Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994266908> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W2994266908 endingPage "455" @default.
- W2994266908 startingPage "448" @default.
- W2994266908 abstract "Convolutional Neural Network (CNN) is one of the widely used deep learning frameworks in image classification, target detection and object recognition domains. Because of the complexity of the network structures, CNNs usually contains a large number of layers and channels, which makes algorithm time-consuming. Using existing CNN architectures to solve specific problems usually leads to many redundant parameters. This paper introduces an approach based on the distinctiveness rules to prune both fully connected layers and filters of the baseline network. We experiment with different pruning means to prune multiple layer neurons and filters by the distinctiveness rules and evaluate the performance of the approach. We also discuss the influence of threshold on the selection of redundant neurons in pattern space and trade-off network scale and accuracy. The result shows using the approach will not change the structure of the baseline network and 32 filters and 161 neurons are removed. The accuracy of the pruned network reaches 80.5% compared with 87% of the original model." @default.
- W2994266908 created "2019-12-13" @default.
- W2994266908 creator A5063366658 @default.
- W2994266908 creator A5068595048 @default.
- W2994266908 date "2019-01-01" @default.
- W2994266908 modified "2023-10-14" @default.
- W2994266908 title "Pruning Convolutional Neural Network with Distinctiveness Approach" @default.
- W2994266908 cites W2012245169 @default.
- W2994266908 cites W2027665223 @default.
- W2994266908 cites W2097117768 @default.
- W2994266908 cites W2097533491 @default.
- W2994266908 cites W2112796928 @default.
- W2994266908 cites W2194775991 @default.
- W2994266908 cites W2734358244 @default.
- W2994266908 cites W2963125010 @default.
- W2994266908 cites W2963140066 @default.
- W2994266908 doi "https://doi.org/10.1007/978-3-030-36802-9_48" @default.
- W2994266908 hasPublicationYear "2019" @default.
- W2994266908 type Work @default.
- W2994266908 sameAs 2994266908 @default.
- W2994266908 citedByCount "1" @default.
- W2994266908 countsByYear W29942669082023 @default.
- W2994266908 crossrefType "book-chapter" @default.
- W2994266908 hasAuthorship W2994266908A5063366658 @default.
- W2994266908 hasAuthorship W2994266908A5068595048 @default.
- W2994266908 hasConcept C108010975 @default.
- W2994266908 hasConcept C154945302 @default.
- W2994266908 hasConcept C15744967 @default.
- W2994266908 hasConcept C41008148 @default.
- W2994266908 hasConcept C47385372 @default.
- W2994266908 hasConcept C542102704 @default.
- W2994266908 hasConcept C59822182 @default.
- W2994266908 hasConcept C81363708 @default.
- W2994266908 hasConcept C86803240 @default.
- W2994266908 hasConceptScore W2994266908C108010975 @default.
- W2994266908 hasConceptScore W2994266908C154945302 @default.
- W2994266908 hasConceptScore W2994266908C15744967 @default.
- W2994266908 hasConceptScore W2994266908C41008148 @default.
- W2994266908 hasConceptScore W2994266908C47385372 @default.
- W2994266908 hasConceptScore W2994266908C542102704 @default.
- W2994266908 hasConceptScore W2994266908C59822182 @default.
- W2994266908 hasConceptScore W2994266908C81363708 @default.
- W2994266908 hasConceptScore W2994266908C86803240 @default.
- W2994266908 hasLocation W29942669081 @default.
- W2994266908 hasOpenAccess W2994266908 @default.
- W2994266908 hasPrimaryLocation W29942669081 @default.
- W2994266908 hasRelatedWork W2521062615 @default.
- W2994266908 hasRelatedWork W2735477435 @default.
- W2994266908 hasRelatedWork W2748454020 @default.
- W2994266908 hasRelatedWork W2901465038 @default.
- W2994266908 hasRelatedWork W2998526951 @default.
- W2994266908 hasRelatedWork W3090822330 @default.
- W2994266908 hasRelatedWork W3119610945 @default.
- W2994266908 hasRelatedWork W3181746755 @default.
- W2994266908 hasRelatedWork W4294334363 @default.
- W2994266908 hasRelatedWork W4321392785 @default.
- W2994266908 isParatext "false" @default.
- W2994266908 isRetracted "false" @default.
- W2994266908 magId "2994266908" @default.
- W2994266908 workType "book-chapter" @default.