DNN Partitioning for Inference Throughput Acceleration at the Edge

Deep neural network (DNN) inference on streaming data requires computing resources to satisfy inference throughput requirements. However, latency and privacy sensitive deep learning applications cannot afford to offload computation to remote clouds because of the implied transmission cost and lack o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access Jg. 11; S. 52236 - 52249
Hauptverfasser:	Feltin, Thomas, Marcho, Leo, Cordero-Fuertes, Juan-Antonio, Brockners, Frank, Clausen, Thomas H.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.01.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Artificial intelligence Artificial neural networks Cloud computing Computation offloading Computational modeling Computer Science Deep learning Design optimization Distributed artificial intelligence Edge computing Inference Machine learning Neural networks Optimization Partitioning scheduling and task partitioning Throughput
ISSN:	2169-3536, 2169-3536
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!