Matches in SemOpenAlex for { <https://semopenalex.org/work/W2564444812> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2564444812 abstract "Training state-of-the-art deep neural networks is computationally expensive and time consuming. In this paper we present a method that can reduce training time while at the same time maintain nearly the same accuracy as traditional training approaches. This allows for faster experimentation and better use of computational resource. Our method extends the well-known dropout technique by randomly removing entire network layers instead of individual neurons during training and hence reducing the number of expensive convolution operations needed per training iteration. We conduct experiments on object recognition using the CIFAR10 and ImageNet datasets to demonstrate the effectiveness of our approach. Our results show that we can train residual convolutional neural networks (ResNets) 17.5% faster with only 0.4% decrease in error rate or 34.1% faster with 1.3% increase in error rate compared to a baseline model. We also perform analysis on the trade-off between testing accuracy and training speedup as a function of the drop-out ratio." @default.
- W2564444812 created "2017-01-06" @default.
- W2564444812 creator A5004026570 @default.
- W2564444812 creator A5042584066 @default.
- W2564444812 date "2016-11-01" @default.
- W2564444812 modified "2023-09-26" @default.
- W2564444812 title "Depth Dropout: Efficient Training of Residual Convolutional Neural Networks" @default.
- W2564444812 cites W1836465849 @default.
- W2564444812 cites W1904365287 @default.
- W2564444812 cites W2097117768 @default.
- W2564444812 cites W2108598243 @default.
- W2564444812 cites W2117539524 @default.
- W2564444812 cites W2155893237 @default.
- W2564444812 cites W2163605009 @default.
- W2564444812 cites W2331143823 @default.
- W2564444812 cites W2962835968 @default.
- W2564444812 doi "https://doi.org/10.1109/dicta.2016.7797032" @default.
- W2564444812 hasPublicationYear "2016" @default.
- W2564444812 type Work @default.
- W2564444812 sameAs 2564444812 @default.
- W2564444812 citedByCount "10" @default.
- W2564444812 countsByYear W25644448122017 @default.
- W2564444812 countsByYear W25644448122018 @default.
- W2564444812 countsByYear W25644448122019 @default.
- W2564444812 countsByYear W25644448122020 @default.
- W2564444812 countsByYear W25644448122021 @default.
- W2564444812 crossrefType "proceedings-article" @default.
- W2564444812 hasAuthorship W2564444812A5004026570 @default.
- W2564444812 hasAuthorship W2564444812A5042584066 @default.
- W2564444812 hasConcept C108583219 @default.
- W2564444812 hasConcept C11413529 @default.
- W2564444812 hasConcept C119857082 @default.
- W2564444812 hasConcept C121332964 @default.
- W2564444812 hasConcept C153180895 @default.
- W2564444812 hasConcept C153294291 @default.
- W2564444812 hasConcept C154945302 @default.
- W2564444812 hasConcept C155512373 @default.
- W2564444812 hasConcept C173608175 @default.
- W2564444812 hasConcept C2776145597 @default.
- W2564444812 hasConcept C2777211547 @default.
- W2564444812 hasConcept C40969351 @default.
- W2564444812 hasConcept C41008148 @default.
- W2564444812 hasConcept C45347329 @default.
- W2564444812 hasConcept C50644808 @default.
- W2564444812 hasConcept C68339613 @default.
- W2564444812 hasConcept C81363708 @default.
- W2564444812 hasConceptScore W2564444812C108583219 @default.
- W2564444812 hasConceptScore W2564444812C11413529 @default.
- W2564444812 hasConceptScore W2564444812C119857082 @default.
- W2564444812 hasConceptScore W2564444812C121332964 @default.
- W2564444812 hasConceptScore W2564444812C153180895 @default.
- W2564444812 hasConceptScore W2564444812C153294291 @default.
- W2564444812 hasConceptScore W2564444812C154945302 @default.
- W2564444812 hasConceptScore W2564444812C155512373 @default.
- W2564444812 hasConceptScore W2564444812C173608175 @default.
- W2564444812 hasConceptScore W2564444812C2776145597 @default.
- W2564444812 hasConceptScore W2564444812C2777211547 @default.
- W2564444812 hasConceptScore W2564444812C40969351 @default.
- W2564444812 hasConceptScore W2564444812C41008148 @default.
- W2564444812 hasConceptScore W2564444812C45347329 @default.
- W2564444812 hasConceptScore W2564444812C50644808 @default.
- W2564444812 hasConceptScore W2564444812C68339613 @default.
- W2564444812 hasConceptScore W2564444812C81363708 @default.
- W2564444812 hasLocation W25644448121 @default.
- W2564444812 hasOpenAccess W2564444812 @default.
- W2564444812 hasPrimaryLocation W25644448121 @default.
- W2564444812 hasRelatedWork W2160082767 @default.
- W2564444812 hasRelatedWork W2475884125 @default.
- W2564444812 hasRelatedWork W2618541429 @default.
- W2564444812 hasRelatedWork W2765384635 @default.
- W2564444812 hasRelatedWork W2803858435 @default.
- W2564444812 hasRelatedWork W2900628392 @default.
- W2564444812 hasRelatedWork W2908596665 @default.
- W2564444812 hasRelatedWork W2946529874 @default.
- W2564444812 hasRelatedWork W2955436611 @default.
- W2564444812 hasRelatedWork W2963521187 @default.
- W2564444812 hasRelatedWork W2963617102 @default.
- W2564444812 hasRelatedWork W2963919236 @default.
- W2564444812 hasRelatedWork W3005165565 @default.
- W2564444812 hasRelatedWork W3090288569 @default.
- W2564444812 hasRelatedWork W3107352446 @default.
- W2564444812 hasRelatedWork W3112603106 @default.
- W2564444812 hasRelatedWork W3119699820 @default.
- W2564444812 hasRelatedWork W3133313904 @default.
- W2564444812 hasRelatedWork W3158750136 @default.
- W2564444812 hasRelatedWork W3163244872 @default.
- W2564444812 isParatext "false" @default.
- W2564444812 isRetracted "false" @default.
- W2564444812 magId "2564444812" @default.
- W2564444812 workType "article" @default.