Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804157688> ?p ?o ?g. }
- W2804157688 abstract "The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes (GPs) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks." @default.
- W2804157688 created "2018-06-01" @default.
- W2804157688 creator A5017009335 @default.
- W2804157688 creator A5021162375 @default.
- W2804157688 creator A5023657363 @default.
- W2804157688 creator A5026047687 @default.
- W2804157688 creator A5030697996 @default.
- W2804157688 date "2018-05-26" @default.
- W2804157688 modified "2023-09-28" @default.
- W2804157688 title "Calibrating Deep Convolutional Gaussian Processes" @default.
- W2804157688 cites W1591346633 @default.
- W2804157688 cites W1618905105 @default.
- W2804157688 cites W1746819321 @default.
- W2804157688 cites W1959608418 @default.
- W2804157688 cites W2098824882 @default.
- W2804157688 cites W2118563516 @default.
- W2804157688 cites W2144902422 @default.
- W2804157688 cites W2167608136 @default.
- W2804157688 cites W2170912685 @default.
- W2804157688 cites W2544176167 @default.
- W2804157688 cites W2626967530 @default.
- W2804157688 cites W2725875209 @default.
- W2804157688 cites W2728139190 @default.
- W2804157688 cites W2735471653 @default.
- W2804157688 cites W2950517871 @default.
- W2804157688 cites W2951060109 @default.
- W2804157688 cites W2951985269 @default.
- W2804157688 cites W2952291055 @default.
- W2804157688 cites W2963238274 @default.
- W2804157688 cites W2963711523 @default.
- W2804157688 cites W2964059111 @default.
- W2804157688 cites W2964121744 @default.
- W2804157688 cites W3037590790 @default.
- W2804157688 cites W601603264 @default.
- W2804157688 hasPublicationYear "2018" @default.
- W2804157688 type Work @default.
- W2804157688 sameAs 2804157688 @default.
- W2804157688 citedByCount "2" @default.
- W2804157688 countsByYear W28041576882018 @default.
- W2804157688 countsByYear W28041576882020 @default.
- W2804157688 crossrefType "posted-content" @default.
- W2804157688 hasAuthorship W2804157688A5017009335 @default.
- W2804157688 hasAuthorship W2804157688A5021162375 @default.
- W2804157688 hasAuthorship W2804157688A5023657363 @default.
- W2804157688 hasAuthorship W2804157688A5026047687 @default.
- W2804157688 hasAuthorship W2804157688A5030697996 @default.
- W2804157688 hasConcept C11413529 @default.
- W2804157688 hasConcept C119599485 @default.
- W2804157688 hasConcept C119857082 @default.
- W2804157688 hasConcept C121332964 @default.
- W2804157688 hasConcept C127413603 @default.
- W2804157688 hasConcept C148043351 @default.
- W2804157688 hasConcept C153180895 @default.
- W2804157688 hasConcept C154945302 @default.
- W2804157688 hasConcept C163716315 @default.
- W2804157688 hasConcept C41008148 @default.
- W2804157688 hasConcept C48103436 @default.
- W2804157688 hasConcept C60229501 @default.
- W2804157688 hasConcept C61326573 @default.
- W2804157688 hasConcept C62520636 @default.
- W2804157688 hasConcept C76155785 @default.
- W2804157688 hasConcept C81363708 @default.
- W2804157688 hasConceptScore W2804157688C11413529 @default.
- W2804157688 hasConceptScore W2804157688C119599485 @default.
- W2804157688 hasConceptScore W2804157688C119857082 @default.
- W2804157688 hasConceptScore W2804157688C121332964 @default.
- W2804157688 hasConceptScore W2804157688C127413603 @default.
- W2804157688 hasConceptScore W2804157688C148043351 @default.
- W2804157688 hasConceptScore W2804157688C153180895 @default.
- W2804157688 hasConceptScore W2804157688C154945302 @default.
- W2804157688 hasConceptScore W2804157688C163716315 @default.
- W2804157688 hasConceptScore W2804157688C41008148 @default.
- W2804157688 hasConceptScore W2804157688C48103436 @default.
- W2804157688 hasConceptScore W2804157688C60229501 @default.
- W2804157688 hasConceptScore W2804157688C61326573 @default.
- W2804157688 hasConceptScore W2804157688C62520636 @default.
- W2804157688 hasConceptScore W2804157688C76155785 @default.
- W2804157688 hasConceptScore W2804157688C81363708 @default.
- W2804157688 hasOpenAccess W2804157688 @default.
- W2804157688 hasRelatedWork W1798702550 @default.
- W2804157688 hasRelatedWork W2563954902 @default.
- W2804157688 hasRelatedWork W2898111068 @default.
- W2804157688 hasRelatedWork W2902854273 @default.
- W2804157688 hasRelatedWork W2944840759 @default.
- W2804157688 hasRelatedWork W2988739636 @default.
- W2804157688 hasRelatedWork W2989028032 @default.
- W2804157688 hasRelatedWork W2995851819 @default.
- W2804157688 hasRelatedWork W3004893834 @default.
- W2804157688 hasRelatedWork W3010129597 @default.
- W2804157688 hasRelatedWork W3034666242 @default.
- W2804157688 hasRelatedWork W3049165116 @default.
- W2804157688 hasRelatedWork W3106521501 @default.
- W2804157688 hasRelatedWork W3137502297 @default.
- W2804157688 hasRelatedWork W3143648836 @default.
- W2804157688 hasRelatedWork W3180217530 @default.
- W2804157688 hasRelatedWork W3189050980 @default.
- W2804157688 hasRelatedWork W3199064820 @default.
- W2804157688 hasRelatedWork W3200439229 @default.
- W2804157688 hasRelatedWork W3205907861 @default.
- W2804157688 isParatext "false" @default.