FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887275656> ?p ?o ?g. }

• W2887275656 abstract "Deep Learning (DL) applications are gaining momentum in the realm of Artificial Intelligence, particularly after GPUs have demonstrated remarkable skills for accelerating their challenging computational requirements. Within this context, Convolutional Neural Network (CNN) models constitute a representative example of success on a wide set of complex applications, particularly on datasets where the target can be represented through a hierarchy of local features of increasing semantic complexity. In most of the real scenarios, the roadmap to improve results relies on CNN settings involving brute force computation, and researchers have lately proven Nvidia GPUs to be one of the best hardware counterparts for acceleration. Our work complements those findings with an energy study on critical parameters for the deployment of CNNs on flagship image and video applications: object recognition and people identification by gait, respectively. We evaluate energy consumption on four different networks based on the two most popular ones (ResNet/AlexNet): ResNet (167 layers), a 2D CNN (15 layers), a CaffeNet (25 layers) and a ResNetIm (94 layers) using batch sizes of 64, 128 and 256, and then correlate those with speed-up and accuracy to determine optimal settings. Experimental results on a multi-GPU server endowed with twin Maxwell and twin Pascal Titan X GPUs demonstrate that energy correlates with performance and that Pascal may have up to 40% gains versus Maxwell. Larger batch sizes extend performance gains and energy savings, but we have to keep an eye on accuracy, which sometimes shows a preference for small batches. We expect this work to provide a preliminary guidance for a wide set of CNN and DL applications in modern HPC times, where the GFLOPS/w ratio constitutes the primary goal." @default.
• W2887275656 created "2018-08-22" @default.
• W2887275656 creator A5001884113 @default.
• W2887275656 creator A5029567783 @default.
• W2887275656 creator A5040312714 @default.
• W2887275656 creator A5041004091 @default.
• W2887275656 creator A5042354417 @default.
• W2887275656 date "2018-08-01" @default.
• W2887275656 modified "2023-10-01" @default.
• W2887275656 title "Energy-based Tuning of Convolutional Neural Networks on Multi-GPUs" @default.
• W2887275656 cites W1244930767 @default.
• W2887275656 cites W1755205674 @default.
• W2887275656 cites W1963882359 @default.
• W2887275656 cites W1984031350 @default.
• W2887275656 cites W2003529142 @default.
• W2887275656 cites W2022508996 @default.
• W2887275656 cites W2082880628 @default.
• W2887275656 cites W2094756095 @default.
• W2887275656 cites W2097117768 @default.
• W2887275656 cites W2101926813 @default.
• W2887275656 cites W2112796928 @default.
• W2887275656 cites W2119821739 @default.
• W2887275656 cites W2124386111 @default.
• W2887275656 cites W2126574503 @default.
• W2887275656 cites W2144982973 @default.
• W2887275656 cites W2194775991 @default.
• W2887275656 cites W2287234120 @default.
• W2887275656 cites W2346541858 @default.
• W2887275656 cites W2431931973 @default.
• W2887275656 cites W2513383847 @default.
• W2887275656 cites W2514858228 @default.
• W2887275656 cites W2517073324 @default.
• W2887275656 cites W2736230459 @default.
• W2887275656 cites W2736596806 @default.
• W2887275656 cites W2737244778 @default.
• W2887275656 cites W2754666677 @default.
• W2887275656 cites W2759777444 @default.
• W2887275656 cites W2796013597 @default.
• W2887275656 cites W2950094539 @default.
• W2887275656 cites W2952186347 @default.
• W2887275656 cites W2953106684 @default.
• W2887275656 cites W3106250896 @default.
• W2887275656 cites W3118608800 @default.
• W2887275656 hasPublicationYear "2018" @default.
• W2887275656 type Work @default.
• W2887275656 sameAs 2887275656 @default.
• W2887275656 citedByCount "0" @default.
• W2887275656 crossrefType "posted-content" @default.
• W2887275656 hasAuthorship W2887275656A5001884113 @default.
• W2887275656 hasAuthorship W2887275656A5029567783 @default.
• W2887275656 hasAuthorship W2887275656A5040312714 @default.
• W2887275656 hasAuthorship W2887275656A5041004091 @default.
• W2887275656 hasAuthorship W2887275656A5042354417 @default.
• W2887275656 hasConcept C105339364 @default.
• W2887275656 hasConcept C108583219 @default.
• W2887275656 hasConcept C111919701 @default.
• W2887275656 hasConcept C113775141 @default.
• W2887275656 hasConcept C115537543 @default.
• W2887275656 hasConcept C119599485 @default.
• W2887275656 hasConcept C119857082 @default.
• W2887275656 hasConcept C127413603 @default.
• W2887275656 hasConcept C13164978 @default.
• W2887275656 hasConcept C146978453 @default.
• W2887275656 hasConcept C149635348 @default.
• W2887275656 hasConcept C154945302 @default.
• W2887275656 hasConcept C165696696 @default.
• W2887275656 hasConcept C173608175 @default.
• W2887275656 hasConcept C18903297 @default.
• W2887275656 hasConcept C199360897 @default.
• W2887275656 hasConcept C205711294 @default.
• W2887275656 hasConcept C2742236 @default.
• W2887275656 hasConcept C2778100165 @default.
• W2887275656 hasConcept C2780165032 @default.
• W2887275656 hasConcept C38652104 @default.
• W2887275656 hasConcept C41008148 @default.
• W2887275656 hasConcept C42935608 @default.
• W2887275656 hasConcept C50644808 @default.
• W2887275656 hasConcept C50805821 @default.
• W2887275656 hasConcept C68339613 @default.
• W2887275656 hasConcept C75608658 @default.
• W2887275656 hasConcept C81363708 @default.
• W2887275656 hasConcept C86803240 @default.
• W2887275656 hasConceptScore W2887275656C105339364 @default.
• W2887275656 hasConceptScore W2887275656C108583219 @default.
• W2887275656 hasConceptScore W2887275656C111919701 @default.
• W2887275656 hasConceptScore W2887275656C113775141 @default.
• W2887275656 hasConceptScore W2887275656C115537543 @default.
• W2887275656 hasConceptScore W2887275656C119599485 @default.
• W2887275656 hasConceptScore W2887275656C119857082 @default.
• W2887275656 hasConceptScore W2887275656C127413603 @default.
• W2887275656 hasConceptScore W2887275656C13164978 @default.
• W2887275656 hasConceptScore W2887275656C146978453 @default.
• W2887275656 hasConceptScore W2887275656C149635348 @default.
• W2887275656 hasConceptScore W2887275656C154945302 @default.
• W2887275656 hasConceptScore W2887275656C165696696 @default.
• W2887275656 hasConceptScore W2887275656C173608175 @default.
• W2887275656 hasConceptScore W2887275656C18903297 @default.
• W2887275656 hasConceptScore W2887275656C199360897 @default.
• W2887275656 hasConceptScore W2887275656C205711294 @default.
• W2887275656 hasConceptScore W2887275656C2742236 @default.

• next