FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892094491> ?p ?o ?g. }

• W2892094491 endingPage "915" @default.
• W2892094491 startingPage "906" @default.
• W2892094491 abstract "We present a scheme to obtain an inexpensive and reliable estimate of the uncertainty associated with the predictions of a machine-learning model of atomic and molecular properties. The scheme is based on resampling, with multiple models being generated based on subsampling of the same training data. The accuracy of the uncertainty prediction can be benchmarked by maximum likelihood estimation, which can also be used to correct for correlations between resampled models and to improve the performance of the uncertainty estimation by a cross-validation procedure. In the case of sparse Gaussian Process Regression models, this resampled estimator can be evaluated at negligible cost. We demonstrate the reliability of these estimates for the prediction of molecular and materials energetics and for the estimation of nuclear chemical shieldings in molecular crystals. Extension to estimate the uncertainty in energy differences, forces, or other correlated predictions is straightforward. This method can be easily applied to other machine-learning schemes and will be beneficial to make data-driven predictions more reliable and to facilitate training-set optimization and active-learning strategies." @default.
• W2892094491 created "2018-09-27" @default.
• W2892094491 creator A5015430594 @default.
• W2892094491 creator A5021241296 @default.
• W2892094491 creator A5072067086 @default.
• W2892094491 creator A5079309376 @default.
• W2892094491 date "2019-01-03" @default.
• W2892094491 modified "2023-10-16" @default.
• W2892094491 title "Fast and Accurate Uncertainty Estimation in Chemical Machine Learning" @default.
• W2892094491 cites W1557550410 @default.
• W2892094491 cites W1560021816 @default.
• W2892094491 cites W1865667476 @default.
• W2892094491 cites W1973310094 @default.
• W2892094491 cites W1978183953 @default.
• W2892094491 cites W1981368803 @default.
• W2892094491 cites W1984087004 @default.
• W2892094491 cites W1995771589 @default.
• W2892094491 cites W2010288272 @default.
• W2892094491 cites W2025444507 @default.
• W2892094491 cites W2026195773 @default.
• W2892094491 cites W2029413789 @default.
• W2892094491 cites W2036113194 @default.
• W2892094491 cites W2037672122 @default.
• W2892094491 cites W2037761619 @default.
• W2892094491 cites W2057858097 @default.
• W2892094491 cites W2059527006 @default.
• W2892094491 cites W2070668052 @default.
• W2892094491 cites W2079782346 @default.
• W2892094491 cites W2080635178 @default.
• W2892094491 cites W2083415705 @default.
• W2892094491 cites W2104489082 @default.
• W2892094491 cites W2117897510 @default.
• W2892094491 cites W2120145199 @default.
• W2892094491 cites W2122643824 @default.
• W2892094491 cites W2129832613 @default.
• W2892094491 cites W2142635246 @default.
• W2892094491 cites W2148284063 @default.
• W2892094491 cites W2158471180 @default.
• W2892094491 cites W2168175751 @default.
• W2892094491 cites W2319902168 @default.
• W2892094491 cites W2337496963 @default.
• W2892094491 cites W2464725281 @default.
• W2892094491 cites W2547447472 @default.
• W2892094491 cites W2566642125 @default.
• W2892094491 cites W2605925159 @default.
• W2892094491 cites W2620687153 @default.
• W2892094491 cites W2757878424 @default.
• W2892094491 cites W2765966278 @default.
• W2892094491 cites W2782772320 @default.
• W2892094491 cites W2792137452 @default.
• W2892094491 cites W2792348590 @default.
• W2892094491 cites W2799063346 @default.
• W2892094491 cites W2800168263 @default.
• W2892094491 cites W2800301423 @default.
• W2892094491 cites W2805461540 @default.
• W2892094491 cites W2889002363 @default.
• W2892094491 cites W3101095095 @default.
• W2892094491 cites W3104585744 @default.
• W2892094491 cites W4212883601 @default.
• W2892094491 cites W4300266293 @default.
• W2892094491 doi "https://doi.org/10.1021/acs.jctc.8b00959" @default.
• W2892094491 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30605342" @default.
• W2892094491 hasPublicationYear "2019" @default.
• W2892094491 type Work @default.
• W2892094491 sameAs 2892094491 @default.
• W2892094491 citedByCount "101" @default.
• W2892094491 countsByYear W28920944912019 @default.
• W2892094491 countsByYear W28920944912020 @default.
• W2892094491 countsByYear W28920944912021 @default.
• W2892094491 countsByYear W28920944912022 @default.
• W2892094491 countsByYear W28920944912023 @default.
• W2892094491 crossrefType "journal-article" @default.
• W2892094491 hasAuthorship W2892094491A5015430594 @default.
• W2892094491 hasAuthorship W2892094491A5021241296 @default.
• W2892094491 hasAuthorship W2892094491A5072067086 @default.
• W2892094491 hasAuthorship W2892094491A5079309376 @default.
• W2892094491 hasBestOaLocation W28920944912 @default.
• W2892094491 hasConcept C105795698 @default.
• W2892094491 hasConcept C111919701 @default.
• W2892094491 hasConcept C119857082 @default.
• W2892094491 hasConcept C121332964 @default.
• W2892094491 hasConcept C124101348 @default.
• W2892094491 hasConcept C150921843 @default.
• W2892094491 hasConcept C154945302 @default.
• W2892094491 hasConcept C163258240 @default.
• W2892094491 hasConcept C163716315 @default.
• W2892094491 hasConcept C177264268 @default.
• W2892094491 hasConcept C185429906 @default.
• W2892094491 hasConcept C199360897 @default.
• W2892094491 hasConcept C32230216 @default.
• W2892094491 hasConcept C33923547 @default.
• W2892094491 hasConcept C41008148 @default.
• W2892094491 hasConcept C43214815 @default.
• W2892094491 hasConcept C61326573 @default.
• W2892094491 hasConcept C62520636 @default.
• W2892094491 hasConcept C81692654 @default.
• W2892094491 hasConcept C98045186 @default.
• W2892094491 hasConceptScore W2892094491C105795698 @default.

• next