Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217138612> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W3217138612 abstract "The field of materials science has seen an explosion in the amount of accessible high quality data. With this sudden surge of data, the application of machine learning (ML) onto materials data has led to great results. Particular success has been found in training models based on chemical formula. Such models have traditionally focused on learning from density functional theory (DFT) or experimental data. Though some researchers have explored the use of DFT calculated properties as features for learning, this has not gained much traction since the machine learning predictions would be limited by the DFT computation time and accuracy. In this work, we explore the use of a stacked ensemble learning system that combines machine learning from DFT calculations to improve learning on experimental data. This is accomplished by handling the DFT and experimental data separately, training distinct models for each. The DFT models are used to generate a predicted DFT value for the formulae in the experimental data. A meta-learner-trained using predictions generated by the experimental models combined with predictions from the DFT models-is shown to improve root-mean-squared-error by over 9% in the test data, when compared to a baseline model that only learns from the training data." @default.
- W3217138612 created "2021-12-06" @default.
- W3217138612 creator A5003301534 @default.
- W3217138612 creator A5030732386 @default.
- W3217138612 creator A5050610772 @default.
- W3217138612 date "2018-10-23" @default.
- W3217138612 modified "2023-09-23" @default.
- W3217138612 title "Extracting Knowledge from DFT: Experimental Band Gap Predictions Through Ensemble Learning" @default.
- W3217138612 doi "https://doi.org/10.26434/chemrxiv.7236029.v1" @default.
- W3217138612 hasPublicationYear "2018" @default.
- W3217138612 type Work @default.
- W3217138612 sameAs 3217138612 @default.
- W3217138612 citedByCount "1" @default.
- W3217138612 countsByYear W32171386122019 @default.
- W3217138612 crossrefType "posted-content" @default.
- W3217138612 hasAuthorship W3217138612A5003301534 @default.
- W3217138612 hasAuthorship W3217138612A5030732386 @default.
- W3217138612 hasAuthorship W3217138612A5050610772 @default.
- W3217138612 hasBestOaLocation W32171386121 @default.
- W3217138612 hasConcept C105795698 @default.
- W3217138612 hasConcept C11413529 @default.
- W3217138612 hasConcept C119857082 @default.
- W3217138612 hasConcept C147597530 @default.
- W3217138612 hasConcept C152365726 @default.
- W3217138612 hasConcept C154945302 @default.
- W3217138612 hasConcept C16910744 @default.
- W3217138612 hasConcept C185592680 @default.
- W3217138612 hasConcept C199360897 @default.
- W3217138612 hasConcept C33923547 @default.
- W3217138612 hasConcept C41008148 @default.
- W3217138612 hasConcept C45374587 @default.
- W3217138612 hasConcept C45942800 @default.
- W3217138612 hasConcept C55037315 @default.
- W3217138612 hasConceptScore W3217138612C105795698 @default.
- W3217138612 hasConceptScore W3217138612C11413529 @default.
- W3217138612 hasConceptScore W3217138612C119857082 @default.
- W3217138612 hasConceptScore W3217138612C147597530 @default.
- W3217138612 hasConceptScore W3217138612C152365726 @default.
- W3217138612 hasConceptScore W3217138612C154945302 @default.
- W3217138612 hasConceptScore W3217138612C16910744 @default.
- W3217138612 hasConceptScore W3217138612C185592680 @default.
- W3217138612 hasConceptScore W3217138612C199360897 @default.
- W3217138612 hasConceptScore W3217138612C33923547 @default.
- W3217138612 hasConceptScore W3217138612C41008148 @default.
- W3217138612 hasConceptScore W3217138612C45374587 @default.
- W3217138612 hasConceptScore W3217138612C45942800 @default.
- W3217138612 hasConceptScore W3217138612C55037315 @default.
- W3217138612 hasLocation W32171386121 @default.
- W3217138612 hasOpenAccess W3217138612 @default.
- W3217138612 hasPrimaryLocation W32171386121 @default.
- W3217138612 hasRelatedWork W1191482210 @default.
- W3217138612 hasRelatedWork W2005827916 @default.
- W3217138612 hasRelatedWork W2582268762 @default.
- W3217138612 hasRelatedWork W2889453578 @default.
- W3217138612 hasRelatedWork W3005055299 @default.
- W3217138612 hasRelatedWork W3013699712 @default.
- W3217138612 hasRelatedWork W3211971560 @default.
- W3217138612 hasRelatedWork W4225307033 @default.
- W3217138612 hasRelatedWork W4254688476 @default.
- W3217138612 hasRelatedWork W4285741730 @default.
- W3217138612 isParatext "false" @default.
- W3217138612 isRetracted "false" @default.
- W3217138612 magId "3217138612" @default.
- W3217138612 workType "article" @default.