FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2616014673> ?p ?o ?g. }

• W2616014673 endingPage "47" @default.
• W2616014673 startingPage "35" @default.
• W2616014673 abstract "Convolutional neural network (CNN) has become a successful algorithm in the region of artificial intelligence and a strong candidate for many computer vision algorithms. But the computation complexity of CNN is much higher than traditional algorithms. With the help of GPU acceleration, CNN-based applications are widely deployed in servers. However, for embedded platforms, CNN-based solutions are still too complex to be applied. Various dedicated hardware designs on field-programmable gate arrays (FPGAs) have been carried out to accelerate CNNs, while few of them explore the whole design flow for both fast deployment and high power efficiency. In this paper, we investigate state-of-the-art CNN models and CNN-based applications. Requirements on memory, computation and the flexibility of the system are summarized for mapping CNN on embedded FPGAs. Based on these requirements, we propose Angel-Eye, a programmable and flexible CNN accelerator architecture, together with data quantization strategy and compilation tool. Data quantization strategy helps reduce the bit-width down to 8-bit with negligible accuracy loss. The compilation tool maps a certain CNN model efficiently onto hardware. Evaluated on Zynq XC7Z045 platform, Angel-Eye is $6 {times }$ faster and $5{times }$ better in power efficiency than peer FPGA implementation on the same platform. Applications of VGG network, pedestrian detection and face alignment are used to evaluate our design on Zynq XC7Z020. NIVIDA TK1 and TX1 platforms are used for comparison. Angel-Eye achieves similar performance and delivers up to $16 {times }$ better energy efficiency." @default.
• W2616014673 created "2017-05-26" @default.
• W2616014673 creator A5004624473 @default.
• W2616014673 creator A5023755254 @default.
• W2616014673 creator A5024859435 @default.
• W2616014673 creator A5025755637 @default.
• W2616014673 creator A5032098525 @default.
• W2616014673 creator A5061832737 @default.
• W2616014673 creator A5062869202 @default.
• W2616014673 creator A5083510126 @default.
• W2616014673 creator A5090846991 @default.
• W2616014673 date "2018-01-01" @default.
• W2616014673 modified "2023-10-17" @default.
• W2616014673 title "Angel-Eye: A Complete Design Flow for Mapping CNN Onto Embedded FPGA" @default.
• W2616014673 cites W1536680647 @default.
• W2616014673 cites W1903029394 @default.
• W2616014673 cites W1934410531 @default.
• W2616014673 cites W2044535169 @default.
• W2616014673 cites W2067523571 @default.
• W2616014673 cites W2070167224 @default.
• W2616014673 cites W2097117768 @default.
• W2616014673 cites W2102605133 @default.
• W2616014673 cites W2125203716 @default.
• W2616014673 cites W2135252045 @default.
• W2616014673 cites W2155893237 @default.
• W2616014673 cites W2172654076 @default.
• W2616014673 cites W2194775991 @default.
• W2616014673 cites W2276486856 @default.
• W2616014673 cites W2285660444 @default.
• W2616014673 cites W2290132443 @default.
• W2616014673 cites W2396572963 @default.
• W2616014673 cites W2516141709 @default.
• W2616014673 cites W2520083297 @default.
• W2616014673 cites W2524802307 @default.
• W2616014673 cites W2963037989 @default.
• W2616014673 cites W3004171485 @default.
• W2616014673 cites W3024621361 @default.
• W2616014673 cites W4240168186 @default.
• W2616014673 doi "https://doi.org/10.1109/tcad.2017.2705069" @default.
• W2616014673 hasPublicationYear "2018" @default.
• W2616014673 type Work @default.
• W2616014673 sameAs 2616014673 @default.
• W2616014673 citedByCount "364" @default.
• W2616014673 countsByYear W26160146732017 @default.
• W2616014673 countsByYear W26160146732018 @default.
• W2616014673 countsByYear W26160146732019 @default.
• W2616014673 countsByYear W26160146732020 @default.
• W2616014673 countsByYear W26160146732021 @default.
• W2616014673 countsByYear W26160146732022 @default.
• W2616014673 countsByYear W26160146732023 @default.
• W2616014673 crossrefType "journal-article" @default.
• W2616014673 hasAuthorship W2616014673A5004624473 @default.
• W2616014673 hasAuthorship W2616014673A5023755254 @default.
• W2616014673 hasAuthorship W2616014673A5024859435 @default.
• W2616014673 hasAuthorship W2616014673A5025755637 @default.
• W2616014673 hasAuthorship W2616014673A5032098525 @default.
• W2616014673 hasAuthorship W2616014673A5061832737 @default.
• W2616014673 hasAuthorship W2616014673A5062869202 @default.
• W2616014673 hasAuthorship W2616014673A5083510126 @default.
• W2616014673 hasAuthorship W2616014673A5090846991 @default.
• W2616014673 hasConcept C118524514 @default.
• W2616014673 hasConcept C121684516 @default.
• W2616014673 hasConcept C149635348 @default.
• W2616014673 hasConcept C2524010 @default.
• W2616014673 hasConcept C33923547 @default.
• W2616014673 hasConcept C37135326 @default.
• W2616014673 hasConcept C38349280 @default.
• W2616014673 hasConcept C41008148 @default.
• W2616014673 hasConcept C42935608 @default.
• W2616014673 hasConcept C9390403 @default.
• W2616014673 hasConceptScore W2616014673C118524514 @default.
• W2616014673 hasConceptScore W2616014673C121684516 @default.
• W2616014673 hasConceptScore W2616014673C149635348 @default.
• W2616014673 hasConceptScore W2616014673C2524010 @default.
• W2616014673 hasConceptScore W2616014673C33923547 @default.
• W2616014673 hasConceptScore W2616014673C37135326 @default.
• W2616014673 hasConceptScore W2616014673C38349280 @default.
• W2616014673 hasConceptScore W2616014673C41008148 @default.
• W2616014673 hasConceptScore W2616014673C42935608 @default.
• W2616014673 hasConceptScore W2616014673C9390403 @default.
• W2616014673 hasFunder F4320321001 @default.
• W2616014673 hasFunder F4320322392 @default.
• W2616014673 hasIssue "1" @default.
• W2616014673 hasLocation W26160146731 @default.
• W2616014673 hasOpenAccess W2616014673 @default.
• W2616014673 hasPrimaryLocation W26160146731 @default.
• W2616014673 hasRelatedWork W1604320855 @default.
• W2616014673 hasRelatedWork W1976338682 @default.
• W2616014673 hasRelatedWork W2093864534 @default.
• W2616014673 hasRelatedWork W2142848556 @default.
• W2616014673 hasRelatedWork W2167716702 @default.
• W2616014673 hasRelatedWork W2169423330 @default.
• W2616014673 hasRelatedWork W2376977248 @default.
• W2616014673 hasRelatedWork W2998132311 @default.
• W2616014673 hasRelatedWork W4308084229 @default.
• W2616014673 hasRelatedWork W2126880757 @default.
• W2616014673 hasVolume "37" @default.
• W2616014673 isParatext "false" @default.

• next