Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904990161> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2904990161 endingPage "3789" @default.
- W2904990161 startingPage "3778" @default.
- W2904990161 abstract "Deep learning is a state-of-the-art approach that provides highly accurate inference for many cyber-physical systems (CPS) such as autonomous cars and robots. Deep learning inference often needs to be performed locally on mobile and embedded devices, rather than in the cloud, to address concerns such as latency, power consumption, and limited bandwidth. However, existing approaches have focused on delivering “best-effort” performance to resource-constrained mobile embedded devices, resulting in unpredictable performance under highly variable environments of CPS. In this paper, we propose a novel deep learning inference runtime, called DeepRT, that supports multiple QoS objectives simultaneously against unpredictable workloads. In DeepRT, the multiple inputs/multiple outputs (MIMO) modeling and control methodology is proposed as a primary tool to support multiple QoS goals including the inference latency and power consumption. DeepRT’s MIMO controller coordinates multiple computing resources, such as CPUs and GPUs, by capturing their close interactions and effects on multiple QoS objectives. We demonstrate the viability of DeepRT’s QoS management architecture by implementing a prototype of DeepRT. The evaluation results demonstrate that, compared with baseline approaches, DeepRT can support the desired inference latency as well as power consumption for various deep learning models in a highly robust manner." @default.
- W2904990161 created "2018-12-22" @default.
- W2904990161 creator A5006563419 @default.
- W2904990161 creator A5054582945 @default.
- W2904990161 date "2019-01-01" @default.
- W2904990161 modified "2023-09-26" @default.
- W2904990161 title "Power- and Time-Aware Deep Learning Inference for Mobile Embedded Devices" @default.
- W2904990161 cites W1495021188 @default.
- W2904990161 cites W1903029394 @default.
- W2904990161 cites W1996901117 @default.
- W2904990161 cites W2015244008 @default.
- W2904990161 cites W2067523571 @default.
- W2904990161 cites W2074084090 @default.
- W2904990161 cites W2080663940 @default.
- W2904990161 cites W2096441239 @default.
- W2904990161 cites W2097117768 @default.
- W2904990161 cites W2099961254 @default.
- W2904990161 cites W2109488193 @default.
- W2904990161 cites W2112796928 @default.
- W2904990161 cites W2126356851 @default.
- W2904990161 cites W2135099885 @default.
- W2904990161 cites W2151223307 @default.
- W2904990161 cites W2153380308 @default.
- W2904990161 cites W2285660444 @default.
- W2904990161 cites W2392395307 @default.
- W2904990161 cites W2529165666 @default.
- W2904990161 cites W2562035485 @default.
- W2904990161 cites W2606722458 @default.
- W2904990161 cites W2615131227 @default.
- W2904990161 cites W2777215928 @default.
- W2904990161 cites W2786171709 @default.
- W2904990161 cites W2883839680 @default.
- W2904990161 cites W3003587919 @default.
- W2904990161 cites W4236853429 @default.
- W2904990161 doi "https://doi.org/10.1109/access.2018.2887099" @default.
- W2904990161 hasPublicationYear "2019" @default.
- W2904990161 type Work @default.
- W2904990161 sameAs 2904990161 @default.
- W2904990161 citedByCount "5" @default.
- W2904990161 countsByYear W29049901612019 @default.
- W2904990161 countsByYear W29049901612020 @default.
- W2904990161 countsByYear W29049901612021 @default.
- W2904990161 countsByYear W29049901612022 @default.
- W2904990161 crossrefType "journal-article" @default.
- W2904990161 hasAuthorship W2904990161A5006563419 @default.
- W2904990161 hasAuthorship W2904990161A5054582945 @default.
- W2904990161 hasBestOaLocation W29049901611 @default.
- W2904990161 hasConcept C108583219 @default.
- W2904990161 hasConcept C119857082 @default.
- W2904990161 hasConcept C121332964 @default.
- W2904990161 hasConcept C136764020 @default.
- W2904990161 hasConcept C154945302 @default.
- W2904990161 hasConcept C163258240 @default.
- W2904990161 hasConcept C186967261 @default.
- W2904990161 hasConcept C2776214188 @default.
- W2904990161 hasConcept C41008148 @default.
- W2904990161 hasConcept C62520636 @default.
- W2904990161 hasConceptScore W2904990161C108583219 @default.
- W2904990161 hasConceptScore W2904990161C119857082 @default.
- W2904990161 hasConceptScore W2904990161C121332964 @default.
- W2904990161 hasConceptScore W2904990161C136764020 @default.
- W2904990161 hasConceptScore W2904990161C154945302 @default.
- W2904990161 hasConceptScore W2904990161C163258240 @default.
- W2904990161 hasConceptScore W2904990161C186967261 @default.
- W2904990161 hasConceptScore W2904990161C2776214188 @default.
- W2904990161 hasConceptScore W2904990161C41008148 @default.
- W2904990161 hasConceptScore W2904990161C62520636 @default.
- W2904990161 hasFunder F4320321363 @default.
- W2904990161 hasFunder F4320322120 @default.
- W2904990161 hasLocation W29049901611 @default.
- W2904990161 hasOpenAccess W2904990161 @default.
- W2904990161 hasPrimaryLocation W29049901611 @default.
- W2904990161 hasRelatedWork W2567271240 @default.
- W2904990161 hasRelatedWork W2922457425 @default.
- W2904990161 hasRelatedWork W3009238340 @default.
- W2904990161 hasRelatedWork W3014300295 @default.
- W2904990161 hasRelatedWork W3164822677 @default.
- W2904990161 hasRelatedWork W3215138031 @default.
- W2904990161 hasRelatedWork W4210805261 @default.
- W2904990161 hasRelatedWork W4223943233 @default.
- W2904990161 hasRelatedWork W4250304930 @default.
- W2904990161 hasRelatedWork W4299487748 @default.
- W2904990161 hasVolume "7" @default.
- W2904990161 isParatext "false" @default.
- W2904990161 isRetracted "false" @default.
- W2904990161 magId "2904990161" @default.
- W2904990161 workType "article" @default.