FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3096272898> ?p ?o ?g. }

• W3096272898 abstract "Predictive models that accurately emulate complex scientific processes can achieve exponential speed-ups over numerical simulators or experiments, and at the same time provide surrogates for improving the subsequent analysis. Consequently, there is a recent surge in utilizing modern machine learning (ML) methods, such as deep neural networks, to build data-driven emulators. While the majority of existing efforts has focused on tailoring off-the-shelf ML solutions to better suit the scientific problem at hand, we study an often overlooked, yet important, problem of choosing loss functions to measure the discrepancy between observed data and the predictions from a model. Due to lack of better priors on the expected residual structure, in practice, simple choices such as the mean squared error and the mean absolute error are made. However, the inherent symmetric noise assumption made by these loss functions makes them inappropriate in cases where the data is heterogeneous or when the noise distribution is asymmetric. We propose Learn-by-Calibrating (LbC), a novel deep learning approach based on interval calibration for designing emulators in scientific applications, that are effective even with heterogeneous data and are robust to outliers. Using a large suite of use-cases, we show that LbC provides significant improvements in generalization error over widely-adopted loss function choices, achieves high-quality emulators even in small data regimes and more importantly, recovers the inherent noise structure without any explicit priors." @default.
• W3096272898 created "2020-11-09" @default.
• W3096272898 creator A5019902487 @default.
• W3096272898 creator A5024559172 @default.
• W3096272898 creator A5026742436 @default.
• W3096272898 creator A5034354413 @default.
• W3096272898 creator A5046632395 @default.
• W3096272898 creator A5056062979 @default.
• W3096272898 creator A5074529081 @default.
• W3096272898 date "2020-11-06" @default.
• W3096272898 modified "2023-10-18" @default.
• W3096272898 title "Designing accurate emulators for scientific processes using calibration-driven deep models" @default.
• W3096272898 cites W1977079033 @default.
• W3096272898 cites W2025720061 @default.
• W3096272898 cites W2033350940 @default.
• W3096272898 cites W2041302083 @default.
• W3096272898 cites W2043680591 @default.
• W3096272898 cites W2095445185 @default.
• W3096272898 cites W2125621954 @default.
• W3096272898 cites W2137620021 @default.
• W3096272898 cites W2154029067 @default.
• W3096272898 cites W2163922914 @default.
• W3096272898 cites W2416574941 @default.
• W3096272898 cites W2593649365 @default.
• W3096272898 cites W2614083378 @default.
• W3096272898 cites W2619383789 @default.
• W3096272898 cites W2657631929 @default.
• W3096272898 cites W2750732093 @default.
• W3096272898 cites W2751448052 @default.
• W3096272898 cites W2775280502 @default.
• W3096272898 cites W2775970449 @default.
• W3096272898 cites W2784733489 @default.
• W3096272898 cites W2884430236 @default.
• W3096272898 cites W2905810301 @default.
• W3096272898 cites W2907560147 @default.
• W3096272898 cites W2908541468 @default.
• W3096272898 cites W2921353139 @default.
• W3096272898 cites W2951934944 @default.
• W3096272898 cites W2951965145 @default.
• W3096272898 cites W2962927818 @default.
• W3096272898 cites W2963798770 @default.
• W3096272898 cites W2982509564 @default.
• W3096272898 cites W2998618342 @default.
• W3096272898 cites W3015993000 @default.
• W3096272898 cites W3016740865 @default.
• W3096272898 cites W3023371261 @default.
• W3096272898 doi "https://doi.org/10.1038/s41467-020-19448-8" @default.
• W3096272898 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7648787" @default.
• W3096272898 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33159053" @default.
• W3096272898 hasPublicationYear "2020" @default.
• W3096272898 type Work @default.
• W3096272898 sameAs 3096272898 @default.
• W3096272898 citedByCount "14" @default.
• W3096272898 countsByYear W30962728982021 @default.
• W3096272898 countsByYear W30962728982022 @default.
• W3096272898 countsByYear W30962728982023 @default.
• W3096272898 crossrefType "journal-article" @default.
• W3096272898 hasAuthorship W3096272898A5019902487 @default.
• W3096272898 hasAuthorship W3096272898A5024559172 @default.
• W3096272898 hasAuthorship W3096272898A5026742436 @default.
• W3096272898 hasAuthorship W3096272898A5034354413 @default.
• W3096272898 hasAuthorship W3096272898A5046632395 @default.
• W3096272898 hasAuthorship W3096272898A5056062979 @default.
• W3096272898 hasAuthorship W3096272898A5074529081 @default.
• W3096272898 hasBestOaLocation W30962728981 @default.
• W3096272898 hasConcept C105795698 @default.
• W3096272898 hasConcept C107673813 @default.
• W3096272898 hasConcept C108583219 @default.
• W3096272898 hasConcept C11413529 @default.
• W3096272898 hasConcept C115961682 @default.
• W3096272898 hasConcept C119857082 @default.
• W3096272898 hasConcept C124101348 @default.
• W3096272898 hasConcept C134306372 @default.
• W3096272898 hasConcept C139945424 @default.
• W3096272898 hasConcept C154945302 @default.
• W3096272898 hasConcept C155512373 @default.
• W3096272898 hasConcept C165838908 @default.
• W3096272898 hasConcept C177148314 @default.
• W3096272898 hasConcept C177769412 @default.
• W3096272898 hasConcept C2780009758 @default.
• W3096272898 hasConcept C33923547 @default.
• W3096272898 hasConcept C41008148 @default.
• W3096272898 hasConcept C50644808 @default.
• W3096272898 hasConcept C79337645 @default.
• W3096272898 hasConcept C99498987 @default.
• W3096272898 hasConceptScore W3096272898C105795698 @default.
• W3096272898 hasConceptScore W3096272898C107673813 @default.
• W3096272898 hasConceptScore W3096272898C108583219 @default.
• W3096272898 hasConceptScore W3096272898C11413529 @default.
• W3096272898 hasConceptScore W3096272898C115961682 @default.
• W3096272898 hasConceptScore W3096272898C119857082 @default.
• W3096272898 hasConceptScore W3096272898C124101348 @default.
• W3096272898 hasConceptScore W3096272898C134306372 @default.
• W3096272898 hasConceptScore W3096272898C139945424 @default.
• W3096272898 hasConceptScore W3096272898C154945302 @default.
• W3096272898 hasConceptScore W3096272898C155512373 @default.
• W3096272898 hasConceptScore W3096272898C165838908 @default.
• W3096272898 hasConceptScore W3096272898C177148314 @default.
• W3096272898 hasConceptScore W3096272898C177769412 @default.
• W3096272898 hasConceptScore W3096272898C2780009758 @default.

• next