Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184236731> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3184236731 abstract "Recent advances in the field of computer vision create the demand for larger and more complex architectures for Deep Convolutional Neural Networks (CNNs). As a result, computation time and memory usage become the main bottleneck in applied deep network inference, particularly in Embedded Systems implementations. Parameter quantization is often employed in these cases to minimize the detrimental effect of the aforementioned bottlenecks. In this paper, low level hardware optimizations on fixed point convolution are considered. Emphasis is given on the utilization of Digital Signal Processing Units (DSPs) as dual multipliers and on practical considerations. Three-by- three convolution kernels are formulated based on this research and are measured as case studies. The experiments show that the proper exploitation of dual multipliers can offer significant benefits to the system." @default.
- W3184236731 created "2021-08-02" @default.
- W3184236731 creator A5000929982 @default.
- W3184236731 creator A5050998978 @default.
- W3184236731 creator A5070254829 @default.
- W3184236731 creator A5077987514 @default.
- W3184236731 date "2021-07-05" @default.
- W3184236731 modified "2023-09-26" @default.
- W3184236731 title "Efficient Utilization of FPGA Multipliers for Convolutional Neural Networks" @default.
- W3184236731 cites W1599533721 @default.
- W3184236731 cites W1605005685 @default.
- W3184236731 cites W2133757342 @default.
- W3184236731 cites W2155893237 @default.
- W3184236731 cites W2172119162 @default.
- W3184236731 cites W2625954420 @default.
- W3184236731 cites W2771059075 @default.
- W3184236731 cites W2948244774 @default.
- W3184236731 cites W2964350391 @default.
- W3184236731 doi "https://doi.org/10.1109/mocast52088.2021.9493366" @default.
- W3184236731 hasPublicationYear "2021" @default.
- W3184236731 type Work @default.
- W3184236731 sameAs 3184236731 @default.
- W3184236731 citedByCount "1" @default.
- W3184236731 countsByYear W31842367312022 @default.
- W3184236731 crossrefType "proceedings-article" @default.
- W3184236731 hasAuthorship W3184236731A5000929982 @default.
- W3184236731 hasAuthorship W3184236731A5050998978 @default.
- W3184236731 hasAuthorship W3184236731A5070254829 @default.
- W3184236731 hasAuthorship W3184236731A5077987514 @default.
- W3184236731 hasConcept C113775141 @default.
- W3184236731 hasConcept C11413529 @default.
- W3184236731 hasConcept C124584101 @default.
- W3184236731 hasConcept C139719470 @default.
- W3184236731 hasConcept C149635348 @default.
- W3184236731 hasConcept C154945302 @default.
- W3184236731 hasConcept C162324750 @default.
- W3184236731 hasConcept C199360897 @default.
- W3184236731 hasConcept C26713055 @default.
- W3184236731 hasConcept C2776214188 @default.
- W3184236731 hasConcept C2780513914 @default.
- W3184236731 hasConcept C28855332 @default.
- W3184236731 hasConcept C41008148 @default.
- W3184236731 hasConcept C42935608 @default.
- W3184236731 hasConcept C45347329 @default.
- W3184236731 hasConcept C45374587 @default.
- W3184236731 hasConcept C50644808 @default.
- W3184236731 hasConcept C81363708 @default.
- W3184236731 hasConcept C84462506 @default.
- W3184236731 hasConcept C9390403 @default.
- W3184236731 hasConceptScore W3184236731C113775141 @default.
- W3184236731 hasConceptScore W3184236731C11413529 @default.
- W3184236731 hasConceptScore W3184236731C124584101 @default.
- W3184236731 hasConceptScore W3184236731C139719470 @default.
- W3184236731 hasConceptScore W3184236731C149635348 @default.
- W3184236731 hasConceptScore W3184236731C154945302 @default.
- W3184236731 hasConceptScore W3184236731C162324750 @default.
- W3184236731 hasConceptScore W3184236731C199360897 @default.
- W3184236731 hasConceptScore W3184236731C26713055 @default.
- W3184236731 hasConceptScore W3184236731C2776214188 @default.
- W3184236731 hasConceptScore W3184236731C2780513914 @default.
- W3184236731 hasConceptScore W3184236731C28855332 @default.
- W3184236731 hasConceptScore W3184236731C41008148 @default.
- W3184236731 hasConceptScore W3184236731C42935608 @default.
- W3184236731 hasConceptScore W3184236731C45347329 @default.
- W3184236731 hasConceptScore W3184236731C45374587 @default.
- W3184236731 hasConceptScore W3184236731C50644808 @default.
- W3184236731 hasConceptScore W3184236731C81363708 @default.
- W3184236731 hasConceptScore W3184236731C84462506 @default.
- W3184236731 hasConceptScore W3184236731C9390403 @default.
- W3184236731 hasLocation W31842367311 @default.
- W3184236731 hasOpenAccess W3184236731 @default.
- W3184236731 hasPrimaryLocation W31842367311 @default.
- W3184236731 hasRelatedWork W1549325751 @default.
- W3184236731 hasRelatedWork W2786216825 @default.
- W3184236731 hasRelatedWork W2902363683 @default.
- W3184236731 hasRelatedWork W2952735458 @default.
- W3184236731 hasRelatedWork W3005273712 @default.
- W3184236731 hasRelatedWork W3151612890 @default.
- W3184236731 hasRelatedWork W3184236731 @default.
- W3184236731 hasRelatedWork W4319662858 @default.
- W3184236731 hasRelatedWork W4327640786 @default.
- W3184236731 hasRelatedWork W3116497574 @default.
- W3184236731 isParatext "false" @default.
- W3184236731 isRetracted "false" @default.
- W3184236731 magId "3184236731" @default.
- W3184236731 workType "article" @default.