Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137149088> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3137149088 endingPage "10289" @default.
- W3137149088 startingPage "10276" @default.
- W3137149088 abstract "Deep kernel learning (DKL) leverages the connection between the Gaussian process (GP) and neural networks (NNs) to build an end-to-end hybrid model. It combines the capability of NN to learn rich representations under massive data and the nonparametric property of GP to achieve automatic regularization that incorporates a tradeoff between model fit and model complexity. However, the deterministic NN encoder may weaken the model regularization of the following GP part, especially on small datasets, due to the free latent representation. We, therefore, present a complete deep latent-variable kernel learning (DLVKL) model wherein the latent variables perform stochastic encoding for regularized representation. We further enhance the DLVKL from two aspects: 1) the expressive variational posterior through neural stochastic differential equation (NSDE) to improve the approximation quality and 2) the hybrid prior taking knowledge from both the SDE prior and the posterior to arrive at a flexible tradeoff. Extensive experiments imply that DLVKL-NSDE performs similar to the well-calibrated GP on small datasets, and shows superiority on large datasets." @default.
- W3137149088 created "2021-03-29" @default.
- W3137149088 creator A5060723344 @default.
- W3137149088 creator A5071030446 @default.
- W3137149088 creator A5077441448 @default.
- W3137149088 creator A5084638227 @default.
- W3137149088 date "2022-10-01" @default.
- W3137149088 modified "2023-10-16" @default.
- W3137149088 title "Deep Latent-Variable Kernel Learning" @default.
- W3137149088 cites W1567512734 @default.
- W3137149088 cites W2008717648 @default.
- W3137149088 cites W2090722674 @default.
- W3137149088 cites W2128973832 @default.
- W3137149088 cites W2143351549 @default.
- W3137149088 cites W2192203593 @default.
- W3137149088 cites W2194775991 @default.
- W3137149088 cites W2781973163 @default.
- W3137149088 cites W2791362611 @default.
- W3137149088 cites W2888935987 @default.
- W3137149088 cites W3000508506 @default.
- W3137149088 doi "https://doi.org/10.1109/tcyb.2021.3062140" @default.
- W3137149088 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33750728" @default.
- W3137149088 hasPublicationYear "2022" @default.
- W3137149088 type Work @default.
- W3137149088 sameAs 3137149088 @default.
- W3137149088 citedByCount "0" @default.
- W3137149088 crossrefType "journal-article" @default.
- W3137149088 hasAuthorship W3137149088A5060723344 @default.
- W3137149088 hasAuthorship W3137149088A5071030446 @default.
- W3137149088 hasAuthorship W3137149088A5077441448 @default.
- W3137149088 hasAuthorship W3137149088A5084638227 @default.
- W3137149088 hasBestOaLocation W31371490882 @default.
- W3137149088 hasConcept C108583219 @default.
- W3137149088 hasConcept C11413529 @default.
- W3137149088 hasConcept C114614502 @default.
- W3137149088 hasConcept C119857082 @default.
- W3137149088 hasConcept C121332964 @default.
- W3137149088 hasConcept C154945302 @default.
- W3137149088 hasConcept C163716315 @default.
- W3137149088 hasConcept C2776135515 @default.
- W3137149088 hasConcept C33923547 @default.
- W3137149088 hasConcept C41008148 @default.
- W3137149088 hasConcept C50644808 @default.
- W3137149088 hasConcept C51167844 @default.
- W3137149088 hasConcept C59404180 @default.
- W3137149088 hasConcept C61326573 @default.
- W3137149088 hasConcept C62520636 @default.
- W3137149088 hasConcept C65965080 @default.
- W3137149088 hasConcept C74193536 @default.
- W3137149088 hasConceptScore W3137149088C108583219 @default.
- W3137149088 hasConceptScore W3137149088C11413529 @default.
- W3137149088 hasConceptScore W3137149088C114614502 @default.
- W3137149088 hasConceptScore W3137149088C119857082 @default.
- W3137149088 hasConceptScore W3137149088C121332964 @default.
- W3137149088 hasConceptScore W3137149088C154945302 @default.
- W3137149088 hasConceptScore W3137149088C163716315 @default.
- W3137149088 hasConceptScore W3137149088C2776135515 @default.
- W3137149088 hasConceptScore W3137149088C33923547 @default.
- W3137149088 hasConceptScore W3137149088C41008148 @default.
- W3137149088 hasConceptScore W3137149088C50644808 @default.
- W3137149088 hasConceptScore W3137149088C51167844 @default.
- W3137149088 hasConceptScore W3137149088C59404180 @default.
- W3137149088 hasConceptScore W3137149088C61326573 @default.
- W3137149088 hasConceptScore W3137149088C62520636 @default.
- W3137149088 hasConceptScore W3137149088C65965080 @default.
- W3137149088 hasConceptScore W3137149088C74193536 @default.
- W3137149088 hasFunder F4320321001 @default.
- W3137149088 hasFunder F4320335787 @default.
- W3137149088 hasIssue "10" @default.
- W3137149088 hasLocation W31371490881 @default.
- W3137149088 hasLocation W31371490882 @default.
- W3137149088 hasLocation W31371490883 @default.
- W3137149088 hasOpenAccess W3137149088 @default.
- W3137149088 hasPrimaryLocation W31371490881 @default.
- W3137149088 hasRelatedWork W2619336040 @default.
- W3137149088 hasRelatedWork W2908875379 @default.
- W3137149088 hasRelatedWork W2964125661 @default.
- W3137149088 hasRelatedWork W3158586592 @default.
- W3137149088 hasRelatedWork W3197060662 @default.
- W3137149088 hasRelatedWork W3207676007 @default.
- W3137149088 hasRelatedWork W4206762304 @default.
- W3137149088 hasRelatedWork W4211155169 @default.
- W3137149088 hasRelatedWork W4213225422 @default.
- W3137149088 hasRelatedWork W4221136938 @default.
- W3137149088 hasVolume "52" @default.
- W3137149088 isParatext "false" @default.
- W3137149088 isRetracted "false" @default.
- W3137149088 magId "3137149088" @default.
- W3137149088 workType "article" @default.