IEEE Internet Computing 
2024

Impact Factor: 3.7

Revisiting Edge AI: Opportunities and Challenges

Abstract:

Edge 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 healthcare. 
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


Pre-camera PDF 

IEEE Library Open Access

@article{Meuser:IC2024,
  author={T Meuser, L Loven, M Bhuyan, S Patil, S Dustdar, A Aral, S Bayhan, C Becker, E de Lara, Aaron Ding, J Edinger, J Gross, N Mohan, A Pimentel, E Riviere, H Schulzrinne, P Simoens, G Solmaz, M Welzl},
  journal={IEEE Internet Computing}, 
  title={Revisiting Edge AI: Opportunities and Challenges}, 
  year={2024}
}

T Meuser, L Loven, M Bhuyan, S Patil, S Dustdar, A Aral, S Bayhan, C Becker, E de Lara, Aaron Ding, J Edinger, J Gross, N Mohan, A Pimentel, E Riviere, H Schulzrinne, P Simoens, G Solmaz, M Welzl, "Revisiting Edge AI: Opportunities and Challenges", in IEEE Internet Computing, 2024.