Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897800076> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2897800076 abstract "Due to the computational complexity of Convolutional Neural Networks (CNNs), high performance platforms are generally considered for their execution. However, CNNs are very useful in embedded systems and its execution right next to the source of data has many advantages, like avoiding the need for data communication. In this paper, we propose an architecture for CNN inference (Lite-CNN) that can achieve high performance in low density FPGAs. Lite-CNN adopts a fixed-point representation for both neurons and weights, which was already shown to be sufficient for most CNNs. Also, with a simple and known dot product reorganization, the number of multiplications is reduced to half. We show implementation results for 8 bit fixed-point in a ZYNQ7020 and extrapolate for other larger FPGAs. Lite-CNN achieves 410 GOPs in a ZYNQ7020." @default.
- W2897800076 created "2018-10-26" @default.
- W2897800076 creator A5003178960 @default.
- W2897800076 creator A5062555847 @default.
- W2897800076 creator A5079441335 @default.
- W2897800076 creator A5086015292 @default.
- W2897800076 date "2018-08-01" @default.
- W2897800076 modified "2023-09-27" @default.
- W2897800076 title "Lite-CNN: A High-Performance Architecture to Execute CNNs in Low Density FPGAs" @default.
- W2897800076 cites W2117539524 @default.
- W2897800076 cites W2119112357 @default.
- W2897800076 cites W2276486856 @default.
- W2897800076 cites W2294282016 @default.
- W2897800076 cites W2404540148 @default.
- W2897800076 cites W2513568085 @default.
- W2897800076 cites W2574797063 @default.
- W2897800076 cites W2616014673 @default.
- W2897800076 cites W2737762472 @default.
- W2897800076 doi "https://doi.org/10.1109/fpl.2018.00075" @default.
- W2897800076 hasPublicationYear "2018" @default.
- W2897800076 type Work @default.
- W2897800076 sameAs 2897800076 @default.
- W2897800076 citedByCount "14" @default.
- W2897800076 countsByYear W28978000762019 @default.
- W2897800076 countsByYear W28978000762020 @default.
- W2897800076 countsByYear W28978000762021 @default.
- W2897800076 countsByYear W28978000762022 @default.
- W2897800076 countsByYear W28978000762023 @default.
- W2897800076 crossrefType "proceedings-article" @default.
- W2897800076 hasAuthorship W2897800076A5003178960 @default.
- W2897800076 hasAuthorship W2897800076A5062555847 @default.
- W2897800076 hasAuthorship W2897800076A5079441335 @default.
- W2897800076 hasAuthorship W2897800076A5086015292 @default.
- W2897800076 hasBestOaLocation W28978000762 @default.
- W2897800076 hasConcept C111472728 @default.
- W2897800076 hasConcept C113775141 @default.
- W2897800076 hasConcept C118524514 @default.
- W2897800076 hasConcept C123657996 @default.
- W2897800076 hasConcept C138885662 @default.
- W2897800076 hasConcept C142362112 @default.
- W2897800076 hasConcept C149635348 @default.
- W2897800076 hasConcept C153349607 @default.
- W2897800076 hasConcept C154945302 @default.
- W2897800076 hasConcept C173608175 @default.
- W2897800076 hasConcept C17744445 @default.
- W2897800076 hasConcept C199539241 @default.
- W2897800076 hasConcept C2776214188 @default.
- W2897800076 hasConcept C2776359362 @default.
- W2897800076 hasConcept C2780586882 @default.
- W2897800076 hasConcept C41008148 @default.
- W2897800076 hasConcept C42935608 @default.
- W2897800076 hasConcept C81363708 @default.
- W2897800076 hasConcept C94625758 @default.
- W2897800076 hasConceptScore W2897800076C111472728 @default.
- W2897800076 hasConceptScore W2897800076C113775141 @default.
- W2897800076 hasConceptScore W2897800076C118524514 @default.
- W2897800076 hasConceptScore W2897800076C123657996 @default.
- W2897800076 hasConceptScore W2897800076C138885662 @default.
- W2897800076 hasConceptScore W2897800076C142362112 @default.
- W2897800076 hasConceptScore W2897800076C149635348 @default.
- W2897800076 hasConceptScore W2897800076C153349607 @default.
- W2897800076 hasConceptScore W2897800076C154945302 @default.
- W2897800076 hasConceptScore W2897800076C173608175 @default.
- W2897800076 hasConceptScore W2897800076C17744445 @default.
- W2897800076 hasConceptScore W2897800076C199539241 @default.
- W2897800076 hasConceptScore W2897800076C2776214188 @default.
- W2897800076 hasConceptScore W2897800076C2776359362 @default.
- W2897800076 hasConceptScore W2897800076C2780586882 @default.
- W2897800076 hasConceptScore W2897800076C41008148 @default.
- W2897800076 hasConceptScore W2897800076C42935608 @default.
- W2897800076 hasConceptScore W2897800076C81363708 @default.
- W2897800076 hasConceptScore W2897800076C94625758 @default.
- W2897800076 hasLocation W28978000761 @default.
- W2897800076 hasLocation W28978000762 @default.
- W2897800076 hasOpenAccess W2897800076 @default.
- W2897800076 hasPrimaryLocation W28978000761 @default.
- W2897800076 hasRelatedWork W2002703587 @default.
- W2897800076 hasRelatedWork W2025382273 @default.
- W2897800076 hasRelatedWork W2295680811 @default.
- W2897800076 hasRelatedWork W2524802307 @default.
- W2897800076 hasRelatedWork W2901346193 @default.
- W2897800076 hasRelatedWork W2904058793 @default.
- W2897800076 hasRelatedWork W3186240590 @default.
- W2897800076 hasRelatedWork W4220896354 @default.
- W2897800076 hasRelatedWork W4304140748 @default.
- W2897800076 hasRelatedWork W4319662858 @default.
- W2897800076 isParatext "false" @default.
- W2897800076 isRetracted "false" @default.
- W2897800076 magId "2897800076" @default.
- W2897800076 workType "article" @default.