Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048902839> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3048902839 endingPage "387" @default.
- W3048902839 startingPage "376" @default.
- W3048902839 abstract "The superiority of various Deep Neural Networks (DNN) models, such as Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), and Recurrent Neural Networks (RNN), has been proven in various real-world applications and has received much attention. However, different DNN models include various types of operations. For example, CNN models are usually composed of convolutional layers (Conv) and fully-connected layers (FC). Furthermore, some light CNN models such as MobileNet adopt depthwise separable convolution with depthwise convolution (DWC) and pointwise convolution (PWC) to compress the models. In addition to regular convolution, de-convolution (De-Conv) is also widely used in many GAN models. Moreover, many RNN models also employ long-short-term memory (LSTM) to control update of internal states and data. Such a high diversity of various DNN operations poses great design challenges in implementing reconfigurable Deep Learning (DL) accelerators, which can support various types of DNN operations. Most recent DL accelerators focus only on some DNN operations, which lacks computing flexibility. In this paper, by exploiting the sparsity in current DNN models, we design sparsity-aware DL hardware accelerators that can support efficient computation of various DNN operations, including Conv, DeConv, DWC, PWC, FC, and LSTM. Through reconfiguring dataflow and parallelizing different operations, the proposed designs not only improve system performance but also increase hardware utilization with a significant reduction of power consumption in memory accesses and arithmetic computations." @default.
- W3048902839 created "2020-08-18" @default.
- W3048902839 creator A5002103052 @default.
- W3048902839 creator A5070765584 @default.
- W3048902839 creator A5085694226 @default.
- W3048902839 creator A5088517936 @default.
- W3048902839 creator A5088586836 @default.
- W3048902839 date "2020-09-01" @default.
- W3048902839 modified "2023-10-14" @default.
- W3048902839 title "Design of a Sparsity-Aware Reconfigurable Deep Learning Accelerator Supporting Various Types of Operations" @default.
- W3048902839 cites W1901129140 @default.
- W3048902839 cites W2097117768 @default.
- W3048902839 cites W2194775991 @default.
- W3048902839 cites W2285660444 @default.
- W3048902839 cites W2289252105 @default.
- W3048902839 cites W2331128040 @default.
- W3048902839 cites W2334805829 @default.
- W3048902839 cites W2516141709 @default.
- W3048902839 cites W2531409750 @default.
- W3048902839 cites W2549139847 @default.
- W3048902839 cites W2565960208 @default.
- W3048902839 cites W2585720638 @default.
- W3048902839 cites W2605487586 @default.
- W3048902839 cites W2606722458 @default.
- W3048902839 cites W2625468380 @default.
- W3048902839 cites W2730834423 @default.
- W3048902839 cites W2734572653 @default.
- W3048902839 cites W2750173518 @default.
- W3048902839 cites W2757184610 @default.
- W3048902839 cites W2773339846 @default.
- W3048902839 cites W2803193013 @default.
- W3048902839 cites W2886352393 @default.
- W3048902839 cites W2895531329 @default.
- W3048902839 cites W2895738878 @default.
- W3048902839 cites W2896050315 @default.
- W3048902839 cites W2904902077 @default.
- W3048902839 cites W2945146780 @default.
- W3048902839 cites W2962793481 @default.
- W3048902839 cites W2963125010 @default.
- W3048902839 cites W2963163009 @default.
- W3048902839 cites W4234472914 @default.
- W3048902839 cites W4240168186 @default.
- W3048902839 doi "https://doi.org/10.1109/jetcas.2020.3015238" @default.
- W3048902839 hasPublicationYear "2020" @default.
- W3048902839 type Work @default.
- W3048902839 sameAs 3048902839 @default.
- W3048902839 citedByCount "13" @default.
- W3048902839 countsByYear W30489028392021 @default.
- W3048902839 countsByYear W30489028392022 @default.
- W3048902839 countsByYear W30489028392023 @default.
- W3048902839 crossrefType "journal-article" @default.
- W3048902839 hasAuthorship W3048902839A5002103052 @default.
- W3048902839 hasAuthorship W3048902839A5070765584 @default.
- W3048902839 hasAuthorship W3048902839A5085694226 @default.
- W3048902839 hasAuthorship W3048902839A5088517936 @default.
- W3048902839 hasAuthorship W3048902839A5088586836 @default.
- W3048902839 hasConcept C108583219 @default.
- W3048902839 hasConcept C118524514 @default.
- W3048902839 hasConcept C149635348 @default.
- W3048902839 hasConcept C154945302 @default.
- W3048902839 hasConcept C41008148 @default.
- W3048902839 hasConcept C42935608 @default.
- W3048902839 hasConceptScore W3048902839C108583219 @default.
- W3048902839 hasConceptScore W3048902839C118524514 @default.
- W3048902839 hasConceptScore W3048902839C149635348 @default.
- W3048902839 hasConceptScore W3048902839C154945302 @default.
- W3048902839 hasConceptScore W3048902839C41008148 @default.
- W3048902839 hasConceptScore W3048902839C42935608 @default.
- W3048902839 hasFunder F4320322795 @default.
- W3048902839 hasIssue "3" @default.
- W3048902839 hasLocation W30489028391 @default.
- W3048902839 hasOpenAccess W3048902839 @default.
- W3048902839 hasPrimaryLocation W30489028391 @default.
- W3048902839 hasRelatedWork W2063534976 @default.
- W3048902839 hasRelatedWork W2320205417 @default.
- W3048902839 hasRelatedWork W2616418345 @default.
- W3048902839 hasRelatedWork W2771532367 @default.
- W3048902839 hasRelatedWork W2907463061 @default.
- W3048902839 hasRelatedWork W2954307240 @default.
- W3048902839 hasRelatedWork W2980006224 @default.
- W3048902839 hasRelatedWork W2980171969 @default.
- W3048902839 hasRelatedWork W3116132749 @default.
- W3048902839 hasRelatedWork W3133757386 @default.
- W3048902839 hasVolume "10" @default.
- W3048902839 isParatext "false" @default.
- W3048902839 isRetracted "false" @default.
- W3048902839 magId "3048902839" @default.
- W3048902839 workType "article" @default.