Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980852088> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2980852088 abstract "In recent years, convolutional neural networks (CNN) has achieved great success in computer vision tasks, such as object detection, face recognition and image classification. With the diversification of CNN models, accelerators that only support a single network can no longer meet the needs of applications. Due to the computational intensiveness of convolution operations, the implementation of CNN on the FPGA platform faces many challenges. In this paper, a convolution unit based on systolic arrays is proposed in the design of CNN accelerator, and the fixed-point quantization method is adopted to save a large amount of storage resources and reduce the required transmission bandwidth, thus improving throughput and power efficiency. The performance density and power efficiency of our design can reach 0.165 GOPS/DSP and 36.3 GOPS/W under 100MHz clock frequency." @default.
- W2980852088 created "2019-10-25" @default.
- W2980852088 creator A5007960012 @default.
- W2980852088 creator A5023104005 @default.
- W2980852088 creator A5047123790 @default.
- W2980852088 creator A5061397843 @default.
- W2980852088 creator A5088664989 @default.
- W2980852088 date "2019-07-01" @default.
- W2980852088 modified "2023-09-28" @default.
- W2980852088 title "High-performance Convolutional Neural Network Accelerator Based on Systolic Arrays and Quantization" @default.
- W2980852088 cites W2276486856 @default.
- W2980852088 cites W2605487586 @default.
- W2980852088 cites W2625954420 @default.
- W2980852088 cites W2737244778 @default.
- W2980852088 cites W2896983500 @default.
- W2980852088 cites W2904132118 @default.
- W2980852088 doi "https://doi.org/10.1109/siprocess.2019.8868327" @default.
- W2980852088 hasPublicationYear "2019" @default.
- W2980852088 type Work @default.
- W2980852088 sameAs 2980852088 @default.
- W2980852088 citedByCount "7" @default.
- W2980852088 countsByYear W29808520882021 @default.
- W2980852088 countsByYear W29808520882022 @default.
- W2980852088 countsByYear W29808520882023 @default.
- W2980852088 crossrefType "proceedings-article" @default.
- W2980852088 hasAuthorship W2980852088A5007960012 @default.
- W2980852088 hasAuthorship W2980852088A5023104005 @default.
- W2980852088 hasAuthorship W2980852088A5047123790 @default.
- W2980852088 hasAuthorship W2980852088A5061397843 @default.
- W2980852088 hasAuthorship W2980852088A5088664989 @default.
- W2980852088 hasConcept C113775141 @default.
- W2980852088 hasConcept C149635348 @default.
- W2980852088 hasConcept C154945302 @default.
- W2980852088 hasConcept C157764524 @default.
- W2980852088 hasConcept C28855332 @default.
- W2980852088 hasConcept C31972630 @default.
- W2980852088 hasConcept C41008148 @default.
- W2980852088 hasConcept C42935608 @default.
- W2980852088 hasConcept C45347329 @default.
- W2980852088 hasConcept C50644808 @default.
- W2980852088 hasConcept C555944384 @default.
- W2980852088 hasConcept C76155785 @default.
- W2980852088 hasConcept C81363708 @default.
- W2980852088 hasConcept C84462506 @default.
- W2980852088 hasConcept C9390403 @default.
- W2980852088 hasConceptScore W2980852088C113775141 @default.
- W2980852088 hasConceptScore W2980852088C149635348 @default.
- W2980852088 hasConceptScore W2980852088C154945302 @default.
- W2980852088 hasConceptScore W2980852088C157764524 @default.
- W2980852088 hasConceptScore W2980852088C28855332 @default.
- W2980852088 hasConceptScore W2980852088C31972630 @default.
- W2980852088 hasConceptScore W2980852088C41008148 @default.
- W2980852088 hasConceptScore W2980852088C42935608 @default.
- W2980852088 hasConceptScore W2980852088C45347329 @default.
- W2980852088 hasConceptScore W2980852088C50644808 @default.
- W2980852088 hasConceptScore W2980852088C555944384 @default.
- W2980852088 hasConceptScore W2980852088C76155785 @default.
- W2980852088 hasConceptScore W2980852088C81363708 @default.
- W2980852088 hasConceptScore W2980852088C84462506 @default.
- W2980852088 hasConceptScore W2980852088C9390403 @default.
- W2980852088 hasLocation W29808520881 @default.
- W2980852088 hasOpenAccess W2980852088 @default.
- W2980852088 hasPrimaryLocation W29808520881 @default.
- W2980852088 hasRelatedWork W2349666940 @default.
- W2980852088 hasRelatedWork W2350861609 @default.
- W2980852088 hasRelatedWork W2352017551 @default.
- W2980852088 hasRelatedWork W2353364150 @default.
- W2980852088 hasRelatedWork W2375677847 @default.
- W2980852088 hasRelatedWork W2377087316 @default.
- W2980852088 hasRelatedWork W2383668268 @default.
- W2980852088 hasRelatedWork W2384717299 @default.
- W2980852088 hasRelatedWork W2524802307 @default.
- W2980852088 hasRelatedWork W4308216800 @default.
- W2980852088 isParatext "false" @default.
- W2980852088 isRetracted "false" @default.
- W2980852088 magId "2980852088" @default.
- W2980852088 workType "article" @default.