In recent years, the emergence of edge computing has reduced the costs associated with transferring data to centralized cloud servers by relocating data processing to edge devices placed within the local network. Edge computing is a promising solution for distributed applications requiring privacy and real-time data processing capability with minimal delays. However, utilizing the full potential of this paradigm is not feasible without the capabilities to analyse complex data and generate new content. This talk investigated the challenges of deploying generative Artificial Intelligence (AI) at the edge to enhance privacy and efficiently use network and computational resources. By considering the limitations of edge environments and exploring current solutions for optimizing AI models on resource-limited devices, this talk addressed the challenges of implementing efficient distributed learning for generative AI applications, such as Large Language Models.
Speaker: Albert Y. Zomaya, University of Sydney, Australia
Moderators:
Ian F. Akyildiz, Editor-in-Chief, ITU Journal on Future and Evolving Technologies (ITU-J FET)
Alessia Magliarditi, ITU Journal and ITU-T Academia Coordinator, International Telecommunication Union (ITU)
This webinar is organized by the ITU Journal on Future and Evolving Technologies (ITU J-FET), an international journal providing complete coverage of all communications and networking paradigms, free of charge for both readers and authors. The ITU Journal considers yet-to-be-published papers addressing fundamental and applied research. Open topics for future research will be discussed. See more information on the ITU Journal webinar series and the open Calls for Papers for the upcoming ITU Journal’s issues here.
👉 Discover the ITU Journal on Future and Evolving Technologies (ITU J-FET) here: [ Ссылка ]
📅 Explore the full ITU Journal webinar series programme here: [ Ссылка ]...
#ITU #ITUJFET
