Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212348580> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3212348580 abstract "To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bounded by the designated constraint. Our proposed method increases the compression rate, reduces the training time and reduces the number of hyper-parameters compared with state-of-the-art ADMM-based hard constraint method." @default.
- W3212348580 created "2021-11-22" @default.
- W3212348580 creator A5016070401 @default.
- W3212348580 creator A5016139042 @default.
- W3212348580 creator A5025596795 @default.
- W3212348580 creator A5030060072 @default.
- W3212348580 creator A5037655503 @default.
- W3212348580 creator A5057639149 @default.
- W3212348580 creator A5070625162 @default.
- W3212348580 date "2021-12-05" @default.
- W3212348580 modified "2023-10-13" @default.
- W3212348580 title "A Unified DNN Weight Pruning Framework Using Reweighted Optimization Methods" @default.
- W3212348580 cites W2107861471 @default.
- W3212348580 cites W2138019504 @default.
- W3212348580 cites W2160815625 @default.
- W3212348580 cites W2194775991 @default.
- W3212348580 cites W2928560789 @default.
- W3212348580 cites W2945335799 @default.
- W3212348580 cites W2963163009 @default.
- W3212348580 cites W2998342322 @default.
- W3212348580 cites W3042215422 @default.
- W3212348580 cites W4292363360 @default.
- W3212348580 doi "https://doi.org/10.1109/dac18074.2021.9586152" @default.
- W3212348580 hasPublicationYear "2021" @default.
- W3212348580 type Work @default.
- W3212348580 sameAs 3212348580 @default.
- W3212348580 citedByCount "12" @default.
- W3212348580 countsByYear W32123485802022 @default.
- W3212348580 countsByYear W32123485802023 @default.
- W3212348580 crossrefType "proceedings-article" @default.
- W3212348580 hasAuthorship W3212348580A5016070401 @default.
- W3212348580 hasAuthorship W3212348580A5016139042 @default.
- W3212348580 hasAuthorship W3212348580A5025596795 @default.
- W3212348580 hasAuthorship W3212348580A5030060072 @default.
- W3212348580 hasAuthorship W3212348580A5037655503 @default.
- W3212348580 hasAuthorship W3212348580A5057639149 @default.
- W3212348580 hasAuthorship W3212348580A5070625162 @default.
- W3212348580 hasConcept C108010975 @default.
- W3212348580 hasConcept C11413529 @default.
- W3212348580 hasConcept C126255220 @default.
- W3212348580 hasConcept C134306372 @default.
- W3212348580 hasConcept C147764199 @default.
- W3212348580 hasConcept C154945302 @default.
- W3212348580 hasConcept C199360897 @default.
- W3212348580 hasConcept C2524010 @default.
- W3212348580 hasConcept C2776036281 @default.
- W3212348580 hasConcept C2776135515 @default.
- W3212348580 hasConcept C2984842247 @default.
- W3212348580 hasConcept C33923547 @default.
- W3212348580 hasConcept C34388435 @default.
- W3212348580 hasConcept C41008148 @default.
- W3212348580 hasConcept C45374587 @default.
- W3212348580 hasConcept C50644808 @default.
- W3212348580 hasConcept C6557445 @default.
- W3212348580 hasConcept C86803240 @default.
- W3212348580 hasConceptScore W3212348580C108010975 @default.
- W3212348580 hasConceptScore W3212348580C11413529 @default.
- W3212348580 hasConceptScore W3212348580C126255220 @default.
- W3212348580 hasConceptScore W3212348580C134306372 @default.
- W3212348580 hasConceptScore W3212348580C147764199 @default.
- W3212348580 hasConceptScore W3212348580C154945302 @default.
- W3212348580 hasConceptScore W3212348580C199360897 @default.
- W3212348580 hasConceptScore W3212348580C2524010 @default.
- W3212348580 hasConceptScore W3212348580C2776036281 @default.
- W3212348580 hasConceptScore W3212348580C2776135515 @default.
- W3212348580 hasConceptScore W3212348580C2984842247 @default.
- W3212348580 hasConceptScore W3212348580C33923547 @default.
- W3212348580 hasConceptScore W3212348580C34388435 @default.
- W3212348580 hasConceptScore W3212348580C41008148 @default.
- W3212348580 hasConceptScore W3212348580C45374587 @default.
- W3212348580 hasConceptScore W3212348580C50644808 @default.
- W3212348580 hasConceptScore W3212348580C6557445 @default.
- W3212348580 hasConceptScore W3212348580C86803240 @default.
- W3212348580 hasFunder F4320306076 @default.
- W3212348580 hasLocation W32123485801 @default.
- W3212348580 hasOpenAccess W3212348580 @default.
- W3212348580 hasPrimaryLocation W32123485801 @default.
- W3212348580 hasRelatedWork W1490470283 @default.
- W3212348580 hasRelatedWork W2111622281 @default.
- W3212348580 hasRelatedWork W2901381533 @default.
- W3212348580 hasRelatedWork W2917246213 @default.
- W3212348580 hasRelatedWork W2950717866 @default.
- W3212348580 hasRelatedWork W3015657140 @default.
- W3212348580 hasRelatedWork W3124987929 @default.
- W3212348580 hasRelatedWork W3161108526 @default.
- W3212348580 hasRelatedWork W4307314844 @default.
- W3212348580 hasRelatedWork W3093303313 @default.
- W3212348580 isParatext "false" @default.
- W3212348580 isRetracted "false" @default.
- W3212348580 magId "3212348580" @default.
- W3212348580 workType "article" @default.