Matches in SemOpenAlex for { <https://semopenalex.org/work/W3168541340> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3168541340 abstract "Significant advances in hardware capabilities and the availability of enormous data sets have led to the rise and penetration of artificial intelligence (AI) and deep learning (DL) in various domains. Considerable efforts have been put forth in academia and industry to make these computationally demanding DL tasks work on resource-constrained edge devices. However, performing DL tasks on edge devices is still challenging due to the diversity of DNN (Deep Neural Networks) architectures and heterogeneity of edge devices. This study evaluates and characterizes the performance and resource heterogeneity in various edge devices for performing DL tasks. We benchmark various DNN models for image classification on a set of edge devices ranging from the widely popular and relatively less powerful Raspberry Pi to GPU-equipped high-performance edge devices like Jetson Xavier NX. We also compare and contrast the performance of three widely-used DL frameworks when used in these edge devices. We report DL inference throughput, CPU and memory usage, power consumption, and frameworks' initialization overhead, which are the most critical factors for characterizing DL tasks on edge devices. Additionally, we provide our insights and findings, which will provide a better idea of how compatible or feasible edge devices are for running DL applications." @default.
- W3168541340 created "2021-06-22" @default.
- W3168541340 creator A5051928424 @default.
- W3168541340 creator A5077150320 @default.
- W3168541340 creator A5082188602 @default.
- W3168541340 creator A5084996425 @default.
- W3168541340 date "2020-06-21" @default.
- W3168541340 modified "2023-09-23" @default.
- W3168541340 title "Characterizing Resource Heterogeneity in Edge Devices for Deep Learning Inferences" @default.
- W3168541340 cites W2117539524 @default.
- W3168541340 cites W2194775991 @default.
- W3168541340 cites W2945856475 @default.
- W3168541340 cites W2988271927 @default.
- W3168541340 cites W3009018976 @default.
- W3168541340 cites W3016842236 @default.
- W3168541340 cites W3018955265 @default.
- W3168541340 cites W3046289513 @default.
- W3168541340 cites W4236099117 @default.
- W3168541340 doi "https://doi.org/10.1145/3452411.3464446" @default.
- W3168541340 hasPublicationYear "2020" @default.
- W3168541340 type Work @default.
- W3168541340 sameAs 3168541340 @default.
- W3168541340 citedByCount "0" @default.
- W3168541340 crossrefType "proceedings-article" @default.
- W3168541340 hasAuthorship W3168541340A5051928424 @default.
- W3168541340 hasAuthorship W3168541340A5077150320 @default.
- W3168541340 hasAuthorship W3168541340A5082188602 @default.
- W3168541340 hasAuthorship W3168541340A5084996425 @default.
- W3168541340 hasConcept C108583219 @default.
- W3168541340 hasConcept C119857082 @default.
- W3168541340 hasConcept C154945302 @default.
- W3168541340 hasConcept C162307627 @default.
- W3168541340 hasConcept C206345919 @default.
- W3168541340 hasConcept C2522767166 @default.
- W3168541340 hasConcept C31258907 @default.
- W3168541340 hasConcept C41008148 @default.
- W3168541340 hasConceptScore W3168541340C108583219 @default.
- W3168541340 hasConceptScore W3168541340C119857082 @default.
- W3168541340 hasConceptScore W3168541340C154945302 @default.
- W3168541340 hasConceptScore W3168541340C162307627 @default.
- W3168541340 hasConceptScore W3168541340C206345919 @default.
- W3168541340 hasConceptScore W3168541340C2522767166 @default.
- W3168541340 hasConceptScore W3168541340C31258907 @default.
- W3168541340 hasConceptScore W3168541340C41008148 @default.
- W3168541340 hasLocation W31685413401 @default.
- W3168541340 hasOpenAccess W3168541340 @default.
- W3168541340 hasPrimaryLocation W31685413401 @default.
- W3168541340 hasRelatedWork W2922457425 @default.
- W3168541340 hasRelatedWork W3014300295 @default.
- W3168541340 hasRelatedWork W3164822677 @default.
- W3168541340 hasRelatedWork W3215138031 @default.
- W3168541340 hasRelatedWork W4223943233 @default.
- W3168541340 hasRelatedWork W4225161397 @default.
- W3168541340 hasRelatedWork W4250304930 @default.
- W3168541340 hasRelatedWork W4299487748 @default.
- W3168541340 hasRelatedWork W4309045103 @default.
- W3168541340 hasRelatedWork W4312200629 @default.
- W3168541340 isParatext "false" @default.
- W3168541340 isRetracted "false" @default.
- W3168541340 magId "3168541340" @default.
- W3168541340 workType "article" @default.