TECoSA Seminar – Edge Intelligence: The Surprises, Risks and Lessons
April 1, 15:00 – 16:30
We aim to bring you a TECoSA Seminar at kl.15 on the first Thursday of each month. This Spring they will be on-line, and all are welcome to join. Each invited speaker will talk for about 40 minutes, followed by a panel discussion coordinated by TECoSA members.
The sixth speaker in our series is Asst Prof Aaron Ding, Assistant Professor in Engineering Systems & Services at TU Delft and Adjunct Professor in Computer Science at University of Helsinki .You can read more at: http://homepage.tudelft.nl/8e79t/
Panel: James Gross (Chair), industry and academic reps tbc
Please email firstname.lastname@example.org to register!
Edge Intelligence: The Surprises, Risks and Lessons
ABSTRACT: Similar to the transition from Cloud to Cloud Intelligence, we are witnessing a fast evolution from the Internet of Things to the Internet of Intelligent Things (IoIT). The IoIT paves the way to a programmable infrastructure that can consolidate the power of the Cloud and distributed computing resources to enhance performance, resilience, and quality of experience for users. The envisioned programmable infrastructure has the potential to bring our society to the next level, by making it more intelligent, more sustainable, healthier, and forging innovations in numerous fields such as autonomous driving, smart energy, logistics, and e-health.
Behind the curtains, one of the key enablers for this vision is Edge Intelligence – a powerful combination of edge computing and artificial intelligence. This talk will present my investigations on Edge Intelligence with a system flavor. Besides sharing my first-hand experience of system design and development, the talk will reveal several pitfalls and lessons learned through live cases. The goal is twofold: 1) to disclose blind spots and interesting directions that deserve further investigations in our community, and 2) to share my observations on doing system research in such “buzzword bingo” domain, especially what could hinder us from transferring the mostly fun system work into solid scientific outcome.