Matches in SemOpenAlex for { <https://semopenalex.org/work/W2909699200> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2909699200 endingPage "700" @default.
- W2909699200 startingPage "690" @default.
- W2909699200 abstract "Unsupervised discovery of interpretable features and controllable generation with highdimensional data are currently major challenges in machine learning, with applicationsin data visualisation, clustering and artificialdata synthesis. We propose a model basedon variational auto-encoders (VAEs) in whichinterpretation is induced through latent spacesparsity with a mixture of Spike and Slab distributions as prior. We derive an evidencelower bound for this model and propose a specific training method for recovering disentangled features as sparse elements in latent vectors. In our experiments, we demonstrate superior disentanglement performance to standardVAE approaches when an estimate of the number of true sources of variation is not availableand objects display different combinations ofattributes. Furthermore, the new model provides unique capabilities, such as recoveringfeature exploitation, synthesising samples thatshare attributes with a given input object andcontrolling both discrete and continuous features upon generation." @default.
- W2909699200 created "2019-01-25" @default.
- W2909699200 creator A5017068912 @default.
- W2909699200 creator A5048873240 @default.
- W2909699200 creator A5070918132 @default.
- W2909699200 date "2019-07-25" @default.
- W2909699200 modified "2023-09-24" @default.
- W2909699200 title "Variational Sparse Coding" @default.
- W2909699200 cites W1857382374 @default.
- W2909699200 cites W1909320841 @default.
- W2909699200 cites W1999974018 @default.
- W2909699200 cites W2145889472 @default.
- W2909699200 cites W2147942061 @default.
- W2909699200 cites W2155676512 @default.
- W2909699200 cites W2163922914 @default.
- W2909699200 cites W2567691283 @default.
- W2909699200 cites W2625327772 @default.
- W2909699200 cites W2750384547 @default.
- W2909699200 cites W2753738274 @default.
- W2909699200 cites W2785519580 @default.
- W2909699200 cites W2950821630 @default.
- W2909699200 cites W2951004968 @default.
- W2909699200 cites W2951287198 @default.
- W2909699200 cites W2951326654 @default.
- W2909699200 cites W2952165242 @default.
- W2909699200 cites W2962738009 @default.
- W2909699200 cites W2962976271 @default.
- W2909699200 cites W2963504544 @default.
- W2909699200 cites W2963532523 @default.
- W2909699200 cites W2963799213 @default.
- W2909699200 cites W2964127395 @default.
- W2909699200 hasPublicationYear "2019" @default.
- W2909699200 type Work @default.
- W2909699200 sameAs 2909699200 @default.
- W2909699200 citedByCount "12" @default.
- W2909699200 countsByYear W29096992002018 @default.
- W2909699200 countsByYear W29096992002019 @default.
- W2909699200 countsByYear W29096992002020 @default.
- W2909699200 countsByYear W29096992002021 @default.
- W2909699200 countsByYear W29096992002022 @default.
- W2909699200 crossrefType "proceedings-article" @default.
- W2909699200 hasAuthorship W2909699200A5017068912 @default.
- W2909699200 hasAuthorship W2909699200A5048873240 @default.
- W2909699200 hasAuthorship W2909699200A5070918132 @default.
- W2909699200 hasConcept C101738243 @default.
- W2909699200 hasConcept C153180895 @default.
- W2909699200 hasConcept C154945302 @default.
- W2909699200 hasConcept C36464697 @default.
- W2909699200 hasConcept C41008148 @default.
- W2909699200 hasConcept C50644808 @default.
- W2909699200 hasConcept C67186912 @default.
- W2909699200 hasConcept C73555534 @default.
- W2909699200 hasConcept C77088390 @default.
- W2909699200 hasConcept C77637269 @default.
- W2909699200 hasConcept C8038995 @default.
- W2909699200 hasConcept C83665646 @default.
- W2909699200 hasConceptScore W2909699200C101738243 @default.
- W2909699200 hasConceptScore W2909699200C153180895 @default.
- W2909699200 hasConceptScore W2909699200C154945302 @default.
- W2909699200 hasConceptScore W2909699200C36464697 @default.
- W2909699200 hasConceptScore W2909699200C41008148 @default.
- W2909699200 hasConceptScore W2909699200C50644808 @default.
- W2909699200 hasConceptScore W2909699200C67186912 @default.
- W2909699200 hasConceptScore W2909699200C73555534 @default.
- W2909699200 hasConceptScore W2909699200C77088390 @default.
- W2909699200 hasConceptScore W2909699200C77637269 @default.
- W2909699200 hasConceptScore W2909699200C8038995 @default.
- W2909699200 hasConceptScore W2909699200C83665646 @default.
- W2909699200 hasLocation W29096992001 @default.
- W2909699200 hasOpenAccess W2909699200 @default.
- W2909699200 hasPrimaryLocation W29096992001 @default.
- W2909699200 hasRelatedWork W1520325657 @default.
- W2909699200 hasRelatedWork W1959608418 @default.
- W2909699200 hasRelatedWork W2550969209 @default.
- W2909699200 hasRelatedWork W2727551782 @default.
- W2909699200 hasRelatedWork W2753738274 @default.
- W2909699200 hasRelatedWork W2809657535 @default.
- W2909699200 hasRelatedWork W2920987997 @default.
- W2909699200 hasRelatedWork W2951741291 @default.
- W2909699200 hasRelatedWork W2962944330 @default.
- W2909699200 hasRelatedWork W2963504544 @default.
- W2909699200 hasRelatedWork W2964121744 @default.
- W2909699200 hasRelatedWork W2971335355 @default.
- W2909699200 hasRelatedWork W2980725178 @default.
- W2909699200 hasRelatedWork W2989511902 @default.
- W2909699200 hasRelatedWork W3036118961 @default.
- W2909699200 hasRelatedWork W3037109476 @default.
- W2909699200 hasRelatedWork W3122688130 @default.
- W2909699200 hasRelatedWork W3134908072 @default.
- W2909699200 hasRelatedWork W3167712819 @default.
- W2909699200 hasRelatedWork W81214986 @default.
- W2909699200 isParatext "false" @default.
- W2909699200 isRetracted "false" @default.
- W2909699200 magId "2909699200" @default.
- W2909699200 workType "article" @default.