Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907807896> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2907807896 abstract "Convolutional Neural Networks (CNNs) are constituted of complex, slow convolutional layers and memory-demanding fully- connected layers. Current pruning techniques can reduce memory accesses and power consumption, but cannot speed up the convolutional layers. In this paper, we introduce a pruning technique able to reduce the number of kernels in convolutional layers of up to 90% with negligible accuracy degradation. We propose an architecture to accelerate fully- connected and convolutional computations within a single computational core, with power$/$energy consumption below mobile devices budget. The proposed pruning technique speeds up convolutional computations by up to $ 6.9times $, reducing memory accesses by the same factor." @default.
- W2907807896 created "2019-01-11" @default.
- W2907807896 creator A5064497251 @default.
- W2907807896 creator A5085812448 @default.
- W2907807896 creator A5091600002 @default.
- W2907807896 date "2018-06-01" @default.
- W2907807896 modified "2023-09-25" @default.
- W2907807896 title "A Multi-Mode Accelerator for Pruned Deep Neural Networks" @default.
- W2907807896 cites W2097117768 @default.
- W2907807896 cites W2194775991 @default.
- W2907807896 cites W2219959730 @default.
- W2907807896 cites W2285660444 @default.
- W2907807896 cites W2289252105 @default.
- W2907807896 cites W2335728318 @default.
- W2907807896 cites W2431931973 @default.
- W2907807896 cites W2565960208 @default.
- W2907807896 cites W2594492285 @default.
- W2907807896 cites W2766143712 @default.
- W2907807896 cites W2919115771 @default.
- W2907807896 cites W2962835968 @default.
- W2907807896 cites W2963114950 @default.
- W2907807896 cites W2963200642 @default.
- W2907807896 cites W2963674932 @default.
- W2907807896 cites W2964299589 @default.
- W2907807896 cites W3118608800 @default.
- W2907807896 doi "https://doi.org/10.1109/newcas.2018.8585517" @default.
- W2907807896 hasPublicationYear "2018" @default.
- W2907807896 type Work @default.
- W2907807896 sameAs 2907807896 @default.
- W2907807896 citedByCount "0" @default.
- W2907807896 crossrefType "proceedings-article" @default.
- W2907807896 hasAuthorship W2907807896A5064497251 @default.
- W2907807896 hasAuthorship W2907807896A5085812448 @default.
- W2907807896 hasAuthorship W2907807896A5091600002 @default.
- W2907807896 hasConcept C108010975 @default.
- W2907807896 hasConcept C11413529 @default.
- W2907807896 hasConcept C119599485 @default.
- W2907807896 hasConcept C127413603 @default.
- W2907807896 hasConcept C154945302 @default.
- W2907807896 hasConcept C157899210 @default.
- W2907807896 hasConcept C173608175 @default.
- W2907807896 hasConcept C176649486 @default.
- W2907807896 hasConcept C2780165032 @default.
- W2907807896 hasConcept C41008148 @default.
- W2907807896 hasConcept C45374587 @default.
- W2907807896 hasConcept C57273362 @default.
- W2907807896 hasConcept C6557445 @default.
- W2907807896 hasConcept C68339613 @default.
- W2907807896 hasConcept C81363708 @default.
- W2907807896 hasConcept C86803240 @default.
- W2907807896 hasConcept C9390403 @default.
- W2907807896 hasConcept C98986596 @default.
- W2907807896 hasConceptScore W2907807896C108010975 @default.
- W2907807896 hasConceptScore W2907807896C11413529 @default.
- W2907807896 hasConceptScore W2907807896C119599485 @default.
- W2907807896 hasConceptScore W2907807896C127413603 @default.
- W2907807896 hasConceptScore W2907807896C154945302 @default.
- W2907807896 hasConceptScore W2907807896C157899210 @default.
- W2907807896 hasConceptScore W2907807896C173608175 @default.
- W2907807896 hasConceptScore W2907807896C176649486 @default.
- W2907807896 hasConceptScore W2907807896C2780165032 @default.
- W2907807896 hasConceptScore W2907807896C41008148 @default.
- W2907807896 hasConceptScore W2907807896C45374587 @default.
- W2907807896 hasConceptScore W2907807896C57273362 @default.
- W2907807896 hasConceptScore W2907807896C6557445 @default.
- W2907807896 hasConceptScore W2907807896C68339613 @default.
- W2907807896 hasConceptScore W2907807896C81363708 @default.
- W2907807896 hasConceptScore W2907807896C86803240 @default.
- W2907807896 hasConceptScore W2907807896C9390403 @default.
- W2907807896 hasConceptScore W2907807896C98986596 @default.
- W2907807896 hasLocation W29078078961 @default.
- W2907807896 hasOpenAccess W2907807896 @default.
- W2907807896 hasPrimaryLocation W29078078961 @default.
- W2907807896 hasRelatedWork W1984294874 @default.
- W2907807896 hasRelatedWork W2622872848 @default.
- W2907807896 hasRelatedWork W2767644592 @default.
- W2907807896 hasRelatedWork W2795177683 @default.
- W2907807896 hasRelatedWork W2798317693 @default.
- W2907807896 hasRelatedWork W2893341906 @default.
- W2907807896 hasRelatedWork W2907757276 @default.
- W2907807896 hasRelatedWork W2964588512 @default.
- W2907807896 hasRelatedWork W2966206672 @default.
- W2907807896 hasRelatedWork W2966456821 @default.
- W2907807896 hasRelatedWork W2968754051 @default.
- W2907807896 hasRelatedWork W2989199275 @default.
- W2907807896 hasRelatedWork W3081137248 @default.
- W2907807896 hasRelatedWork W3090420559 @default.
- W2907807896 hasRelatedWork W3094014938 @default.
- W2907807896 hasRelatedWork W3108198978 @default.
- W2907807896 hasRelatedWork W3125142456 @default.
- W2907807896 hasRelatedWork W3135732781 @default.
- W2907807896 hasRelatedWork W3198164737 @default.
- W2907807896 hasRelatedWork W3198711939 @default.
- W2907807896 isParatext "false" @default.
- W2907807896 isRetracted "false" @default.
- W2907807896 magId "2907807896" @default.
- W2907807896 workType "article" @default.