Revisiting Edge AI: Opportunities and Challenges
Tobias Meuser (Technische Universität Darmstadt)
Lauri Lovén (University of Oulu)
M Bhuyan (Umeå University)
Shishir G. Patil (University of California)
Schahram Dustdar (Technische Universität Wien)
Atakan Aral (Umeå University)
Suzan Bayhan (University of Twente)
Aaron Yi Ding (TU Delft - Information and Communication Technology)
Nitinder Mohan (Technische Universität München)
undefined More Authors (External organisation)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
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.