509 @default.
- W2998428519 cites W2790960441 @default.
- W2998428519 cites W2792500745 @default.
- W2998428519 cites W2804765537 @default.
- W2998428519 cites W2807471255 @default.
- W2998428519 cites W2810731239 @default.
- W2998428519 cites W2883578585 @default.
- W2998428519 cites W2885048850 @default.
- W2998428519 cites W2909102051 @default.
- W2998428519 cites W2923096151 @default.
- W2998428519 cites W2953641512 @default.
- W2998428519 cites W2963784900 @default.
- W2998428519 cites W2970591347 @default.
- W2998428519 cites W2983329389 @default.
- W2998428519 cites W336365082 @default.
- W2998428519 cites W4205835102 @default.
- W2998428519 cites W4232741888 @default.
- W2998428519 cites W4242320552 @default.
- W2998428519 doi "https://doi.org/10.1016/j.commatsci.2019.109498" @default.
- W2998428519 hasPublicationYear "2020" @default.
- W2998428519 type Work @default.
- W2998428519 sameAs 2998428519 @default.
- W2998428519 citedByCount "53" @default.
- W2998428519 countsByYear W29984285192020 @default.
- W2998428519 countsByYear W29984285192021 @default.
- W2998428519 countsByYear W29984285192022 @default.
- W2998428519 countsByYear W29984285192023 @default.
- W2998428519 crossrefType "journal-article" @default.
- W2998428519 hasAuthorship W2998428519A5003301534 @default.
- W2998428519 hasAuthorship W2998428519A5008401924 @default.
- W2998428519 hasAuthorship W2998428519A5050610772 @default.
- W2998428519 hasAuthorship W2998428519A5056006831 @default.
- W2998428519 hasConcept C171250308 @default.
- W2998428519 hasConcept C192562407 @default.
- W2998428519 hasConcept C41008148 @default.
- W2998428519 hasConceptScore W2998428519C171250308 @default.
- W2998428519 hasConceptScore W2998428519C192562407 @default.
- W2998428519 hasConceptScore W2998428519C41008148 @default.
- W2998428519 hasLocation W29984285191 @default.
- W2998428519 hasOpenAccess W2998428519 @default.
- W2998428519 hasPrimaryLocation W29984285191 @default.
- W2998428519 hasRelatedWork W2160608618 @default.
- W2998428519 hasRelatedWork W2328380595 @default.
- W2998428519 hasRelatedWork W2737498735 @default.
- W2998428519 hasRelatedWork W2748952813 @default.
- W2998428519 hasRelatedWork W2889753853 @default.
- W2998428519 hasRelatedWork W2899084033 @default.
- W2998428519 hasRelatedWork W2899764894 @default.
- W2998428519 hasRelatedWork W3000789669 @default.
- W2998428519 hasRelatedWork W4212879511 @default.
- W2998428519 hasRelatedWork W4292492973 @default.
- W2998428519 hasVolume "174" @default.
- W2998428519 isParatext "false" @default.
- W2998428519 isRetracted "false" @default.
- W2998428519 magId "2998428519" @default.
- W2998428519 workType "article" @default.