Bringing Intelligence to the Edge: The Fun, Lessons and Outlook

Date and time: 
Thu, Jan 27 2022 - 12:00pm
Dr. Aaron Ding
Delft University of Technology, the Netherlands

Similar to the progression from cloud computing to cloud intelligence, we are witnessing a fast evolution from edge computing to edge intelligence (aka Edge AI).  As a research branch that merges distributed computing, data analytics, embedded and distributed ML, Edge AI is envisioned to provide adaptation for data-driven applications, enhance network access performance, and enable the creation, optimization and deployment of distributed AI/ML pipelines with the given quality of experience, trust, security and privacy targets.

However, despite of all the promises ahead, the path to realize Edge AI is far from straightforward - although we could still view the hurdles as opportunities in an optimistic manner. This talk will present my on-going research exploration to bring the 'intelligence' to the edge with a system flavor. Besides sharing my first-hand experience, the talk will reveal pitfalls and lessons learned through live cases. The goal is twofold: 1) to reveal blind spots and interesting directions that deserve further investigations from the community, and 2) to share my reflections about conducting research on such 'buzzword bingo' topic, especially how to better engage with and evolve the community.


Dr. Aaron Ding is leading the Cyber-Physical Intelligence (CPI) Lab in the Dept. of Engineering Systems and Services at TU Delft. As a Tenured Faculty (UD1) at TU Delft and Associate Professor (Docent) in Computer Science at the University of Helsinki, he has over 14 years of R&D experience across EU, UK and USA. Prior to TU Delft, he has worked at TU Munich with Jörg Ott, at Columbia University with Henning Schulzrinne, at University of Cambridge with Jon Crowcroft. He obtained undergrad MSc and PhD degrees all with distinctions (5/5) from the Department of Computer Science (Birthplace of Linux) at the University of Helsinki. His PhD is supervised by Prof. Sasu Tarkoma and Prof. Jon Crowcroft at Cambridge. As funded by Nokia Foundation, vital part of his PhD programme is completed physically at University of Cambridge and at Columbia University in New York. (Biography and image from .)