Roadmap for edge AI: a Dagstuhl perspective

Roadmap for edge AI: a Dagstuhl perspective

Abstract

Edge AI deploys AI methods and capabilities across edge computing resources. Edge AI adapts to data-driven applications, enhances network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The edge AI research community investigates novel ML methods and network systems for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The paper summarises the discussions of the Dagstuhl Seminar 21342.

Grafik Top
Authors
  • Ding, Aaron Yi
  • Peltonen, Ella
  • Meuser, Tobias
  • Aral, Atakan
  • Becker, Christian
  • Dustdar, Schahram
  • Hiessl, Thomas
  • Kranzlmüller, Dieter
  • Liyanage, Madhusanka
  • Maghsudi, Setareh
  • Mohan, Nitinder
  • Ott, Jörg
  • Rellermeyer, Jan S.
  • Schulte, Stefan
  • Schulzrinne, Henning
  • Solmaz, Gürkan
  • Tarkoma, Sasu
  • Varghese, Blesson
  • Wolf, Lars
Grafik Top
Projects
Grafik Top
Shortfacts
Category
Journal Paper
Divisions
Scientific Computing
Subjects
Datenverarbeitungsmanagement
Kuenstliche Intelligenz
Rechnerperipherie, Datenkommunikationshardware
Systemarchitektur Allgemeines
Journal or Publication Title
ACM SIGCOMM Computer Communication Review
ISSN
0146-4833
Publisher
ACM
Page Range
pp. 28-33
Number
1
Volume
52
Date
January 2022
Official URL
http://dx.doi.org/10.1145/3523230.3523235
Export
Grafik Top