Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200219902> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3200219902 abstract "In recent years, with the development of computation capability in devices, companies are eager to investigate and utilize suitable ML/DL methods to improve their service quality. However, with the traditional learning strategy, companies need to first build up a powerful data center to collect and analyze data from the edge and then perform centralized model training, which turns out to be inefficient. Federated Learning has been introduced to solve this challenge. Because of its characteristics such as model-only exchange and parallel training, the technique can not only preserve user data privacy but also accelerate model training speed. The method can easily handle real-time data generated from the edge without taking up a lot of valuable network transmission resources. In this paper, we introduce an approach to end-to-end on-device Machine Learning by utilizing Federated Learning. We validate our approach with an important industrial use case in the field of autonomous driving vehicles, the wheel steering angle prediction. Our results show that Federated Learning can significantly improve the quality of local edge models and also reach the same accuracy level as compared to the traditional centralized Machine Learning approach without its negative effects. Furthermore, Federated Learning can accelerate model training speed and reduce the communication overhead, which proves that this approach has great strength when deploying ML/DL components to various real-world embedded systems." @default.
- W3200219902 created "2021-09-27" @default.
- W3200219902 creator A5010170972 @default.
- W3200219902 creator A5029808671 @default.
- W3200219902 creator A5049811300 @default.
- W3200219902 date "2021-07-18" @default.
- W3200219902 modified "2023-10-06" @default.
- W3200219902 title "End-to-End Federated Learning for Autonomous Driving Vehicles" @default.
- W3200219902 cites W1755205674 @default.
- W3200219902 cites W2559767995 @default.
- W3200219902 cites W2609731728 @default.
- W3200219902 cites W2740067745 @default.
- W3200219902 cites W2751023760 @default.
- W3200219902 cites W2912213068 @default.
- W3200219902 cites W2937443896 @default.
- W3200219902 cites W2944264045 @default.
- W3200219902 cites W2962804345 @default.
- W3200219902 cites W3007607795 @default.
- W3200219902 cites W3017201198 @default.
- W3200219902 doi "https://doi.org/10.1109/ijcnn52387.2021.9533808" @default.
- W3200219902 hasPublicationYear "2021" @default.
- W3200219902 type Work @default.
- W3200219902 sameAs 3200219902 @default.
- W3200219902 citedByCount "11" @default.
- W3200219902 countsByYear W32002199022022 @default.
- W3200219902 countsByYear W32002199022023 @default.
- W3200219902 crossrefType "proceedings-article" @default.
- W3200219902 hasAuthorship W3200219902A5010170972 @default.
- W3200219902 hasAuthorship W3200219902A5029808671 @default.
- W3200219902 hasAuthorship W3200219902A5049811300 @default.
- W3200219902 hasConcept C111472728 @default.
- W3200219902 hasConcept C111919701 @default.
- W3200219902 hasConcept C11413529 @default.
- W3200219902 hasConcept C119857082 @default.
- W3200219902 hasConcept C120314980 @default.
- W3200219902 hasConcept C138236772 @default.
- W3200219902 hasConcept C138885662 @default.
- W3200219902 hasConcept C154945302 @default.
- W3200219902 hasConcept C162307627 @default.
- W3200219902 hasConcept C202444582 @default.
- W3200219902 hasConcept C2779530757 @default.
- W3200219902 hasConcept C2779960059 @default.
- W3200219902 hasConcept C33923547 @default.
- W3200219902 hasConcept C41008148 @default.
- W3200219902 hasConcept C45374587 @default.
- W3200219902 hasConcept C67186912 @default.
- W3200219902 hasConcept C74296488 @default.
- W3200219902 hasConcept C77088390 @default.
- W3200219902 hasConcept C79974875 @default.
- W3200219902 hasConcept C9652623 @default.
- W3200219902 hasConceptScore W3200219902C111472728 @default.
- W3200219902 hasConceptScore W3200219902C111919701 @default.
- W3200219902 hasConceptScore W3200219902C11413529 @default.
- W3200219902 hasConceptScore W3200219902C119857082 @default.
- W3200219902 hasConceptScore W3200219902C120314980 @default.
- W3200219902 hasConceptScore W3200219902C138236772 @default.
- W3200219902 hasConceptScore W3200219902C138885662 @default.
- W3200219902 hasConceptScore W3200219902C154945302 @default.
- W3200219902 hasConceptScore W3200219902C162307627 @default.
- W3200219902 hasConceptScore W3200219902C202444582 @default.
- W3200219902 hasConceptScore W3200219902C2779530757 @default.
- W3200219902 hasConceptScore W3200219902C2779960059 @default.
- W3200219902 hasConceptScore W3200219902C33923547 @default.
- W3200219902 hasConceptScore W3200219902C41008148 @default.
- W3200219902 hasConceptScore W3200219902C45374587 @default.
- W3200219902 hasConceptScore W3200219902C67186912 @default.
- W3200219902 hasConceptScore W3200219902C74296488 @default.
- W3200219902 hasConceptScore W3200219902C77088390 @default.
- W3200219902 hasConceptScore W3200219902C79974875 @default.
- W3200219902 hasConceptScore W3200219902C9652623 @default.
- W3200219902 hasLocation W32002199021 @default.
- W3200219902 hasOpenAccess W3200219902 @default.
- W3200219902 hasPrimaryLocation W32002199021 @default.
- W3200219902 hasRelatedWork W2047259201 @default.
- W3200219902 hasRelatedWork W2082747552 @default.
- W3200219902 hasRelatedWork W2092071486 @default.
- W3200219902 hasRelatedWork W2391167130 @default.
- W3200219902 hasRelatedWork W3189674571 @default.
- W3200219902 hasRelatedWork W4242952987 @default.
- W3200219902 hasRelatedWork W4283067488 @default.
- W3200219902 hasRelatedWork W4293869292 @default.
- W3200219902 hasRelatedWork W4376106090 @default.
- W3200219902 hasRelatedWork W2460246254 @default.
- W3200219902 isParatext "false" @default.
- W3200219902 isRetracted "false" @default.
- W3200219902 magId "3200219902" @default.
- W3200219902 workType "article" @default.