Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951322342> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2951322342 endingPage "052003" @default.
- W2951322342 startingPage "052003" @default.
- W2951322342 abstract "Abstract Deep networks have achieved great success in many areas in recent years. However, with the increasing sophistication of deep neural networks (DNNs), the memory consumption and computational cost expand exponentially, greatly hindering their application in mobile devices and other limited resources. Therefore, there is impending necessity to consider model compression and acceleration without affecting the inference accuracy. In this paper, we review the recent popular techniques for compressing and accelerating deep networks. Those methods could be broadly divided into four categories: parameter pruning and sharing, low rank approximation, sparse regularization constraints and network weight low-bit quantization. The advantages and disadvantages of different compression and acceleration methods are also described in detail, other types of approach are also introduced in our paper, and future prospects for the field are given finally." @default.
- W2951322342 created "2019-06-27" @default.
- W2951322342 creator A5013559313 @default.
- W2951322342 creator A5019674440 @default.
- W2951322342 creator A5021293751 @default.
- W2951322342 date "2019-06-01" @default.
- W2951322342 modified "2023-09-26" @default.
- W2951322342 title "A Survey of Related Research on Compression and Acceleration of Deep Neural Networks" @default.
- W2951322342 cites W1986931325 @default.
- W2951322342 cites W1992348535 @default.
- W2951322342 cites W2129131372 @default.
- W2951322342 cites W2138019504 @default.
- W2951322342 cites W2159514083 @default.
- W2951322342 cites W2300242332 @default.
- W2951322342 cites W2913340405 @default.
- W2951322342 cites W3105329799 @default.
- W2951322342 cites W4234698323 @default.
- W2951322342 cites W4250955649 @default.
- W2951322342 cites W4375869345 @default.
- W2951322342 cites W566555209 @default.
- W2951322342 doi "https://doi.org/10.1088/1742-6596/1213/5/052003" @default.
- W2951322342 hasPublicationYear "2019" @default.
- W2951322342 type Work @default.
- W2951322342 sameAs 2951322342 @default.
- W2951322342 citedByCount "4" @default.
- W2951322342 countsByYear W29513223422020 @default.
- W2951322342 countsByYear W29513223422021 @default.
- W2951322342 countsByYear W29513223422022 @default.
- W2951322342 crossrefType "journal-article" @default.
- W2951322342 hasAuthorship W2951322342A5013559313 @default.
- W2951322342 hasAuthorship W2951322342A5019674440 @default.
- W2951322342 hasAuthorship W2951322342A5021293751 @default.
- W2951322342 hasBestOaLocation W29513223421 @default.
- W2951322342 hasConcept C113775141 @default.
- W2951322342 hasConcept C11413529 @default.
- W2951322342 hasConcept C117896860 @default.
- W2951322342 hasConcept C119857082 @default.
- W2951322342 hasConcept C121332964 @default.
- W2951322342 hasConcept C154945302 @default.
- W2951322342 hasConcept C202444582 @default.
- W2951322342 hasConcept C2776135515 @default.
- W2951322342 hasConcept C2776214188 @default.
- W2951322342 hasConcept C28855332 @default.
- W2951322342 hasConcept C2984842247 @default.
- W2951322342 hasConcept C33923547 @default.
- W2951322342 hasConcept C41008148 @default.
- W2951322342 hasConcept C50644808 @default.
- W2951322342 hasConcept C74650414 @default.
- W2951322342 hasConcept C9652623 @default.
- W2951322342 hasConceptScore W2951322342C113775141 @default.
- W2951322342 hasConceptScore W2951322342C11413529 @default.
- W2951322342 hasConceptScore W2951322342C117896860 @default.
- W2951322342 hasConceptScore W2951322342C119857082 @default.
- W2951322342 hasConceptScore W2951322342C121332964 @default.
- W2951322342 hasConceptScore W2951322342C154945302 @default.
- W2951322342 hasConceptScore W2951322342C202444582 @default.
- W2951322342 hasConceptScore W2951322342C2776135515 @default.
- W2951322342 hasConceptScore W2951322342C2776214188 @default.
- W2951322342 hasConceptScore W2951322342C28855332 @default.
- W2951322342 hasConceptScore W2951322342C2984842247 @default.
- W2951322342 hasConceptScore W2951322342C33923547 @default.
- W2951322342 hasConceptScore W2951322342C41008148 @default.
- W2951322342 hasConceptScore W2951322342C50644808 @default.
- W2951322342 hasConceptScore W2951322342C74650414 @default.
- W2951322342 hasConceptScore W2951322342C9652623 @default.
- W2951322342 hasIssue "5" @default.
- W2951322342 hasLocation W29513223421 @default.
- W2951322342 hasOpenAccess W2951322342 @default.
- W2951322342 hasPrimaryLocation W29513223421 @default.
- W2951322342 hasRelatedWork W2798504536 @default.
- W2951322342 hasRelatedWork W2803935332 @default.
- W2951322342 hasRelatedWork W2949701228 @default.
- W2951322342 hasRelatedWork W2971667683 @default.
- W2951322342 hasRelatedWork W3099092507 @default.
- W2951322342 hasRelatedWork W3184547836 @default.
- W2951322342 hasRelatedWork W3195170785 @default.
- W2951322342 hasRelatedWork W4290804603 @default.
- W2951322342 hasRelatedWork W4310823283 @default.
- W2951322342 hasRelatedWork W4322616423 @default.
- W2951322342 hasVolume "1213" @default.
- W2951322342 isParatext "false" @default.
- W2951322342 isRetracted "false" @default.
- W2951322342 magId "2951322342" @default.
- W2951322342 workType "article" @default.