Evripidis Gkanias
Research Asscociate in Computational & Neuromorphic Modelling
University of Edinburgh
University of Groningen
Evripidis (or Evri) is a post-doctoral Research Associate at the University of Edinburgh, School of Informatics, and the University of Groningen, Faculty of Science and Engineering.
He is interested in bio-accurate artificial intelligence and information theory, and he currently studies the effectiveness of different forms of working memory constrained by insect neuroscience and nanotechnology hardware, aiming to build an anatomically-accurate polirised light compass circuit.
Scientific questions he is curretly working on:
- how does working memory implement in the brain,
- can photons imitate message passing in the insect brain, and
- how useful this is for visually guided navigation.
- Bio-inspired Artificial Intelligence
- Neuroethology of Navigation
- Probabilistic Machine Learning
- Reinforcement Learning
- Bio-inspired Computer Vision
- Multimodal Integration
-
PhD, Bio-inspired Robotics & Autonomous Systems, 2022 (expected)
University of Edinburgh
-
MSc, Artificial Intelligence, 2016
University of Edinburgh
-
BSc, Computer Science, 2013
Aristotle University of Thessaloniki
Recent Publication
Research Experience
University of Groningen
Advisors: Prof Barbara Webb (Edinburgh), Prof Elisabetta Chicca (Groningen).
Project: Insect Neuro Nano, Funding: European Research Council.
I explore the effectiveness of different forms of working memory constrained by the biology and nanotechnology hardware and build an anatomically-accurate polarised light compass circuit.
Advisor: Prof Barbara Webb.
Project: Insect Neuroethology of Reinforcement Learning, Funding: RAS CDT.
I investigate how insects form associative memories based on reinforcements from the environment and how this impacts their behaviour and especially navigation.
University of Sheffield
Advisors: Dr Michael Mangan (Sheffield), Prof Barbara Webb (Edinburgh).
Project: Invisible Cues, Funding: Engineering and Physical Sciences Research Council.
I was responsible for investigating the information content of polarised light in relation to animal navigation before using the outcomes to develop a technical specification / design for manufacture of a novel robot sensor.
Advisors: Prof Barbara Webb.
Project: Minimal, Funding: European Research Council.
I focus on trying to imitate the learning mechanism of the larval Drosophila, which creates associations among odours and tastes. The goal is to create such a mechanism in neural level and put it on a robot platform. The robot will try to find the gustatory source following the gradients of the associated odour.
Advisors: Dr Petros Daras.
Projects: RePlay, FI-STAR, Funding: European Commision.
My main task was to implement a toolbox, using C# and the WPF subsystem, which could be used to analyse and compare human gestures, tracked using different capturing devices, i.e., Microsoft Kinect, Vicon, WIMUs. I also implemented an extension of it, which was compatible with Unity3D.
Funding & Awards
Teaching Experience
I have been tutoring, demonstrating and marking for a variety of courses including:
-
Introductory Applied Machine Learning: tutor, demonstrator, marker
Instructors: Dr Amos Storkey & Prof Chris Williams
-
Reinforcement Learning: tutor
Instructors: Dr Pavlos Andreadis & Dr Stefano Albrecht
-
System Desighn Project: Machine Vision and Quantitative Analysis expert
Instructors: Dr Steve Tonneau, James Garforth & Prof Barbara Webb
-
Heterogeneous Parallel Programming: I was responsible for answering students' questions regarding the course material and assignments
Instructor: Prof Wen-mei W. Hwu
