Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902431002> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2902431002 abstract "Deep Convolutional Neural Networks (DCNNs) achieve state of the art results compared to classic machine learning in many applications that need recognition, identification and classification. An ever-increasing embedded deployment of DCNNs inference engines thus supporting the intelligence close to the sensor paradigm has been observed, overcoming limitations of cloud-based computing as bandwidth requirements, security, privacy, scalability, and responsiveness. However, increasing the robustness and accuracy of DCNNs comes at the price of increased computational cost. As result, implementing CNNs on embedded devices with real-time constraints is a challenge if the lowest power consumption shall be achieved. A solution to the challenge is to take advantage of the intra-device massive fine grain parallelism offered by these systems and benefit from the extensive concurrency exhibited by DCNN processing pipelines. The trick is to divide intensive tasks into smaller, weakly interacting batches subject to parallel processing. Referred to that, this paper has mainly two goals: 1) describe the implementation of a state-of-art technique to map DCNN most intensive tasks (dominated by multiply-and-accumulate ops) onto Orlando SoC, an ultra-low power heterogeneous multi cores developed by STMicroelectronics; 2) integrate the proposed implementation on a toolchain that allows deep learning developers to deploy DCNNs on low-power applications." @default.
- W2902431002 created "2018-12-11" @default.
- W2902431002 creator A5018246682 @default.
- W2902431002 creator A5021917926 @default.
- W2902431002 creator A5030840085 @default.
- W2902431002 creator A5031461662 @default.
- W2902431002 creator A5036123913 @default.
- W2902431002 creator A5047102959 @default.
- W2902431002 creator A5057121109 @default.
- W2902431002 creator A5068180033 @default.
- W2902431002 date "2018-09-01" @default.
- W2902431002 modified "2023-09-27" @default.
- W2902431002 title "Parallelized Convolutions for Embedded Ultra Low Power Deep Learning SoC" @default.
- W2902431002 cites W2155893237 @default.
- W2902431002 cites W2536365059 @default.
- W2902431002 cites W3118608800 @default.
- W2902431002 doi "https://doi.org/10.1109/rtsi.2018.8548362" @default.
- W2902431002 hasPublicationYear "2018" @default.
- W2902431002 type Work @default.
- W2902431002 sameAs 2902431002 @default.
- W2902431002 citedByCount "2" @default.
- W2902431002 countsByYear W29024310022019 @default.
- W2902431002 countsByYear W29024310022021 @default.
- W2902431002 crossrefType "proceedings-article" @default.
- W2902431002 hasAuthorship W2902431002A5018246682 @default.
- W2902431002 hasAuthorship W2902431002A5021917926 @default.
- W2902431002 hasAuthorship W2902431002A5030840085 @default.
- W2902431002 hasAuthorship W2902431002A5031461662 @default.
- W2902431002 hasAuthorship W2902431002A5036123913 @default.
- W2902431002 hasAuthorship W2902431002A5047102959 @default.
- W2902431002 hasAuthorship W2902431002A5057121109 @default.
- W2902431002 hasAuthorship W2902431002A5068180033 @default.
- W2902431002 hasConcept C104317684 @default.
- W2902431002 hasConcept C105339364 @default.
- W2902431002 hasConcept C108583219 @default.
- W2902431002 hasConcept C111919701 @default.
- W2902431002 hasConcept C113775141 @default.
- W2902431002 hasConcept C115903868 @default.
- W2902431002 hasConcept C118524514 @default.
- W2902431002 hasConcept C119857082 @default.
- W2902431002 hasConcept C120314980 @default.
- W2902431002 hasConcept C149635348 @default.
- W2902431002 hasConcept C154945302 @default.
- W2902431002 hasConcept C185592680 @default.
- W2902431002 hasConcept C2776214188 @default.
- W2902431002 hasConcept C2777062904 @default.
- W2902431002 hasConcept C2777904410 @default.
- W2902431002 hasConcept C41008148 @default.
- W2902431002 hasConcept C48044578 @default.
- W2902431002 hasConcept C55493867 @default.
- W2902431002 hasConcept C63479239 @default.
- W2902431002 hasConcept C79974875 @default.
- W2902431002 hasConcept C81363708 @default.
- W2902431002 hasConceptScore W2902431002C104317684 @default.
- W2902431002 hasConceptScore W2902431002C105339364 @default.
- W2902431002 hasConceptScore W2902431002C108583219 @default.
- W2902431002 hasConceptScore W2902431002C111919701 @default.
- W2902431002 hasConceptScore W2902431002C113775141 @default.
- W2902431002 hasConceptScore W2902431002C115903868 @default.
- W2902431002 hasConceptScore W2902431002C118524514 @default.
- W2902431002 hasConceptScore W2902431002C119857082 @default.
- W2902431002 hasConceptScore W2902431002C120314980 @default.
- W2902431002 hasConceptScore W2902431002C149635348 @default.
- W2902431002 hasConceptScore W2902431002C154945302 @default.
- W2902431002 hasConceptScore W2902431002C185592680 @default.
- W2902431002 hasConceptScore W2902431002C2776214188 @default.
- W2902431002 hasConceptScore W2902431002C2777062904 @default.
- W2902431002 hasConceptScore W2902431002C2777904410 @default.
- W2902431002 hasConceptScore W2902431002C41008148 @default.
- W2902431002 hasConceptScore W2902431002C48044578 @default.
- W2902431002 hasConceptScore W2902431002C55493867 @default.
- W2902431002 hasConceptScore W2902431002C63479239 @default.
- W2902431002 hasConceptScore W2902431002C79974875 @default.
- W2902431002 hasConceptScore W2902431002C81363708 @default.
- W2902431002 hasLocation W29024310021 @default.
- W2902431002 hasOpenAccess W2902431002 @default.
- W2902431002 hasPrimaryLocation W29024310021 @default.
- W2902431002 hasRelatedWork W1566962478 @default.
- W2902431002 hasRelatedWork W1688445866 @default.
- W2902431002 hasRelatedWork W1980333602 @default.
- W2902431002 hasRelatedWork W2731899572 @default.
- W2902431002 hasRelatedWork W2786106922 @default.
- W2902431002 hasRelatedWork W2920938200 @default.
- W2902431002 hasRelatedWork W2945690495 @default.
- W2902431002 hasRelatedWork W2996827035 @default.
- W2902431002 hasRelatedWork W4206841102 @default.
- W2902431002 hasRelatedWork W582556278 @default.
- W2902431002 isParatext "false" @default.
- W2902431002 isRetracted "false" @default.
- W2902431002 magId "2902431002" @default.
- W2902431002 workType "article" @default.