Research
Neuromorphic Computing
Georgios was involved in developing neuromorphic devices capable of embedded and online learning. He was one of the core developers of the software simulator for the Neural and Synaptic Array Transceiver Framework (in collaboration with Intel Corporation Research Labs, the Universities of California Irvine, and San Diego). He investigated how natural mechanisms of biological brains can lead to more efficient and biologically plausible machine learning algorithms suitable for neuromorphic devices.
Parkinson’s Disease
Another research interest is Parkinson’s disease (PD). He has combined neuroscience and control theory to study PD and propose potential treatments. He has developed computational models based on neural fields theory for the basal ganglia and PD and has investigated closed-loop deep brain stimulation (DBS) with applications on PD treatments.
Cortical Plasticity & Self-organizing Maps
His research as a Ph.D. student focused on cortical plasticity and self-organization. He proposed a mathematical/computational model for studying self-organization in the primary somatosensory cortex. The model relied on the neural field’s theory. Simulation of his model showed how the cerebral cortex builds up topographic maps. Furthermore, he demonstrated how the brain maintains topographic maps and how they get reorganized in the face of a lesion.
Rhythmical Motor Control
Finally, as a Master’s student, he studied rhythmical motor control and human tremor. He has applied signal processing theory and analysis on neurophysiological signals like EEG and EMG, trying to determine the role of human tremor. Furthermore, he has investigated Central Pattern Generators (CPGs) and their role in biped locomotion.
He also has some experience in:
Natural Language Processing (NLP)
Georgios has worked as Data Science Architect for adNomus Inc. focusing mainly on Natural Language Processing (NLP). He is developing NLP algorithms with applications on Recommendation Systems and Content Analysis.