FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2911315040> ?p ?o ?g. }

• W2911315040 abstract "Deep learning has been at the foundation of large improvements in image classification. To improve the robustness of predictions, Bayesian approximations have been used to learn parameters in deep neural networks. We follow an alternative approach, by using Gaussian processes as building blocks for Bayesian deep learning models, which has recently become viable due to advances in inference for convolutional and deep structure. We investigate deep convolutional Gaussian processes, and identify a problem that holds back current performance. To remedy the issue, we introduce a translation insensitive convolutional kernel, which removes the restriction of requiring identical outputs for identical patch inputs. We show empirically that this convolutional kernel improves performances in both shallow and deep models. On MNIST, FASHION-MNIST and CIFAR-10 we improve previous GP models in terms of accuracy, with the addition of having more calibrated predictive probabilities than simple DNN models." @default.
• W2911315040 created "2019-02-21" @default.
• W2911315040 creator A5023796924 @default.
• W2911315040 creator A5030860008 @default.
• W2911315040 creator A5077632636 @default.
• W2911315040 creator A5085437275 @default.
• W2911315040 creator A5090110068 @default.
• W2911315040 date "2019-02-15" @default.
• W2911315040 modified "2023-09-27" @default.
• W2911315040 title "Translation Insensitivity for Deep Convolutional Gaussian Processes" @default.
• W2911315040 cites W137285897 @default.
• W2911315040 cites W1522301498 @default.
• W2911315040 cites W1777124189 @default.
• W2911315040 cites W2025720061 @default.
• W2911315040 cites W2130283669 @default.
• W2911315040 cites W2147800946 @default.
• W2911315040 cites W215707797 @default.
• W2911315040 cites W2166851633 @default.
• W2911315040 cites W2174362514 @default.
• W2911315040 cites W2254249950 @default.
• W2911315040 cites W2274287116 @default.
• W2911315040 cites W2582199702 @default.
• W2911315040 cites W2807037403 @default.
• W2911315040 cites W2885059312 @default.
• W2911315040 cites W2886272201 @default.
• W2911315040 cites W2903037999 @default.
• W2911315040 cites W2912279788 @default.
• W2911315040 cites W2951595529 @default.
• W2911315040 cites W2962731272 @default.
• W2911315040 cites W2962875063 @default.
• W2911315040 cites W2963711523 @default.
• W2911315040 cites W2964059111 @default.
• W2911315040 cites W3010435838 @default.
• W2911315040 cites W3031355122 @default.
• W2911315040 hasPublicationYear "2019" @default.
• W2911315040 type Work @default.
• W2911315040 sameAs 2911315040 @default.
• W2911315040 citedByCount "6" @default.
• W2911315040 countsByYear W29113150402019 @default.
• W2911315040 countsByYear W29113150402020 @default.
• W2911315040 countsByYear W29113150402021 @default.
• W2911315040 crossrefType "posted-content" @default.
• W2911315040 hasAuthorship W2911315040A5023796924 @default.
• W2911315040 hasAuthorship W2911315040A5030860008 @default.
• W2911315040 hasAuthorship W2911315040A5077632636 @default.
• W2911315040 hasAuthorship W2911315040A5085437275 @default.
• W2911315040 hasAuthorship W2911315040A5090110068 @default.
• W2911315040 hasConcept C104317684 @default.
• W2911315040 hasConcept C107673813 @default.
• W2911315040 hasConcept C108583219 @default.
• W2911315040 hasConcept C114614502 @default.
• W2911315040 hasConcept C119857082 @default.
• W2911315040 hasConcept C121332964 @default.
• W2911315040 hasConcept C153180895 @default.
• W2911315040 hasConcept C154945302 @default.
• W2911315040 hasConcept C160234255 @default.
• W2911315040 hasConcept C163716315 @default.
• W2911315040 hasConcept C185592680 @default.
• W2911315040 hasConcept C190502265 @default.
• W2911315040 hasConcept C2776214188 @default.
• W2911315040 hasConcept C2984842247 @default.
• W2911315040 hasConcept C33923547 @default.
• W2911315040 hasConcept C41008148 @default.
• W2911315040 hasConcept C55493867 @default.
• W2911315040 hasConcept C61326573 @default.
• W2911315040 hasConcept C62520636 @default.
• W2911315040 hasConcept C63479239 @default.
• W2911315040 hasConcept C74193536 @default.
• W2911315040 hasConcept C81363708 @default.
• W2911315040 hasConceptScore W2911315040C104317684 @default.
• W2911315040 hasConceptScore W2911315040C107673813 @default.
• W2911315040 hasConceptScore W2911315040C108583219 @default.
• W2911315040 hasConceptScore W2911315040C114614502 @default.
• W2911315040 hasConceptScore W2911315040C119857082 @default.
• W2911315040 hasConceptScore W2911315040C121332964 @default.
• W2911315040 hasConceptScore W2911315040C153180895 @default.
• W2911315040 hasConceptScore W2911315040C154945302 @default.
• W2911315040 hasConceptScore W2911315040C160234255 @default.
• W2911315040 hasConceptScore W2911315040C163716315 @default.
• W2911315040 hasConceptScore W2911315040C185592680 @default.
• W2911315040 hasConceptScore W2911315040C190502265 @default.
• W2911315040 hasConceptScore W2911315040C2776214188 @default.
• W2911315040 hasConceptScore W2911315040C2984842247 @default.
• W2911315040 hasConceptScore W2911315040C33923547 @default.
• W2911315040 hasConceptScore W2911315040C41008148 @default.
• W2911315040 hasConceptScore W2911315040C55493867 @default.
• W2911315040 hasConceptScore W2911315040C61326573 @default.
• W2911315040 hasConceptScore W2911315040C62520636 @default.
• W2911315040 hasConceptScore W2911315040C63479239 @default.
• W2911315040 hasConceptScore W2911315040C74193536 @default.
• W2911315040 hasConceptScore W2911315040C81363708 @default.
• W2911315040 hasLocation W29113150401 @default.
• W2911315040 hasOpenAccess W2911315040 @default.
• W2911315040 hasPrimaryLocation W29113150401 @default.
• W2911315040 hasRelatedWork W1746819321 @default.
• W2911315040 hasRelatedWork W2099768828 @default.
• W2911315040 hasRelatedWork W2337746211 @default.
• W2911315040 hasRelatedWork W2605177561 @default.
• W2911315040 hasRelatedWork W2746314669 @default.
• W2911315040 hasRelatedWork W2766774700 @default.

• next