Nikolaos Dionelis

Nikolaos Dionelis

DR

Accepting PhD Students

If you made any changes in Pure these will be visible here soon.

Personal profile

Biography

Nikolaos Dionelis is a postdoctoral Research Associate (RA) in Machine Learning at the University of Edinburgh (UoE) with a PhD degree in Signal Processing from Imperial College London (ICL) and a Masters MEng degree in Electrical Engineering from ICL. As a RA within the University Defence Research Collaboration (UDRC) in Signal Processing, Nikolaos is conducting timely research on areas within deep learning, including designing and developing deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), autoencoders (AEs), and invertible generative models for anomaly detection in high-dimensional spaces which is a promising nascent research area. Before his current RA in Machine Learning position at the UoE and the UDRC, Nikolaos was a postgraduate researcher in the Communications and Signal Processing Group in the Department of Electrical and Electronic Engineering at ICL. He was awarded with the Engineering and Physical Sciences Research Council (EPSRC) Doctoral Training Award when he was working towards his PhD degree at ICL. Nikolaos received his Masters MEng degree (including Batchelors) with First Class Honours in Electrical and Electronic Engineering from ICL in 2015. He completed the International Baccalaureate (IB) Diploma Programme at the Hellenic-American Educational Foundation (HAEF) Athens College – Psychico College, Athens, Greece in 2011. His current research interests include anomaly detection, state-of-the-art deep generative models, deep learning, machine learning, and signal processing using statistical and probabilistic methods.

Education/Academic qualification

Signal Processing, Doctor of Philosophy (PhD), Imperial College London

Award Date: 1 Sep 2019

Electrical Engineering, Master of Engineering, Imperial College London

Fingerprint

Dive into the research topics where Nikolaos Dionelis is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
  • 1 Similar Profiles