Revisiting Edge AI: Opportunities and Challenges

Tobias Meuser*, Lauri Lovén, Monowar Bhuyan, Shishir G. Patil, Schahram Dusdar, Atakan Aral, Suzan Bayhan, Christian Becker, Eyal de Lara, Aaron Yi Ding, Janick Edinger, James Gross, Nitinder Mohan, Andy Pimentel, Etienne Riviere, Henning Schulzrinne, Pieter Simoens, Gurkan Solmaz, Michael Welzl

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

29 Downloads (Pure)

Abstract

Edge artificial intelligence (AI) is an innovative computing paradigm that aims to shift the training and inference of machine learning models to the edge of the network. This paradigm offers the opportunity to significantly impact our everyday lives with new services such as autonomous driving and ubiquitous personalized health care. Nevertheless, bringing intelligence to the edge involves several major challenges, which include the need to constrain model architecture designs, the secure distribution and execution of the trained models, and the substantial network load required to distribute the models and data collected for training. In this article, we highlight key aspects in the development of edge AI in the past and connect them to current challenges. This article aims to identify research opportunities for edge AI, relevant to bring together the research in the fields of artificial intelligence and edge computing.
Original languageEnglish
Pages (from-to)49-59
Number of pages11
JournalIEEE internet computing
Volume28
Issue number4
Early online dateApr 2024
DOIs
Publication statusPublished - Jul 2024

Keywords

  • 2024 OA procedure

Fingerprint

Dive into the research topics of 'Revisiting Edge AI: Opportunities and Challenges'. Together they form a unique fingerprint.

Cite this