Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383567105> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4383567105 endingPage "138" @default.
- W4383567105 startingPage "127" @default.
- W4383567105 abstract "Existing hardware-aware pruning methods for deep neural networks do not take the uncertain execution environment of low-end hardware into consideration. That makes those methods unreliable, since the hardware environments they used for evaluating the pruned models contain uncertainty and thus the performance values contain noise. To deal with this problem, this paper proposes noise-tolerant hardware-aware pruning, i.e., NT-HP. It uses a population-based idea to iteratively generate pruned models. Each pruned model is sent to realistic low-end hardware for performance evaluations. For the noisy values of performance indicators collected from hardware, a threshold for comparison is set, where only the pruned models with significantly better performances are kept in the next generation. Our experimental results show that with the noise-tolerant technique involved, NT-HP can get better pruned models in the uncertain execution environment of low-end hardware." @default.
- W4383567105 created "2023-07-08" @default.
- W4383567105 creator A5014106677 @default.
- W4383567105 creator A5014258107 @default.
- W4383567105 creator A5016856595 @default.
- W4383567105 creator A5017769188 @default.
- W4383567105 creator A5064548129 @default.
- W4383567105 creator A5066242163 @default.
- W4383567105 creator A5069994888 @default.
- W4383567105 creator A5088168239 @default.
- W4383567105 date "2023-01-01" @default.
- W4383567105 modified "2023-09-23" @default.
- W4383567105 title "Noise-Tolerant Hardware-Aware Pruning for Deep Neural Networks" @default.
- W4383567105 cites W2124290836 @default.
- W4383567105 cites W2886851211 @default.
- W4383567105 cites W2890590696 @default.
- W4383567105 cites W2928560789 @default.
- W4383567105 cites W2962861284 @default.
- W4383567105 cites W2964131837 @default.
- W4383567105 cites W2980137827 @default.
- W4383567105 cites W3033114334 @default.
- W4383567105 cites W3160783538 @default.
- W4383567105 cites W3167436278 @default.
- W4383567105 cites W3183695018 @default.
- W4383567105 cites W3186871399 @default.
- W4383567105 cites W3198149465 @default.
- W4383567105 cites W4244330903 @default.
- W4383567105 cites W4296618678 @default.
- W4383567105 cites W4320002812 @default.
- W4383567105 doi "https://doi.org/10.1007/978-3-031-36625-3_11" @default.
- W4383567105 hasPublicationYear "2023" @default.
- W4383567105 type Work @default.
- W4383567105 citedByCount "0" @default.
- W4383567105 crossrefType "book-chapter" @default.
- W4383567105 hasAuthorship W4383567105A5014106677 @default.
- W4383567105 hasAuthorship W4383567105A5014258107 @default.
- W4383567105 hasAuthorship W4383567105A5016856595 @default.
- W4383567105 hasAuthorship W4383567105A5017769188 @default.
- W4383567105 hasAuthorship W4383567105A5064548129 @default.
- W4383567105 hasAuthorship W4383567105A5066242163 @default.
- W4383567105 hasAuthorship W4383567105A5069994888 @default.
- W4383567105 hasAuthorship W4383567105A5088168239 @default.
- W4383567105 hasConcept C108010975 @default.
- W4383567105 hasConcept C113775141 @default.
- W4383567105 hasConcept C115961682 @default.
- W4383567105 hasConcept C144024400 @default.
- W4383567105 hasConcept C149923435 @default.
- W4383567105 hasConcept C154945302 @default.
- W4383567105 hasConcept C177264268 @default.
- W4383567105 hasConcept C199360897 @default.
- W4383567105 hasConcept C2908647359 @default.
- W4383567105 hasConcept C2984842247 @default.
- W4383567105 hasConcept C41008148 @default.
- W4383567105 hasConcept C50644808 @default.
- W4383567105 hasConcept C6557445 @default.
- W4383567105 hasConcept C86803240 @default.
- W4383567105 hasConcept C9390403 @default.
- W4383567105 hasConcept C99498987 @default.
- W4383567105 hasConceptScore W4383567105C108010975 @default.
- W4383567105 hasConceptScore W4383567105C113775141 @default.
- W4383567105 hasConceptScore W4383567105C115961682 @default.
- W4383567105 hasConceptScore W4383567105C144024400 @default.
- W4383567105 hasConceptScore W4383567105C149923435 @default.
- W4383567105 hasConceptScore W4383567105C154945302 @default.
- W4383567105 hasConceptScore W4383567105C177264268 @default.
- W4383567105 hasConceptScore W4383567105C199360897 @default.
- W4383567105 hasConceptScore W4383567105C2908647359 @default.
- W4383567105 hasConceptScore W4383567105C2984842247 @default.
- W4383567105 hasConceptScore W4383567105C41008148 @default.
- W4383567105 hasConceptScore W4383567105C50644808 @default.
- W4383567105 hasConceptScore W4383567105C6557445 @default.
- W4383567105 hasConceptScore W4383567105C86803240 @default.
- W4383567105 hasConceptScore W4383567105C9390403 @default.
- W4383567105 hasConceptScore W4383567105C99498987 @default.
- W4383567105 hasLocation W43835671051 @default.
- W4383567105 hasOpenAccess W4383567105 @default.
- W4383567105 hasPrimaryLocation W43835671051 @default.
- W4383567105 hasRelatedWork W1490470283 @default.
- W4383567105 hasRelatedWork W1967514496 @default.
- W4383567105 hasRelatedWork W2904876938 @default.
- W4383567105 hasRelatedWork W2969797940 @default.
- W4383567105 hasRelatedWork W3098411449 @default.
- W4383567105 hasRelatedWork W3104849992 @default.
- W4383567105 hasRelatedWork W3126221229 @default.
- W4383567105 hasRelatedWork W3177201542 @default.
- W4383567105 hasRelatedWork W3200578280 @default.
- W4383567105 hasRelatedWork W4322759334 @default.
- W4383567105 isParatext "false" @default.
- W4383567105 isRetracted "false" @default.
- W4383567105 workType "book-chapter" @default.