Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046382698> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3046382698 abstract "In deep neural networks (DNNs), by removing unnecessary subnetworks can reduce neural network computing redundancy, or by extracting sub-networks with features can explain how the DNN works. In this paper, we propose a neural network structure search algorithm based on evolutionary algorithm (EA) for DNN pruning and features separation, especially considering the evolutionary efficiency issues and individual evaluation. We get verified on the CIFAR-10 (C10) and CIFAR-100 (C100) datasets. With the classification accuracy with a variation of +/- 1% as the precondition, our method significantly reduces the amount of calculations." @default.
- W3046382698 created "2020-08-07" @default.
- W3046382698 creator A5015860750 @default.
- W3046382698 creator A5041989556 @default.
- W3046382698 creator A5058381808 @default.
- W3046382698 creator A5071445293 @default.
- W3046382698 creator A5085473287 @default.
- W3046382698 creator A5091509968 @default.
- W3046382698 date "2020-07-08" @default.
- W3046382698 modified "2023-09-24" @default.
- W3046382698 title "Evolutionary neural network structure search for DNN pruning and features separation" @default.
- W3046382698 cites W2928560789 @default.
- W3046382698 cites W4229494842 @default.
- W3046382698 doi "https://doi.org/10.1145/3377929.3389970" @default.
- W3046382698 hasPublicationYear "2020" @default.
- W3046382698 type Work @default.
- W3046382698 sameAs 3046382698 @default.
- W3046382698 citedByCount "1" @default.
- W3046382698 countsByYear W30463826982023 @default.
- W3046382698 crossrefType "proceedings-article" @default.
- W3046382698 hasAuthorship W3046382698A5015860750 @default.
- W3046382698 hasAuthorship W3046382698A5041989556 @default.
- W3046382698 hasAuthorship W3046382698A5058381808 @default.
- W3046382698 hasAuthorship W3046382698A5071445293 @default.
- W3046382698 hasAuthorship W3046382698A5085473287 @default.
- W3046382698 hasAuthorship W3046382698A5091509968 @default.
- W3046382698 hasConcept C105902424 @default.
- W3046382698 hasConcept C108010975 @default.
- W3046382698 hasConcept C119857082 @default.
- W3046382698 hasConcept C153180895 @default.
- W3046382698 hasConcept C154945302 @default.
- W3046382698 hasConcept C2776061190 @default.
- W3046382698 hasConcept C41008148 @default.
- W3046382698 hasConcept C50644808 @default.
- W3046382698 hasConcept C6557445 @default.
- W3046382698 hasConcept C86803240 @default.
- W3046382698 hasConceptScore W3046382698C105902424 @default.
- W3046382698 hasConceptScore W3046382698C108010975 @default.
- W3046382698 hasConceptScore W3046382698C119857082 @default.
- W3046382698 hasConceptScore W3046382698C153180895 @default.
- W3046382698 hasConceptScore W3046382698C154945302 @default.
- W3046382698 hasConceptScore W3046382698C2776061190 @default.
- W3046382698 hasConceptScore W3046382698C41008148 @default.
- W3046382698 hasConceptScore W3046382698C50644808 @default.
- W3046382698 hasConceptScore W3046382698C6557445 @default.
- W3046382698 hasConceptScore W3046382698C86803240 @default.
- W3046382698 hasLocation W30463826981 @default.
- W3046382698 hasOpenAccess W3046382698 @default.
- W3046382698 hasPrimaryLocation W30463826981 @default.
- W3046382698 hasRelatedWork W2961085424 @default.
- W3046382698 hasRelatedWork W3199608561 @default.
- W3046382698 hasRelatedWork W4229568052 @default.
- W3046382698 hasRelatedWork W4235367588 @default.
- W3046382698 hasRelatedWork W4237634094 @default.
- W3046382698 hasRelatedWork W4247102092 @default.
- W3046382698 hasRelatedWork W4286629047 @default.
- W3046382698 hasRelatedWork W4306674287 @default.
- W3046382698 hasRelatedWork W1629725936 @default.
- W3046382698 hasRelatedWork W4224009465 @default.
- W3046382698 isParatext "false" @default.
- W3046382698 isRetracted "false" @default.
- W3046382698 magId "3046382698" @default.
- W3046382698 workType "article" @default.