Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204136415> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3204136415 endingPage "613" @default.
- W3204136415 startingPage "604" @default.
- W3204136415 abstract "In healthcare applications, predictive uncertainty has been used to assess predictive accuracy. In this paper, we demonstrate that predictive uncertainty estimated by the current methods does not highly correlate with prediction error by decomposing the latter into random and systematic errors, and showing that the former is equivalent to the variance of the random error. In addition, we observe that current methods unnecessarily compromise performance by modifying the model and training loss to estimate the target and uncertainty jointly. We show that estimating them separately without modifications improves performance. Following this, we propose a novel method that estimates the target labels and magnitude of the prediction error in two steps. We demonstrate this method on a large-scale MRI reconstruction task, and achieve significantly better results than the state-of-the-art uncertainty estimation methods." @default.
- W3204136415 created "2021-10-11" @default.
- W3204136415 creator A5025155285 @default.
- W3204136415 creator A5034214530 @default.
- W3204136415 creator A5087368991 @default.
- W3204136415 date "2021-01-01" @default.
- W3204136415 modified "2023-10-06" @default.
- W3204136415 title "Learning to Predict Error for MRI Reconstruction" @default.
- W3204136415 cites W130387664 @default.
- W3204136415 cites W1560021816 @default.
- W3204136415 cites W1901129140 @default.
- W3204136415 cites W1973333099 @default.
- W3204136415 cites W2103496339 @default.
- W3204136415 cites W2111959010 @default.
- W3204136415 cites W2133665775 @default.
- W3204136415 cites W2476548250 @default.
- W3204136415 cites W2594608309 @default.
- W3204136415 cites W2610571781 @default.
- W3204136415 cites W2787894218 @default.
- W3204136415 cites W2953532875 @default.
- W3204136415 cites W2965563166 @default.
- W3204136415 cites W2979455868 @default.
- W3204136415 cites W3097194025 @default.
- W3204136415 doi "https://doi.org/10.1007/978-3-030-87199-4_57" @default.
- W3204136415 hasPublicationYear "2021" @default.
- W3204136415 type Work @default.
- W3204136415 sameAs 3204136415 @default.
- W3204136415 citedByCount "5" @default.
- W3204136415 countsByYear W32041364152021 @default.
- W3204136415 countsByYear W32041364152022 @default.
- W3204136415 countsByYear W32041364152023 @default.
- W3204136415 crossrefType "book-chapter" @default.
- W3204136415 hasAuthorship W3204136415A5025155285 @default.
- W3204136415 hasAuthorship W3204136415A5034214530 @default.
- W3204136415 hasAuthorship W3204136415A5087368991 @default.
- W3204136415 hasBestOaLocation W32041364152 @default.
- W3204136415 hasConcept C11413529 @default.
- W3204136415 hasConcept C119857082 @default.
- W3204136415 hasConcept C121332964 @default.
- W3204136415 hasConcept C121955636 @default.
- W3204136415 hasConcept C144133560 @default.
- W3204136415 hasConcept C154945302 @default.
- W3204136415 hasConcept C162324750 @default.
- W3204136415 hasConcept C167085575 @default.
- W3204136415 hasConcept C187736073 @default.
- W3204136415 hasConcept C196083921 @default.
- W3204136415 hasConcept C2778755073 @default.
- W3204136415 hasConcept C2780451532 @default.
- W3204136415 hasConcept C41008148 @default.
- W3204136415 hasConcept C62520636 @default.
- W3204136415 hasConceptScore W3204136415C11413529 @default.
- W3204136415 hasConceptScore W3204136415C119857082 @default.
- W3204136415 hasConceptScore W3204136415C121332964 @default.
- W3204136415 hasConceptScore W3204136415C121955636 @default.
- W3204136415 hasConceptScore W3204136415C144133560 @default.
- W3204136415 hasConceptScore W3204136415C154945302 @default.
- W3204136415 hasConceptScore W3204136415C162324750 @default.
- W3204136415 hasConceptScore W3204136415C167085575 @default.
- W3204136415 hasConceptScore W3204136415C187736073 @default.
- W3204136415 hasConceptScore W3204136415C196083921 @default.
- W3204136415 hasConceptScore W3204136415C2778755073 @default.
- W3204136415 hasConceptScore W3204136415C2780451532 @default.
- W3204136415 hasConceptScore W3204136415C41008148 @default.
- W3204136415 hasConceptScore W3204136415C62520636 @default.
- W3204136415 hasLocation W32041364151 @default.
- W3204136415 hasLocation W32041364152 @default.
- W3204136415 hasLocation W32041364153 @default.
- W3204136415 hasOpenAccess W3204136415 @default.
- W3204136415 hasPrimaryLocation W32041364151 @default.
- W3204136415 hasRelatedWork W2000663367 @default.
- W3204136415 hasRelatedWork W2037004935 @default.
- W3204136415 hasRelatedWork W2081472162 @default.
- W3204136415 hasRelatedWork W2118155885 @default.
- W3204136415 hasRelatedWork W2163515958 @default.
- W3204136415 hasRelatedWork W2585070004 @default.
- W3204136415 hasRelatedWork W2961085424 @default.
- W3204136415 hasRelatedWork W4286629047 @default.
- W3204136415 hasRelatedWork W4306674287 @default.
- W3204136415 hasRelatedWork W4224009465 @default.
- W3204136415 isParatext "false" @default.
- W3204136415 isRetracted "false" @default.
- W3204136415 magId "3204136415" @default.
- W3204136415 workType "book-chapter" @default.