Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891986131> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2891986131 abstract "Deep Generative Models are powerful learning tools that utilize an autoencoder structure for generating data and inferring latent variables. The most basic version has a single latent variable that encodes the training data in an unsupervised manner, and the extension to semi-supervised learning combines a latent class label with a continuous latent variable whose purpose is to provide the variations in the data that are not caused by the class label. The structure of the two-variable generative model should imply that both the class label and the continuous variable are free parameters that can be chosen to generate data, that is, the two are a priori independent. However, we show that this is the case only for certain data sets. We propose two objective functions for guiding the variables to be a priori independent, we use a novel training procedure to optimize the objectives, and we show experimentally that the objectives successfully produce the desired independence. We perform all of our experiments on the multi-labeled NORB dataset." @default.
- W2891986131 created "2018-09-27" @default.
- W2891986131 creator A5019458419 @default.
- W2891986131 creator A5049990629 @default.
- W2891986131 date "2018-07-01" @default.
- W2891986131 modified "2023-09-26" @default.
- W2891986131 title "A Priori Independence for Deep Generative Models" @default.
- W2891986131 cites W1959608418 @default.
- W2891986131 cites W1983320747 @default.
- W2891986131 cites W2099471712 @default.
- W2891986131 cites W2166093887 @default.
- W2891986131 cites W2188365844 @default.
- W2891986131 cites W2280377497 @default.
- W2891986131 cites W2407712691 @default.
- W2891986131 cites W2508499024 @default.
- W2891986131 cites W2510947207 @default.
- W2891986131 cites W2596906311 @default.
- W2891986131 cites W2724955321 @default.
- W2891986131 cites W2890766902 @default.
- W2891986131 cites W2949416428 @default.
- W2891986131 cites W2952673310 @default.
- W2891986131 cites W2963135265 @default.
- W2891986131 cites W2963275229 @default.
- W2891986131 cites W2963351648 @default.
- W2891986131 cites W2963567641 @default.
- W2891986131 cites W2964159205 @default.
- W2891986131 cites W830076066 @default.
- W2891986131 doi "https://doi.org/10.23919/icif.2018.8455743" @default.
- W2891986131 hasPublicationYear "2018" @default.
- W2891986131 type Work @default.
- W2891986131 sameAs 2891986131 @default.
- W2891986131 citedByCount "1" @default.
- W2891986131 countsByYear W28919861312018 @default.
- W2891986131 crossrefType "proceedings-article" @default.
- W2891986131 hasAuthorship W2891986131A5019458419 @default.
- W2891986131 hasAuthorship W2891986131A5049990629 @default.
- W2891986131 hasConcept C101738243 @default.
- W2891986131 hasConcept C105795698 @default.
- W2891986131 hasConcept C108583219 @default.
- W2891986131 hasConcept C111472728 @default.
- W2891986131 hasConcept C119857082 @default.
- W2891986131 hasConcept C134306372 @default.
- W2891986131 hasConcept C138885662 @default.
- W2891986131 hasConcept C153180895 @default.
- W2891986131 hasConcept C154945302 @default.
- W2891986131 hasConcept C156216132 @default.
- W2891986131 hasConcept C167966045 @default.
- W2891986131 hasConcept C182365436 @default.
- W2891986131 hasConcept C2777212361 @default.
- W2891986131 hasConcept C33923547 @default.
- W2891986131 hasConcept C35651441 @default.
- W2891986131 hasConcept C39890363 @default.
- W2891986131 hasConcept C41008148 @default.
- W2891986131 hasConcept C51167844 @default.
- W2891986131 hasConcept C65965080 @default.
- W2891986131 hasConcept C70727504 @default.
- W2891986131 hasConcept C75553542 @default.
- W2891986131 hasConcept C79772020 @default.
- W2891986131 hasConceptScore W2891986131C101738243 @default.
- W2891986131 hasConceptScore W2891986131C105795698 @default.
- W2891986131 hasConceptScore W2891986131C108583219 @default.
- W2891986131 hasConceptScore W2891986131C111472728 @default.
- W2891986131 hasConceptScore W2891986131C119857082 @default.
- W2891986131 hasConceptScore W2891986131C134306372 @default.
- W2891986131 hasConceptScore W2891986131C138885662 @default.
- W2891986131 hasConceptScore W2891986131C153180895 @default.
- W2891986131 hasConceptScore W2891986131C154945302 @default.
- W2891986131 hasConceptScore W2891986131C156216132 @default.
- W2891986131 hasConceptScore W2891986131C167966045 @default.
- W2891986131 hasConceptScore W2891986131C182365436 @default.
- W2891986131 hasConceptScore W2891986131C2777212361 @default.
- W2891986131 hasConceptScore W2891986131C33923547 @default.
- W2891986131 hasConceptScore W2891986131C35651441 @default.
- W2891986131 hasConceptScore W2891986131C39890363 @default.
- W2891986131 hasConceptScore W2891986131C41008148 @default.
- W2891986131 hasConceptScore W2891986131C51167844 @default.
- W2891986131 hasConceptScore W2891986131C65965080 @default.
- W2891986131 hasConceptScore W2891986131C70727504 @default.
- W2891986131 hasConceptScore W2891986131C75553542 @default.
- W2891986131 hasConceptScore W2891986131C79772020 @default.
- W2891986131 hasLocation W28919861311 @default.
- W2891986131 hasOpenAccess W2891986131 @default.
- W2891986131 hasPrimaryLocation W28919861311 @default.
- W2891986131 hasRelatedWork W2331205114 @default.
- W2891986131 hasRelatedWork W2770818364 @default.
- W2891986131 hasRelatedWork W2808508258 @default.
- W2891986131 hasRelatedWork W2884772108 @default.
- W2891986131 hasRelatedWork W2889724758 @default.
- W2891986131 hasRelatedWork W2891986131 @default.
- W2891986131 hasRelatedWork W2949950221 @default.
- W2891986131 hasRelatedWork W2963987720 @default.
- W2891986131 hasRelatedWork W2988134182 @default.
- W2891986131 hasRelatedWork W4287817957 @default.
- W2891986131 isParatext "false" @default.
- W2891986131 isRetracted "false" @default.
- W2891986131 magId "2891986131" @default.
- W2891986131 workType "article" @default.