Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382239711> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4382239711 endingPage "7838" @default.
- W4382239711 startingPage "7830" @default.
- W4382239711 abstract "Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation. The chosen parametric form can be a poor fit to the data-generating distribution, resulting in unreliable uncertainty estimates. In this work, we propose SampleNet, a flexible and scalable architecture for modeling uncertainty that avoids specifying a parametric form on the output distribution. SampleNets do so by defining an empirical distribution using samples that are learned with the Energy Score and regularized with the Sinkhorn Divergence. SampleNets are shown to be able to well-fit a wide range of distributions and to outperform baselines on large-scale real-world regression tasks." @default.
- W4382239711 created "2023-06-28" @default.
- W4382239711 creator A5003543022 @default.
- W4382239711 creator A5024242059 @default.
- W4382239711 creator A5037065865 @default.
- W4382239711 creator A5064150604 @default.
- W4382239711 creator A5087558114 @default.
- W4382239711 date "2023-06-26" @default.
- W4382239711 modified "2023-10-17" @default.
- W4382239711 title "Estimating Regression Predictive Distributions with Sample Networks" @default.
- W4382239711 doi "https://doi.org/10.1609/aaai.v37i6.25948" @default.
- W4382239711 hasPublicationYear "2023" @default.
- W4382239711 type Work @default.
- W4382239711 citedByCount "1" @default.
- W4382239711 countsByYear W43822397112023 @default.
- W4382239711 crossrefType "journal-article" @default.
- W4382239711 hasAuthorship W4382239711A5003543022 @default.
- W4382239711 hasAuthorship W4382239711A5024242059 @default.
- W4382239711 hasAuthorship W4382239711A5037065865 @default.
- W4382239711 hasAuthorship W4382239711A5064150604 @default.
- W4382239711 hasAuthorship W4382239711A5087558114 @default.
- W4382239711 hasBestOaLocation W43822397111 @default.
- W4382239711 hasConcept C105795698 @default.
- W4382239711 hasConcept C107673813 @default.
- W4382239711 hasConcept C117251300 @default.
- W4382239711 hasConcept C124101348 @default.
- W4382239711 hasConcept C127413603 @default.
- W4382239711 hasConcept C138885662 @default.
- W4382239711 hasConcept C146978453 @default.
- W4382239711 hasConcept C149782125 @default.
- W4382239711 hasConcept C154945302 @default.
- W4382239711 hasConcept C160234255 @default.
- W4382239711 hasConcept C204323151 @default.
- W4382239711 hasConcept C207390915 @default.
- W4382239711 hasConcept C24574437 @default.
- W4382239711 hasConcept C33923547 @default.
- W4382239711 hasConcept C37903108 @default.
- W4382239711 hasConcept C41008148 @default.
- W4382239711 hasConcept C41895202 @default.
- W4382239711 hasConcept C83247935 @default.
- W4382239711 hasConcept C83546350 @default.
- W4382239711 hasConceptScore W4382239711C105795698 @default.
- W4382239711 hasConceptScore W4382239711C107673813 @default.
- W4382239711 hasConceptScore W4382239711C117251300 @default.
- W4382239711 hasConceptScore W4382239711C124101348 @default.
- W4382239711 hasConceptScore W4382239711C127413603 @default.
- W4382239711 hasConceptScore W4382239711C138885662 @default.
- W4382239711 hasConceptScore W4382239711C146978453 @default.
- W4382239711 hasConceptScore W4382239711C149782125 @default.
- W4382239711 hasConceptScore W4382239711C154945302 @default.
- W4382239711 hasConceptScore W4382239711C160234255 @default.
- W4382239711 hasConceptScore W4382239711C204323151 @default.
- W4382239711 hasConceptScore W4382239711C207390915 @default.
- W4382239711 hasConceptScore W4382239711C24574437 @default.
- W4382239711 hasConceptScore W4382239711C33923547 @default.
- W4382239711 hasConceptScore W4382239711C37903108 @default.
- W4382239711 hasConceptScore W4382239711C41008148 @default.
- W4382239711 hasConceptScore W4382239711C41895202 @default.
- W4382239711 hasConceptScore W4382239711C83247935 @default.
- W4382239711 hasConceptScore W4382239711C83546350 @default.
- W4382239711 hasIssue "6" @default.
- W4382239711 hasLocation W43822397111 @default.
- W4382239711 hasLocation W43822397112 @default.
- W4382239711 hasOpenAccess W4382239711 @default.
- W4382239711 hasPrimaryLocation W43822397111 @default.
- W4382239711 hasRelatedWork W1775436701 @default.
- W4382239711 hasRelatedWork W1873475443 @default.
- W4382239711 hasRelatedWork W2077410226 @default.
- W4382239711 hasRelatedWork W2092974266 @default.
- W4382239711 hasRelatedWork W2115779695 @default.
- W4382239711 hasRelatedWork W2140012311 @default.
- W4382239711 hasRelatedWork W2145812012 @default.
- W4382239711 hasRelatedWork W2743729757 @default.
- W4382239711 hasRelatedWork W3021457118 @default.
- W4382239711 hasRelatedWork W3091195600 @default.
- W4382239711 hasVolume "37" @default.
- W4382239711 isParatext "false" @default.
- W4382239711 isRetracted "false" @default.
- W4382239711 workType "article" @default.