Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366999913> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4366999913 abstract "Resource-constrained Edge Devices (EDs), e.g., IoT sensors and microcontroller units, are expected to make intelligent decisions using Deep Learning (DL) inference at the edge of the network. Toward this end, there is a significant research effort in developing tinyML models - Deep Learning (DL) models with reduced computation and memory storage requirements - that can be embedded on these devices. However, tinyML models have lower inference accuracy. On a different front, DNN partitioning and inference offloading techniques were studied for distributed DL inference between EDs and Edge Servers (ESs). In this paper, we explore Hierarchical Inference (HI), a novel approach proposed by Vishnu et al. 2023, arXiv:2304.00891v1 , for performing distributed DL inference at the edge. Under HI, for each data sample, an ED first uses a local algorithm (e.g., a tinyML model) for inference. Depending on the application, if the inference provided by the local algorithm is incorrect or further assistance is required from large DL models on edge or cloud, only then the ED offloads the data sample. At the outset, HI seems infeasible as the ED, in general, cannot know if the local inference is sufficient or not. Nevertheless, we present the feasibility of implementing HI for machine fault detection and image classification applications. We demonstrate its benefits using quantitative analysis and argue that using HI will result in low latency, bandwidth savings, and energy savings in edge AI systems." @default.
- W4366999913 created "2023-04-27" @default.
- W4366999913 creator A5001024916 @default.
- W4366999913 creator A5012736869 @default.
- W4366999913 creator A5025956807 @default.
- W4366999913 creator A5051095866 @default.
- W4366999913 creator A5063986838 @default.
- W4366999913 creator A5081058005 @default.
- W4366999913 date "2023-04-23" @default.
- W4366999913 modified "2023-10-14" @default.
- W4366999913 title "The Case for Hierarchical Deep Learning Inference at the Network Edge" @default.
- W4366999913 doi "https://doi.org/10.48550/arxiv.2304.11763" @default.
- W4366999913 hasPublicationYear "2023" @default.
- W4366999913 type Work @default.
- W4366999913 citedByCount "0" @default.
- W4366999913 crossrefType "posted-content" @default.
- W4366999913 hasAuthorship W4366999913A5001024916 @default.
- W4366999913 hasAuthorship W4366999913A5012736869 @default.
- W4366999913 hasAuthorship W4366999913A5025956807 @default.
- W4366999913 hasAuthorship W4366999913A5051095866 @default.
- W4366999913 hasAuthorship W4366999913A5063986838 @default.
- W4366999913 hasAuthorship W4366999913A5081058005 @default.
- W4366999913 hasBestOaLocation W43669999131 @default.
- W4366999913 hasConcept C108583219 @default.
- W4366999913 hasConcept C111919701 @default.
- W4366999913 hasConcept C119857082 @default.
- W4366999913 hasConcept C124101348 @default.
- W4366999913 hasConcept C138236772 @default.
- W4366999913 hasConcept C154945302 @default.
- W4366999913 hasConcept C162307627 @default.
- W4366999913 hasConcept C186108316 @default.
- W4366999913 hasConcept C195975749 @default.
- W4366999913 hasConcept C2776214188 @default.
- W4366999913 hasConcept C2778456923 @default.
- W4366999913 hasConcept C31258907 @default.
- W4366999913 hasConcept C41008148 @default.
- W4366999913 hasConcept C58166 @default.
- W4366999913 hasConcept C79974875 @default.
- W4366999913 hasConcept C93996380 @default.
- W4366999913 hasConcept C97385483 @default.
- W4366999913 hasConceptScore W4366999913C108583219 @default.
- W4366999913 hasConceptScore W4366999913C111919701 @default.
- W4366999913 hasConceptScore W4366999913C119857082 @default.
- W4366999913 hasConceptScore W4366999913C124101348 @default.
- W4366999913 hasConceptScore W4366999913C138236772 @default.
- W4366999913 hasConceptScore W4366999913C154945302 @default.
- W4366999913 hasConceptScore W4366999913C162307627 @default.
- W4366999913 hasConceptScore W4366999913C186108316 @default.
- W4366999913 hasConceptScore W4366999913C195975749 @default.
- W4366999913 hasConceptScore W4366999913C2776214188 @default.
- W4366999913 hasConceptScore W4366999913C2778456923 @default.
- W4366999913 hasConceptScore W4366999913C31258907 @default.
- W4366999913 hasConceptScore W4366999913C41008148 @default.
- W4366999913 hasConceptScore W4366999913C58166 @default.
- W4366999913 hasConceptScore W4366999913C79974875 @default.
- W4366999913 hasConceptScore W4366999913C93996380 @default.
- W4366999913 hasConceptScore W4366999913C97385483 @default.
- W4366999913 hasLocation W43669999131 @default.
- W4366999913 hasOpenAccess W4366999913 @default.
- W4366999913 hasPrimaryLocation W43669999131 @default.
- W4366999913 hasRelatedWork W2945616868 @default.
- W4366999913 hasRelatedWork W2952134957 @default.
- W4366999913 hasRelatedWork W3015440700 @default.
- W4366999913 hasRelatedWork W3082895349 @default.
- W4366999913 hasRelatedWork W3097182782 @default.
- W4366999913 hasRelatedWork W3110617657 @default.
- W4366999913 hasRelatedWork W3185591558 @default.
- W4366999913 hasRelatedWork W3211127556 @default.
- W4366999913 hasRelatedWork W4296943520 @default.
- W4366999913 hasRelatedWork W4302363080 @default.
- W4366999913 isParatext "false" @default.
- W4366999913 isRetracted "false" @default.
- W4366999913 workType "article" @default.