Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950248853> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2950248853 abstract "We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point operations, making their deployment on smartphones and Internet-scale clusters problematic. The computation is dominated by the convolution operations in the lower layers of the model. We exploit the linear structure present within the convolutional filters to derive approximations that significantly reduce the required computation. Using large state-of-the-art models, we demonstrate we demonstrate speedups of convolutional layers on both CPU and GPU by a factor of 2x, while keeping the accuracy within 1% of the original model." @default.
- W2950248853 created "2019-06-27" @default.
- W2950248853 creator A5001226970 @default.
- W2950248853 creator A5045383831 @default.
- W2950248853 creator A5076651586 @default.
- W2950248853 creator A5086430646 @default.
- W2950248853 creator A5089960673 @default.
- W2950248853 date "2014-04-02" @default.
- W2950248853 modified "2023-09-27" @default.
- W2950248853 title "Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation" @default.
- W2950248853 cites W1904365287 @default.
- W2950248853 cites W1922123711 @default.
- W2950248853 cites W2002598080 @default.
- W2950248853 cites W2108598243 @default.
- W2950248853 cites W2141200610 @default.
- W2950248853 cites W2147860648 @default.
- W2950248853 cites W2950789693 @default.
- W2950248853 cites W2950967261 @default.
- W2950248853 cites W2952186574 @default.
- W2950248853 cites W2952899695 @default.
- W2950248853 cites W2963542991 @default.
- W2950248853 cites W587794757 @default.
- W2950248853 hasPublicationYear "2014" @default.
- W2950248853 type Work @default.
- W2950248853 sameAs 2950248853 @default.
- W2950248853 citedByCount "33" @default.
- W2950248853 countsByYear W29502488532014 @default.
- W2950248853 countsByYear W29502488532015 @default.
- W2950248853 countsByYear W29502488532016 @default.
- W2950248853 countsByYear W29502488532017 @default.
- W2950248853 countsByYear W29502488532018 @default.
- W2950248853 countsByYear W29502488532019 @default.
- W2950248853 countsByYear W29502488532020 @default.
- W2950248853 countsByYear W29502488532021 @default.
- W2950248853 crossrefType "posted-content" @default.
- W2950248853 hasAuthorship W2950248853A5001226970 @default.
- W2950248853 hasAuthorship W2950248853A5045383831 @default.
- W2950248853 hasAuthorship W2950248853A5076651586 @default.
- W2950248853 hasAuthorship W2950248853A5086430646 @default.
- W2950248853 hasAuthorship W2950248853A5089960673 @default.
- W2950248853 hasConcept C113775141 @default.
- W2950248853 hasConcept C11413529 @default.
- W2950248853 hasConcept C154945302 @default.
- W2950248853 hasConcept C165696696 @default.
- W2950248853 hasConcept C173608175 @default.
- W2950248853 hasConcept C2781238097 @default.
- W2950248853 hasConcept C38652104 @default.
- W2950248853 hasConcept C41008148 @default.
- W2950248853 hasConcept C45347329 @default.
- W2950248853 hasConcept C45374587 @default.
- W2950248853 hasConcept C48103436 @default.
- W2950248853 hasConcept C50644808 @default.
- W2950248853 hasConcept C81363708 @default.
- W2950248853 hasConceptScore W2950248853C113775141 @default.
- W2950248853 hasConceptScore W2950248853C11413529 @default.
- W2950248853 hasConceptScore W2950248853C154945302 @default.
- W2950248853 hasConceptScore W2950248853C165696696 @default.
- W2950248853 hasConceptScore W2950248853C173608175 @default.
- W2950248853 hasConceptScore W2950248853C2781238097 @default.
- W2950248853 hasConceptScore W2950248853C38652104 @default.
- W2950248853 hasConceptScore W2950248853C41008148 @default.
- W2950248853 hasConceptScore W2950248853C45347329 @default.
- W2950248853 hasConceptScore W2950248853C45374587 @default.
- W2950248853 hasConceptScore W2950248853C48103436 @default.
- W2950248853 hasConceptScore W2950248853C50644808 @default.
- W2950248853 hasConceptScore W2950248853C81363708 @default.
- W2950248853 hasLocation W29502488531 @default.
- W2950248853 hasOpenAccess W2950248853 @default.
- W2950248853 hasPrimaryLocation W29502488531 @default.
- W2950248853 hasRelatedWork W1686810756 @default.
- W2950248853 hasRelatedWork W1724438581 @default.
- W2950248853 hasRelatedWork W1845051632 @default.
- W2950248853 hasRelatedWork W1902934009 @default.
- W2950248853 hasRelatedWork W1996901117 @default.
- W2950248853 hasRelatedWork W2097117768 @default.
- W2950248853 hasRelatedWork W2104636679 @default.
- W2950248853 hasRelatedWork W2108598243 @default.
- W2950248853 hasRelatedWork W2112796928 @default.
- W2950248853 hasRelatedWork W2114766824 @default.
- W2950248853 hasRelatedWork W2163605009 @default.
- W2950248853 hasRelatedWork W2194775991 @default.
- W2950248853 hasRelatedWork W2279098554 @default.
- W2950248853 hasRelatedWork W2300242332 @default.
- W2950248853 hasRelatedWork W2513419314 @default.
- W2950248853 hasRelatedWork W2612445135 @default.
- W2950248853 hasRelatedWork W2952432176 @default.
- W2950248853 hasRelatedWork W2952899695 @default.
- W2950248853 hasRelatedWork W2964299589 @default.
- W2950248853 hasRelatedWork W3118608800 @default.
- W2950248853 isParatext "false" @default.
- W2950248853 isRetracted "false" @default.
- W2950248853 magId "2950248853" @default.
- W2950248853 workType "article" @default.