|Expertise||Machine Learning, Data Science, Data Engineering|
Spyros Theodoropoulos is a PhD Candidate at the School of Electrical and Computer Engineering of the National Technical University of Athens. He is a graduate of the same school and also holds a MSc in Machine Learning from Imperial College London. He has worked in industry as a Software and Big Data Engineer and is now collaborating with the DaC group in the STAR (Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines) research project. His research is focused around deep learning and reinforcement learning as well as the use of simulation for their deployment in real-life dynamic environments.
Personal Research Topics
Simulated Reality for AI Systems in Dynamic Environments
The deployment of AI systems in real-life dynamic environments presents many practical challenges, such as the risk of physical damage due to mistaken decisions, the lack of sufficient training data or the inability to adapt to changes in the operating environment. Simulation can be studied as a technique to mitigate those issues and increase the safety and robustness of AI algorithms. It can be applied in different forms to augment modern Deep Learning and Reinforcement Learning algorithms operating in cyber-physical environments and interacting with humans.