Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295048089> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4295048089 endingPage "36358" @default.
- W4295048089 startingPage "36358" @default.
- W4295048089 abstract "In this work, for the first time to the best of our knowledge, we introduce the iterative pruning technique into the transfer learning (TL) of neural network equalizers (NNE) deployed in optical links with different length. For the purpose of time saving during the training period of NNE, TL migrates the NNE parameters which have been already trained on the source link to the newly-routed link (the target link), which has been proved to outperform the training initialized with the random state. Based on simulations, we proved that iterative pruning technique could further enhance the convergence speed during TL between the source and target links. Moreover, we quantitatively investigate the marginal effects of pruned threshold and pruned span on the convergence performance in various transmission distance scenarios. In addition, we observed a trade-off between performance stability and complexity of NNE, which requires to be optimized compromisingly by choosing an appropriate equalizer scale." @default.
- W4295048089 created "2022-09-09" @default.
- W4295048089 creator A5064845359 @default.
- W4295048089 creator A5071339229 @default.
- W4295048089 creator A5075221489 @default.
- W4295048089 creator A5086412508 @default.
- W4295048089 date "2022-09-20" @default.
- W4295048089 modified "2023-10-01" @default.
- W4295048089 title "Optimizations and investigations for transfer learning of iteratively pruned neural network equalizers for data center networking" @default.
- W4295048089 cites W2014015061 @default.
- W4295048089 cites W2058513979 @default.
- W4295048089 cites W2339027434 @default.
- W4295048089 cites W2345281323 @default.
- W4295048089 cites W2755167349 @default.
- W4295048089 cites W2783323148 @default.
- W4295048089 cites W2783586874 @default.
- W4295048089 cites W2904858595 @default.
- W4295048089 cites W2963179464 @default.
- W4295048089 cites W2969803665 @default.
- W4295048089 cites W3005557053 @default.
- W4295048089 cites W3102321168 @default.
- W4295048089 cites W3107662238 @default.
- W4295048089 cites W3113766111 @default.
- W4295048089 cites W3155320667 @default.
- W4295048089 cites W3197509838 @default.
- W4295048089 cites W3213613600 @default.
- W4295048089 cites W4282044714 @default.
- W4295048089 doi "https://doi.org/10.1364/oe.468716" @default.
- W4295048089 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36258565" @default.
- W4295048089 hasPublicationYear "2022" @default.
- W4295048089 type Work @default.
- W4295048089 citedByCount "2" @default.
- W4295048089 countsByYear W42950480892023 @default.
- W4295048089 crossrefType "journal-article" @default.
- W4295048089 hasAuthorship W4295048089A5064845359 @default.
- W4295048089 hasAuthorship W4295048089A5071339229 @default.
- W4295048089 hasAuthorship W4295048089A5075221489 @default.
- W4295048089 hasAuthorship W4295048089A5086412508 @default.
- W4295048089 hasBestOaLocation W42950480891 @default.
- W4295048089 hasConcept C108010975 @default.
- W4295048089 hasConcept C112972136 @default.
- W4295048089 hasConcept C11413529 @default.
- W4295048089 hasConcept C119857082 @default.
- W4295048089 hasConcept C154945302 @default.
- W4295048089 hasConcept C162324750 @default.
- W4295048089 hasConcept C173608175 @default.
- W4295048089 hasConcept C2776175482 @default.
- W4295048089 hasConcept C2777303404 @default.
- W4295048089 hasConcept C31258907 @default.
- W4295048089 hasConcept C41008148 @default.
- W4295048089 hasConcept C50522688 @default.
- W4295048089 hasConcept C50644808 @default.
- W4295048089 hasConcept C557945733 @default.
- W4295048089 hasConcept C6557445 @default.
- W4295048089 hasConcept C761482 @default.
- W4295048089 hasConcept C76155785 @default.
- W4295048089 hasConcept C86803240 @default.
- W4295048089 hasConceptScore W4295048089C108010975 @default.
- W4295048089 hasConceptScore W4295048089C112972136 @default.
- W4295048089 hasConceptScore W4295048089C11413529 @default.
- W4295048089 hasConceptScore W4295048089C119857082 @default.
- W4295048089 hasConceptScore W4295048089C154945302 @default.
- W4295048089 hasConceptScore W4295048089C162324750 @default.
- W4295048089 hasConceptScore W4295048089C173608175 @default.
- W4295048089 hasConceptScore W4295048089C2776175482 @default.
- W4295048089 hasConceptScore W4295048089C2777303404 @default.
- W4295048089 hasConceptScore W4295048089C31258907 @default.
- W4295048089 hasConceptScore W4295048089C41008148 @default.
- W4295048089 hasConceptScore W4295048089C50522688 @default.
- W4295048089 hasConceptScore W4295048089C50644808 @default.
- W4295048089 hasConceptScore W4295048089C557945733 @default.
- W4295048089 hasConceptScore W4295048089C6557445 @default.
- W4295048089 hasConceptScore W4295048089C761482 @default.
- W4295048089 hasConceptScore W4295048089C76155785 @default.
- W4295048089 hasConceptScore W4295048089C86803240 @default.
- W4295048089 hasFunder F4320321001 @default.
- W4295048089 hasFunder F4320335777 @default.
- W4295048089 hasIssue "20" @default.
- W4295048089 hasLocation W42950480891 @default.
- W4295048089 hasLocation W42950480892 @default.
- W4295048089 hasOpenAccess W4295048089 @default.
- W4295048089 hasPrimaryLocation W42950480891 @default.
- W4295048089 hasRelatedWork W1994993486 @default.
- W4295048089 hasRelatedWork W2356745231 @default.
- W4295048089 hasRelatedWork W2359432571 @default.
- W4295048089 hasRelatedWork W2363683157 @default.
- W4295048089 hasRelatedWork W2364074001 @default.
- W4295048089 hasRelatedWork W2383503060 @default.
- W4295048089 hasRelatedWork W2387284662 @default.
- W4295048089 hasRelatedWork W2905443263 @default.
- W4295048089 hasRelatedWork W2961085424 @default.
- W4295048089 hasRelatedWork W4287113599 @default.
- W4295048089 hasVolume "30" @default.
- W4295048089 isParatext "false" @default.
- W4295048089 isRetracted "false" @default.
- W4295048089 workType "article" @default.