Matches in SemOpenAlex for { <https://semopenalex.org/work/W2261029130> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2261029130 abstract "While the current trend is to increase the depth of neural networks to increase their performance, the size of their training database has to grow accordingly. We notice an emergence of tremendous databases, although providing labels to build a training set still remains a very expensive task. We tackle the problem of selecting the samples to be labelled in an online fashion. In this paper, we present an active learning strategy based on query by committee and dropout technique to train a Convolutional Neural Network (CNN). We derive a commmittee of partial CNNs resulting from batchwise dropout runs on the initial CNN. We evaluate our active learning strategy for CNN on MNIST benchmark, showing in particular that selecting less than 30 % from the annotated database is enough to get similar error rate as using the full training set on MNIST. We also studied the robustness of our method against adversarial examples." @default.
- W2261029130 created "2016-06-24" @default.
- W2261029130 creator A5005307040 @default.
- W2261029130 creator A5009303951 @default.
- W2261029130 date "2015-11-19" @default.
- W2261029130 modified "2023-09-22" @default.
- W2261029130 title "QBDC: Query by dropout committee for training deep supervised architecture" @default.
- W2261029130 cites W1606347560 @default.
- W2261029130 cites W2163922914 @default.
- W2261029130 cites W2164370980 @default.
- W2261029130 hasPublicationYear "2015" @default.
- W2261029130 type Work @default.
- W2261029130 sameAs 2261029130 @default.
- W2261029130 citedByCount "5" @default.
- W2261029130 countsByYear W22610291302016 @default.
- W2261029130 countsByYear W22610291302018 @default.
- W2261029130 countsByYear W22610291302020 @default.
- W2261029130 countsByYear W22610291302021 @default.
- W2261029130 crossrefType "posted-content" @default.
- W2261029130 hasAuthorship W2261029130A5005307040 @default.
- W2261029130 hasAuthorship W2261029130A5009303951 @default.
- W2261029130 hasConcept C104317684 @default.
- W2261029130 hasConcept C108583219 @default.
- W2261029130 hasConcept C119857082 @default.
- W2261029130 hasConcept C127413603 @default.
- W2261029130 hasConcept C13280743 @default.
- W2261029130 hasConcept C154945302 @default.
- W2261029130 hasConcept C177264268 @default.
- W2261029130 hasConcept C185592680 @default.
- W2261029130 hasConcept C185798385 @default.
- W2261029130 hasConcept C190502265 @default.
- W2261029130 hasConcept C199360897 @default.
- W2261029130 hasConcept C201995342 @default.
- W2261029130 hasConcept C205649164 @default.
- W2261029130 hasConcept C2776145597 @default.
- W2261029130 hasConcept C2780451532 @default.
- W2261029130 hasConcept C41008148 @default.
- W2261029130 hasConcept C51632099 @default.
- W2261029130 hasConcept C55493867 @default.
- W2261029130 hasConcept C63479239 @default.
- W2261029130 hasConcept C81363708 @default.
- W2261029130 hasConceptScore W2261029130C104317684 @default.
- W2261029130 hasConceptScore W2261029130C108583219 @default.
- W2261029130 hasConceptScore W2261029130C119857082 @default.
- W2261029130 hasConceptScore W2261029130C127413603 @default.
- W2261029130 hasConceptScore W2261029130C13280743 @default.
- W2261029130 hasConceptScore W2261029130C154945302 @default.
- W2261029130 hasConceptScore W2261029130C177264268 @default.
- W2261029130 hasConceptScore W2261029130C185592680 @default.
- W2261029130 hasConceptScore W2261029130C185798385 @default.
- W2261029130 hasConceptScore W2261029130C190502265 @default.
- W2261029130 hasConceptScore W2261029130C199360897 @default.
- W2261029130 hasConceptScore W2261029130C201995342 @default.
- W2261029130 hasConceptScore W2261029130C205649164 @default.
- W2261029130 hasConceptScore W2261029130C2776145597 @default.
- W2261029130 hasConceptScore W2261029130C2780451532 @default.
- W2261029130 hasConceptScore W2261029130C41008148 @default.
- W2261029130 hasConceptScore W2261029130C51632099 @default.
- W2261029130 hasConceptScore W2261029130C55493867 @default.
- W2261029130 hasConceptScore W2261029130C63479239 @default.
- W2261029130 hasConceptScore W2261029130C81363708 @default.
- W2261029130 hasLocation W22610291301 @default.
- W2261029130 hasOpenAccess W2261029130 @default.
- W2261029130 hasPrimaryLocation W22610291301 @default.
- W2261029130 hasRelatedWork W2551435295 @default.
- W2261029130 hasRelatedWork W2565954814 @default.
- W2261029130 hasRelatedWork W2725245351 @default.
- W2261029130 hasRelatedWork W2740823339 @default.
- W2261029130 hasRelatedWork W2754977407 @default.
- W2261029130 hasRelatedWork W2766914988 @default.
- W2261029130 hasRelatedWork W2773354261 @default.
- W2261029130 hasRelatedWork W2774918944 @default.
- W2261029130 hasRelatedWork W2889565680 @default.
- W2261029130 hasRelatedWork W2900804847 @default.
- W2261029130 hasRelatedWork W2903158431 @default.
- W2261029130 hasRelatedWork W2952552241 @default.
- W2261029130 hasRelatedWork W2975264237 @default.
- W2261029130 hasRelatedWork W2990048693 @default.
- W2261029130 hasRelatedWork W2995746049 @default.
- W2261029130 hasRelatedWork W3022146783 @default.
- W2261029130 hasRelatedWork W3022176462 @default.
- W2261029130 hasRelatedWork W3107275157 @default.
- W2261029130 hasRelatedWork W3152890853 @default.
- W2261029130 hasRelatedWork W3195054941 @default.
- W2261029130 isParatext "false" @default.
- W2261029130 isRetracted "false" @default.
- W2261029130 magId "2261029130" @default.
- W2261029130 workType "article" @default.