Revisiting Edge AI: Opportunities and Challenges
(2024) IEEE Internet Computing — Vol. 28, n° 4, p. 49-59 (2024)
Files
Revisiting_Edge_AI_Opportunities_and_Challenges-2.pdf
Open Access - Adobe PDF
- 601.56 KB
Details
- Authors
Meuser, Tobias 
Lovén, Lauri Bhuyan, Monowar Patil, Shishir G. Welzl, Michael
- 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.
- Affiliations
Citations
Meuser, T., Lovén, L., Bhuyan, M., Patil, S. G., Dustdar, S., Aral, A., Bayhan, S., Becker, C., Lara, E. d., Ding, A. Y., Edinger, J., Gross, J., Mohan, N., Pimentel, A. D., Riviere, E., Schulzrinne, H., Simoens, P., Solmaz, G., & Welzl, M. (2024). Revisiting Edge AI: Opportunities and Challenges. IEEE Internet Computing, 28(4), 49-59. https://doi.org/10.1109/mic.2024.3383758 (Original work published 2024)