Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914681245> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2914681245 abstract "Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) have made great progress in machine learning community. Combining CNN and RNN can accomplish more general and complex tasks. Many specially designed hardware accelerators on FPGA or ASIC have been proposed for CNN or RNN, yet few of them focus on CNN-RNN-based models for general purpose applications. In this paper, we propose a complete design framework for deploying general-purpose CNNRNN-based models on FPGAs. We use Deephi Aristotle and Descartes IPs to build an efficient and reconfigurable hardware system with the support of Deephi's toolchains and Xilinx SDSoC environment. We also design a CNN-RNN-based co-optimization method which can find the IP configuration to achieve the maximum throughput under the given FPGA resources and neural network models. Our implementation on the Xilinx ZU5EG FPGA achieves the throughput of 690.76GOPS and the energy efficiency of 86.34GOPS/W on LRCN network." @default.
- W2914681245 created "2019-02-21" @default.
- W2914681245 creator A5009175141 @default.
- W2914681245 creator A5017382359 @default.
- W2914681245 creator A5018054686 @default.
- W2914681245 creator A5023755254 @default.
- W2914681245 creator A5026831784 @default.
- W2914681245 creator A5054247276 @default.
- W2914681245 creator A5079594267 @default.
- W2914681245 creator A5083510126 @default.
- W2914681245 date "2018-11-01" @default.
- W2914681245 modified "2023-10-18" @default.
- W2914681245 title "An Efficient Reconfigurable Framework for General Purpose CNN-RNN Models on FPGAs" @default.
- W2914681245 cites W1895577753 @default.
- W2914681245 cites W1947481528 @default.
- W2914681245 cites W2094756095 @default.
- W2914681245 cites W2143612262 @default.
- W2914681245 cites W2160815625 @default.
- W2914681245 cites W2163605009 @default.
- W2914681245 cites W2194775991 @default.
- W2914681245 cites W2293771166 @default.
- W2914681245 cites W2585720638 @default.
- W2914681245 cites W2594492285 @default.
- W2914681245 cites W2616014673 @default.
- W2914681245 cites W2727238169 @default.
- W2914681245 cites W2762910930 @default.
- W2914681245 cites W2964288706 @default.
- W2914681245 cites W2964299589 @default.
- W2914681245 doi "https://doi.org/10.1109/icdsp.2018.8631880" @default.
- W2914681245 hasPublicationYear "2018" @default.
- W2914681245 type Work @default.
- W2914681245 sameAs 2914681245 @default.
- W2914681245 citedByCount "2" @default.
- W2914681245 countsByYear W29146812452019 @default.
- W2914681245 countsByYear W29146812452022 @default.
- W2914681245 crossrefType "proceedings-article" @default.
- W2914681245 hasAuthorship W2914681245A5009175141 @default.
- W2914681245 hasAuthorship W2914681245A5017382359 @default.
- W2914681245 hasAuthorship W2914681245A5018054686 @default.
- W2914681245 hasAuthorship W2914681245A5023755254 @default.
- W2914681245 hasAuthorship W2914681245A5026831784 @default.
- W2914681245 hasAuthorship W2914681245A5054247276 @default.
- W2914681245 hasAuthorship W2914681245A5079594267 @default.
- W2914681245 hasAuthorship W2914681245A5083510126 @default.
- W2914681245 hasConcept C108583219 @default.
- W2914681245 hasConcept C113775141 @default.
- W2914681245 hasConcept C118524514 @default.
- W2914681245 hasConcept C142962650 @default.
- W2914681245 hasConcept C147168706 @default.
- W2914681245 hasConcept C149635348 @default.
- W2914681245 hasConcept C154945302 @default.
- W2914681245 hasConcept C157764524 @default.
- W2914681245 hasConcept C41008148 @default.
- W2914681245 hasConcept C42935608 @default.
- W2914681245 hasConcept C50644808 @default.
- W2914681245 hasConcept C555944384 @default.
- W2914681245 hasConcept C76155785 @default.
- W2914681245 hasConcept C77390884 @default.
- W2914681245 hasConcept C81363708 @default.
- W2914681245 hasConceptScore W2914681245C108583219 @default.
- W2914681245 hasConceptScore W2914681245C113775141 @default.
- W2914681245 hasConceptScore W2914681245C118524514 @default.
- W2914681245 hasConceptScore W2914681245C142962650 @default.
- W2914681245 hasConceptScore W2914681245C147168706 @default.
- W2914681245 hasConceptScore W2914681245C149635348 @default.
- W2914681245 hasConceptScore W2914681245C154945302 @default.
- W2914681245 hasConceptScore W2914681245C157764524 @default.
- W2914681245 hasConceptScore W2914681245C41008148 @default.
- W2914681245 hasConceptScore W2914681245C42935608 @default.
- W2914681245 hasConceptScore W2914681245C50644808 @default.
- W2914681245 hasConceptScore W2914681245C555944384 @default.
- W2914681245 hasConceptScore W2914681245C76155785 @default.
- W2914681245 hasConceptScore W2914681245C77390884 @default.
- W2914681245 hasConceptScore W2914681245C81363708 @default.
- W2914681245 hasLocation W29146812451 @default.
- W2914681245 hasOpenAccess W2914681245 @default.
- W2914681245 hasPrimaryLocation W29146812451 @default.
- W2914681245 hasRelatedWork W1604320855 @default.
- W2914681245 hasRelatedWork W2134422574 @default.
- W2914681245 hasRelatedWork W2142497937 @default.
- W2914681245 hasRelatedWork W2250451487 @default.
- W2914681245 hasRelatedWork W2361654132 @default.
- W2914681245 hasRelatedWork W2383233236 @default.
- W2914681245 hasRelatedWork W2524802307 @default.
- W2914681245 hasRelatedWork W2954307240 @default.
- W2914681245 hasRelatedWork W2984236338 @default.
- W2914681245 hasRelatedWork W2506672464 @default.
- W2914681245 isParatext "false" @default.
- W2914681245 isRetracted "false" @default.
- W2914681245 magId "2914681245" @default.
- W2914681245 workType "article" @default.