Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890766902> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W2890766902 abstract "Deep Generative Models (DGMs) are very powerful semi-supervised classifiers. We aim to further improve their prediction accuracies by constructing novel generative models that incorporate multiple labels and by proposing open-book testing, a new testing paradigm that leverages the semi-supervised nature of DGMs. We perform all of our experiments on the NORB data set. Open-book testing allows unlabeled test data to be used while training in an effort to combat overfitting. We show experimentally that open-book testing significantly increases classification performance even though no label information is provided. Further, we develop five new multi-label DGMs. One is a generic multi-label model and four are custom-tailored to the NORB data set. We find that, compared to a single-label classifier, the presence of additional labels degrades performance despite open-book testing but is nearly perfect at 99.7% when a priori independence is enforced." @default.
- W2890766902 created "2018-09-27" @default.
- W2890766902 creator A5019458419 @default.
- W2890766902 creator A5049990629 @default.
- W2890766902 date "2018-07-01" @default.
- W2890766902 modified "2023-10-05" @default.
- W2890766902 title "Open-Book Testing and Multi-Label Deep Generative Models" @default.
- W2890766902 cites W1959608418 @default.
- W2890766902 cites W1983320747 @default.
- W2890766902 cites W2099471712 @default.
- W2890766902 cites W2166093887 @default.
- W2890766902 cites W2188365844 @default.
- W2890766902 cites W2280377497 @default.
- W2890766902 cites W2407712691 @default.
- W2890766902 cites W2508499024 @default.
- W2890766902 cites W2510947207 @default.
- W2890766902 cites W2596906311 @default.
- W2890766902 cites W2724955321 @default.
- W2890766902 cites W2891986131 @default.
- W2890766902 cites W2949416428 @default.
- W2890766902 cites W2952673310 @default.
- W2890766902 cites W2963135265 @default.
- W2890766902 cites W2963275229 @default.
- W2890766902 cites W2963351648 @default.
- W2890766902 cites W2963567641 @default.
- W2890766902 cites W2964159205 @default.
- W2890766902 cites W830076066 @default.
- W2890766902 doi "https://doi.org/10.23919/icif.2018.8455658" @default.
- W2890766902 hasPublicationYear "2018" @default.
- W2890766902 type Work @default.
- W2890766902 sameAs 2890766902 @default.
- W2890766902 citedByCount "1" @default.
- W2890766902 countsByYear W28907669022018 @default.
- W2890766902 crossrefType "proceedings-article" @default.
- W2890766902 hasAuthorship W2890766902A5019458419 @default.
- W2890766902 hasAuthorship W2890766902A5049990629 @default.
- W2890766902 hasConcept C154945302 @default.
- W2890766902 hasConcept C204321447 @default.
- W2890766902 hasConcept C39890363 @default.
- W2890766902 hasConcept C41008148 @default.
- W2890766902 hasConceptScore W2890766902C154945302 @default.
- W2890766902 hasConceptScore W2890766902C204321447 @default.
- W2890766902 hasConceptScore W2890766902C39890363 @default.
- W2890766902 hasConceptScore W2890766902C41008148 @default.
- W2890766902 hasLocation W28907669021 @default.
- W2890766902 hasOpenAccess W2890766902 @default.
- W2890766902 hasPrimaryLocation W28907669021 @default.
- W2890766902 hasRelatedWork W1569841287 @default.
- W2890766902 hasRelatedWork W2293457016 @default.
- W2890766902 hasRelatedWork W2351428524 @default.
- W2890766902 hasRelatedWork W2369308426 @default.
- W2890766902 hasRelatedWork W2789919619 @default.
- W2890766902 hasRelatedWork W3156291593 @default.
- W2890766902 hasRelatedWork W3169305685 @default.
- W2890766902 hasRelatedWork W4220812973 @default.
- W2890766902 hasRelatedWork W1551406738 @default.
- W2890766902 hasRelatedWork W2610387714 @default.
- W2890766902 isParatext "false" @default.
- W2890766902 isRetracted "false" @default.
- W2890766902 magId "2890766902" @default.
- W2890766902 workType "article" @default.