FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092479081> ?p ?o ?g. }

• W3092479081 abstract "Closing the gap between the hardware requirements of state-of-the-art convolutional neural networks and the limited resources constraining embedded applications is the next big challenge in deep learning research. The computational complexity and memory footprint of such neural networks are typically daunting for deployment in resource constrained environments. Model compression techniques, such as pruning, are emphasized among other optimization methods for solving this problem. Most existing techniques require domain expertise or result in irregular sparse representations, which increase the burden of deploying deep learning applications on embedded hardware accelerators. In this paper, we propose the autoencoder-based low-rank filter-sharing technique (ALF). When applied to various networks, ALF is compared to state-of-the-art pruning methods, demonstrating its efficient compression capabilities on theoretical metrics as well as on an accurate, deterministic hardware-model. In our experiments, ALF showed a reduction of 70% in network parameters, 61% in operations and 41% in execution time, with minimal loss in accuracy." @default.
• W3092479081 created "2020-10-15" @default.
• W3092479081 creator A5005732789 @default.
• W3092479081 creator A5034106438 @default.
• W3092479081 creator A5037114730 @default.
• W3092479081 creator A5038840530 @default.
• W3092479081 creator A5047063939 @default.
• W3092479081 creator A5079890456 @default.
• W3092479081 creator A5085220085 @default.
• W3092479081 date "2020-07-01" @default.
• W3092479081 modified "2023-10-16" @default.
• W3092479081 title "ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks" @default.
• W3092479081 cites W1533861849 @default.
• W3092479081 cites W1677182931 @default.
• W3092479081 cites W2097117768 @default.
• W3092479081 cites W2104636679 @default.
• W3092479081 cites W2108598243 @default.
• W3092479081 cites W2194775991 @default.
• W3092479081 cites W2267635276 @default.
• W3092479081 cites W2550831128 @default.
• W3092479081 cites W2565305208 @default.
• W3092479081 cites W2886851211 @default.
• W3092479081 cites W2891735857 @default.
• W3092479081 cites W2899818272 @default.
• W3092479081 cites W2924498682 @default.
• W3092479081 cites W2928560789 @default.
• W3092479081 cites W2940862705 @default.
• W3092479081 cites W2963140066 @default.
• W3092479081 cites W2963674932 @default.
• W3092479081 cites W2963918968 @default.
• W3092479081 cites W2963981420 @default.
• W3092479081 cites W2964259004 @default.
• W3092479081 cites W2965851570 @default.
• W3092479081 cites W2995607862 @default.
• W3092479081 cites W3036058978 @default.
• W3092479081 cites W3090169770 @default.
• W3092479081 doi "https://doi.org/10.1109/dac18072.2020.9218501" @default.
• W3092479081 hasPublicationYear "2020" @default.
• W3092479081 type Work @default.
• W3092479081 sameAs 3092479081 @default.
• W3092479081 citedByCount "4" @default.
• W3092479081 countsByYear W30924790812021 @default.
• W3092479081 countsByYear W30924790812023 @default.
• W3092479081 crossrefType "proceedings-article" @default.
• W3092479081 hasAuthorship W3092479081A5005732789 @default.
• W3092479081 hasAuthorship W3092479081A5034106438 @default.
• W3092479081 hasAuthorship W3092479081A5037114730 @default.
• W3092479081 hasAuthorship W3092479081A5038840530 @default.
• W3092479081 hasAuthorship W3092479081A5047063939 @default.
• W3092479081 hasAuthorship W3092479081A5079890456 @default.
• W3092479081 hasAuthorship W3092479081A5085220085 @default.
• W3092479081 hasBestOaLocation W30924790812 @default.
• W3092479081 hasConcept C101738243 @default.
• W3092479081 hasConcept C106131492 @default.
• W3092479081 hasConcept C108010975 @default.
• W3092479081 hasConcept C108583219 @default.
• W3092479081 hasConcept C111335779 @default.
• W3092479081 hasConcept C111919701 @default.
• W3092479081 hasConcept C113775141 @default.
• W3092479081 hasConcept C114614502 @default.
• W3092479081 hasConcept C119857082 @default.
• W3092479081 hasConcept C154945302 @default.
• W3092479081 hasConcept C164226766 @default.
• W3092479081 hasConcept C2524010 @default.
• W3092479081 hasConcept C31972630 @default.
• W3092479081 hasConcept C33923547 @default.
• W3092479081 hasConcept C41008148 @default.
• W3092479081 hasConcept C50644808 @default.
• W3092479081 hasConcept C6557445 @default.
• W3092479081 hasConcept C74912251 @default.
• W3092479081 hasConcept C81363708 @default.
• W3092479081 hasConcept C86803240 @default.
• W3092479081 hasConceptScore W3092479081C101738243 @default.
• W3092479081 hasConceptScore W3092479081C106131492 @default.
• W3092479081 hasConceptScore W3092479081C108010975 @default.
• W3092479081 hasConceptScore W3092479081C108583219 @default.
• W3092479081 hasConceptScore W3092479081C111335779 @default.
• W3092479081 hasConceptScore W3092479081C111919701 @default.
• W3092479081 hasConceptScore W3092479081C113775141 @default.
• W3092479081 hasConceptScore W3092479081C114614502 @default.
• W3092479081 hasConceptScore W3092479081C119857082 @default.
• W3092479081 hasConceptScore W3092479081C154945302 @default.
• W3092479081 hasConceptScore W3092479081C164226766 @default.
• W3092479081 hasConceptScore W3092479081C2524010 @default.
• W3092479081 hasConceptScore W3092479081C31972630 @default.
• W3092479081 hasConceptScore W3092479081C33923547 @default.
• W3092479081 hasConceptScore W3092479081C41008148 @default.
• W3092479081 hasConceptScore W3092479081C50644808 @default.
• W3092479081 hasConceptScore W3092479081C6557445 @default.
• W3092479081 hasConceptScore W3092479081C74912251 @default.
• W3092479081 hasConceptScore W3092479081C81363708 @default.
• W3092479081 hasConceptScore W3092479081C86803240 @default.
• W3092479081 hasLocation W30924790811 @default.
• W3092479081 hasLocation W30924790812 @default.
• W3092479081 hasOpenAccess W3092479081 @default.
• W3092479081 hasPrimaryLocation W30924790811 @default.
• W3092479081 hasRelatedWork W2337926734 @default.
• W3092479081 hasRelatedWork W2963958939 @default.
• W3092479081 hasRelatedWork W3044458868 @default.
• W3092479081 hasRelatedWork W3045422318 @default.

• next