| Time: | June 25, 2024 |
|---|---|
| Download as iCal: |
|
Dr. Konstantinos Gatsis
School of Electronics and Computer Science
University of Southampton
Southampton, England
Tuesday 2024-06-25 4 p.m.
IST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen
Abstract
The automation of processes in industry and our cities holds a significant economic promise. The developments in autonomous systems are growing as a result and target complex environments ranging from warehouses to autonomous driving. To deal with this complexity there is a lot of interest in using machine learning technology in autonomous systems. But recent advances in machine learning have been driven by models represented by (artificial) neural networks and integrating them with autonomous systems is a difficult task on its own. In this talk, I will discuss recent research in my group, exploring the interface between control systems theory and neural networks. I will discuss the tool of Neural Ordinary Differential Equations (NODEs), that lies in this interface, and I will present two projects, first on the use of NODEs in control systems, and second on the computational efficiency of NODEs.
Biographical Information
Dr. Konstantinos Gatsis is a Lecturer (Assistant Professor) in the School of Electronics and Computer Science at the University of Southampton, UK and a Visiting Academic in the Department of Engineering Science at the University of Oxford, UK. He received the Ph.D. degree in electrical and systems engineering from the University of Pennsylvania, Philadelphia in 2016, and the Diploma degree in electrical and computer engineering from the University of Patras, Patras, Greece in 2010. His research interests include cyber-physical systems and autonomy, developing algorithms at the intersection of control, learning, security, and optimization. Dr. Gatsis received the Best Doctoral Dissertation Award from the department of Electrical and Systems Engineering at the University of Pennsylvania, the 2023 IEEE Communications Society & Information Theory Society Joint Paper Award, the 2014 O. Hugo Schuck Best Paper Award, the Student Best Paper Award at the 2013 American Control Conference, and has been nominated for other best paper awards.