I am a PhD candidate in the Department of Informatics and Telecommunications of the National and Kapodistrian University of Athens under the supervision of Prof. Sergios Theodoridis. At the same time, I hold a research associate position at the Institute of Informatics and Telecommunications of the National Center for Scientific Research “Demokritos”, where I am involved in international projects. I work along the Complex Event Recognition Group and I conduct research mostly in the area of Statistical Relational Learning and AI under the guidance of Dr. Georgios Paliouras and Dr. Alexander Artikis. SRL attempts to represent, reason, and learn in domains governed by uncertainty and complex relational structure by combining logic-based representations, probabilistic modeling and machine learning. Given the increased complexity of the task and the fact that data these days are endless, I am also interested in scalability.
I graduated from the Technical University of Crete, school of Electronics and Computer Engineering and I received a 5-year diploma. During my studies I worked along the Kouretes RoboCup team where I completed my thesis on Dynamic Multi-Robot Coordination for the RoboCup Standard Platform League. In the Fall of 2013 I joined the graduate program of Electronics and Computer Engineering at the Technical University of Crete and in the Spring of 2014 I started working along the CER Group at NCSR where I completed my master thesis on Online Structure Learning for Markov Logic Networks using Background Knowledge Axiomatization and received an MSc degree. Since October 2016 I hold a PhD candidate position.
My research interests are currently focused on AI and machine learning mostly for complex event recognition. I have also some research and development experience in autonomous agents and robotics. Concisely that translates into the following several research fields:
- Artificial Intelligence (Knowledge Representation & Reasoning)
- Machine Learning (Supervised & Semi-Supervised Statistical Learning)
- Statistical Relational Learning (Markov Logic Networks & Probabilistic Soft Logic)
- Inductive Logic Programming (Hypothesis Search & Language Bias)
- Autonomous Agents & Robotics (Robot Coordination & Path Planning)
I am also passionate about programming and software engineering. I am a Scala enthusiast and I have plenty of experience in object-oriented and functional program design, relational databases and parallel computing.
Michelioudakis E., Skarlatidis A., Paliouras G., Artikis A., OSLa: Online Structure Learning using Background Knowledge Axiomatization.
Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery,
LNCS 9851, pp. 232-247, Springer, 2016.
PDF | Appendix | bibtex
Michelioudakis E., Artikis A., Paliouras G., Online Structure Learning for Traffic Management.
Proceedings of the 26th International Conference on Inductive Logic Programming,
LNCS 10326, pp. 27-39, Springer, 2016.
PDF | bibtex
datAcron - Big Data Analytics for Time Critical Mobility Forecasting
Research and development for the Machine Learning component (February 2017 - present)
Objective: datAcron advances the management and integrated exploitation of voluminous and heterogeneous data-at-rest (archival data) and data-in-motion (streaming data) sources, so as to significantly advance the capacities of systems to promote safety and effectiveness of critical operations for large numbers of moving entities in large geographical areas.
- SPEEDD - Scalable Proactive Event-Driven Decision-Making
Leading developer for the Machine Learning component (January 2016 - January 2017)
Objective: SPEEDD develops a prototype for proactive event-driven decision-making wherein decisions are triggered by forecasting events. The decisions are in real-time, in the sense that they are taken under tight time constraints, and require on-the-fly processing of Big Data, that is, extremely large amounts of noisy data flooding in from various geographical locations, as well as historical data.
- REVEAL - REVEALing hidden concepts in Social Media
Research and development on Statistical Relational Learning (April 2014 - December 2015)
Objective: REVEAL aims to advance the necessary technologies for making a higher level analysis of social media possible. The project enables users to reveal hidden modalities such as reputation, influence or credibility of information in order to perform social media verification.