Join us for a deep dive into the future of machine learning at the edge. Dr Blesson Varghese will explore how ML models can be trained directly on the devices where they’re deployed, unlocking new possibilities for efficiency, privacy, and responsiveness.

Drawing on cutting-edge research from the Edge Computing Hub, Dr Varghese will share practical techniques for overcoming computation and communication bottlenecks, enabling ML to run on small form-factor devices.

Whether you’re working in AI, edge computing, or embedded systems, this is a session you won’t want to miss.

When: November 19th, 2 PM GMT
Where: Zoom – https://newcastleuniversity.zoom.us/j/88697614523

Abstract: The premise of on-device learning is to train machine learning (ML) models directly on devices where they are deployed. In this talk, I will discuss our experience with making ML work efficiently on a variety of hardware platforms. I will present a range of techniques developed in my lab that address computation and communication bottlenecks to make ML systems work on small form-factor devices. These patented works highlight that the new techniques offer viable and promising alternatives to conventional ML for small devices that should be explored further.

Speaker biography: Dr Blesson Varghese is a Reader in Computer Science at the University of St Andrews. He has held a Royal Society fellowship to British Telecommunications and directs the Edge Computing Hub funded by Rakuten Mobile, Japan. He received the 2021 IEEE Rising Star Award from the Technical Committee on the Internet for fundamental contributions to edge computing systems and applications.