Séminaire ICE : « Resource-Constrained Training for Edge Intelligence »

Abstract

AI in telecommunications is currently at its all-time high as a solution to optimize and automate networks, keep them healthy and secure, while reducing operational costs. AI not only provides an ability for devices and systems to perceive, deduct, and act intuitively and intelligently, but also changes how we approach and solve technical challenges.
Future 6G networks with their massive connectivity will elevate object capabilities to new levels as well as expand intelligence into new devices. With the proliferation of connected devices and the role of on-device intelligence becoming ever more important, the transformation of AI into fully distributed intelligence will be one of the keys to realize the full potential of future 6G networks.

In this talk, we will present the on-device learning approach through algorithm-system co-design which adapts pre-trained AI model to newly collected data after deployment. By training and adapting locally at the edge, the AI model can learn to improve its predictions and achieve continuous learning and user personalization.

BIO
Van-Tam Nguyen, received the Diplôme d’Ingenieur from CentraleSupelec, the M.Sc. degree in automatic and signal processing from University Paris XI, the graduation degree in image processing from EPFL, Switzerland, in 2000, the Ph.D. degree in communications and electronic from Ecole Nationnale Superieure des Telecommunications (Telecom Paris) in 2004, and the H.D.R. degree from University Paris VI in 2016. He has been at Telecom Paris since 2005, where he is currently a professor. He was a Rank A Guest Researcher at NICT, Japan (2012-2013). He has held visiting positions at UC Berkeley (2013-2016) and Stanford (2016-2017). He was director of Intek Institute (2018) and CEO of TAM-AI Co. Ltd (2019-2021). In 2022, he become the head of the communications and electronic department at Télécom Paris, where his research interests includes ADCs, flexible receiver, neural network, tiny ML, embedded and distributed AI and AIoT. He has authored or co-authored around 100 publications, five patents and one technology transfer. He received a Senior Marie Curie Fellowship from the European Commission in 2015.