Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380987700> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4380987700 abstract "Abstract A simple method for adding uncertainty to neural network regression tasks in earth science via estimation of a general probability distribution is described. Specifically, we highlight the sinh-arcsinh-normal distributions as particularly well suited for neural network uncertainty estimation. The methodology supports estimation of heteroscedastic, asymmetric uncertainties by a simple modification of the network output and loss function. Method performance is demonstrated by predicting tropical cyclone intensity forecast uncertainty and by comparing two other common methods for neural network uncertainty quantification (i.e., Bayesian neural networks and Monte Carlo dropout). The simple approach described here is intuitive and applicable when no prior exists and one just wishes to parameterize the output and its uncertainty according to some previously defined family of distributions. The authors believe it will become a powerful, go-to method moving forward." @default.
- W4380987700 created "2023-06-17" @default.
- W4380987700 creator A5038101556 @default.
- W4380987700 creator A5040398805 @default.
- W4380987700 creator A5090316447 @default.
- W4380987700 date "2023-01-01" @default.
- W4380987700 modified "2023-10-07" @default.
- W4380987700 title "Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts" @default.
- W4380987700 cites W1912754123 @default.
- W4380987700 cites W1973137995 @default.
- W4380987700 cites W1998099504 @default.
- W4380987700 cites W1999377749 @default.
- W4380987700 cites W2041379399 @default.
- W4380987700 cites W2045246746 @default.
- W4380987700 cites W2047229728 @default.
- W4380987700 cites W2069821006 @default.
- W4380987700 cites W2102044921 @default.
- W4380987700 cites W2130715829 @default.
- W4380987700 cites W2228978105 @default.
- W4380987700 cites W2796293253 @default.
- W4380987700 cites W2931749449 @default.
- W4380987700 cites W2969309273 @default.
- W4380987700 cites W3043426275 @default.
- W4380987700 cites W3061312858 @default.
- W4380987700 cites W3102100346 @default.
- W4380987700 cites W3121168429 @default.
- W4380987700 cites W3138147141 @default.
- W4380987700 cites W3140418716 @default.
- W4380987700 cites W3164261338 @default.
- W4380987700 cites W4213041519 @default.
- W4380987700 cites W4249179470 @default.
- W4380987700 cites W4291720110 @default.
- W4380987700 doi "https://doi.org/10.1017/eds.2023.7" @default.
- W4380987700 hasPublicationYear "2023" @default.
- W4380987700 type Work @default.
- W4380987700 citedByCount "0" @default.
- W4380987700 crossrefType "journal-article" @default.
- W4380987700 hasAuthorship W4380987700A5038101556 @default.
- W4380987700 hasAuthorship W4380987700A5040398805 @default.
- W4380987700 hasAuthorship W4380987700A5090316447 @default.
- W4380987700 hasBestOaLocation W43809877001 @default.
- W4380987700 hasConcept C101104100 @default.
- W4380987700 hasConcept C105795698 @default.
- W4380987700 hasConcept C107673813 @default.
- W4380987700 hasConcept C111472728 @default.
- W4380987700 hasConcept C119857082 @default.
- W4380987700 hasConcept C138885662 @default.
- W4380987700 hasConcept C149782125 @default.
- W4380987700 hasConcept C153294291 @default.
- W4380987700 hasConcept C154945302 @default.
- W4380987700 hasConcept C19499675 @default.
- W4380987700 hasConcept C205649164 @default.
- W4380987700 hasConcept C2780586882 @default.
- W4380987700 hasConcept C29141058 @default.
- W4380987700 hasConcept C33923547 @default.
- W4380987700 hasConcept C41008148 @default.
- W4380987700 hasConcept C50644808 @default.
- W4380987700 hasConceptScore W4380987700C101104100 @default.
- W4380987700 hasConceptScore W4380987700C105795698 @default.
- W4380987700 hasConceptScore W4380987700C107673813 @default.
- W4380987700 hasConceptScore W4380987700C111472728 @default.
- W4380987700 hasConceptScore W4380987700C119857082 @default.
- W4380987700 hasConceptScore W4380987700C138885662 @default.
- W4380987700 hasConceptScore W4380987700C149782125 @default.
- W4380987700 hasConceptScore W4380987700C153294291 @default.
- W4380987700 hasConceptScore W4380987700C154945302 @default.
- W4380987700 hasConceptScore W4380987700C19499675 @default.
- W4380987700 hasConceptScore W4380987700C205649164 @default.
- W4380987700 hasConceptScore W4380987700C2780586882 @default.
- W4380987700 hasConceptScore W4380987700C29141058 @default.
- W4380987700 hasConceptScore W4380987700C33923547 @default.
- W4380987700 hasConceptScore W4380987700C41008148 @default.
- W4380987700 hasConceptScore W4380987700C50644808 @default.
- W4380987700 hasFunder F4320332171 @default.
- W4380987700 hasLocation W43809877001 @default.
- W4380987700 hasOpenAccess W4380987700 @default.
- W4380987700 hasPrimaryLocation W43809877001 @default.
- W4380987700 hasRelatedWork W1860603673 @default.
- W4380987700 hasRelatedWork W1974744834 @default.
- W4380987700 hasRelatedWork W2072458142 @default.
- W4380987700 hasRelatedWork W2082929752 @default.
- W4380987700 hasRelatedWork W2108677674 @default.
- W4380987700 hasRelatedWork W2122520405 @default.
- W4380987700 hasRelatedWork W3097231546 @default.
- W4380987700 hasRelatedWork W3124109721 @default.
- W4380987700 hasRelatedWork W3146848662 @default.
- W4380987700 hasRelatedWork W4248389398 @default.
- W4380987700 hasVolume "2" @default.
- W4380987700 isParatext "false" @default.
- W4380987700 isRetracted "false" @default.
- W4380987700 workType "article" @default.