Our first meetup of the season will take place on Friday 29/09 - 19:00 at OK!Thess (https://www.google.gr/maps/place/OK!Thessfirstname.lastname@example.org,22.9511654,15z/data=!4m2!3m1!1s0x0:0x82bc16c6e0e18389?sa=X&ved=0ahUKEwixhI7l6K7WAhWFQBoKHU-hB28Q_BIIcjAN)
- 19:00: Welcome and Introductions, Doropoulos Stavros, Meetup Organizer
- 19:15: First Talk
'A short journey to intelligence', Dr. Nikos Zikos
- 20:00: Quick Break
- 20:15: Second Talk
'Deep Learning intro and hands-on tutorial', Nikolaos Passalis
- 21:00: Networking and socializing
'A short journey to intelligence'
Dr. Nikos Zikos
Abstract: Intelligence: A short journey to intelligence. Modeling logic and behaviorism. A simplified model of consciousness and it's extension to self-awareness. The human brain as a perpetual time-series predictor. Why do we not succeed?
Biography: Nikos Zikos received his diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki, Greece in 2005. He received his M.Sc. in cognitive systems from the same department at 2009. In 2014 he received his Ph.D. from the same department studying on mobile robots and especially on the field of localization and mapping. His interests include robotics, cognitive systems, computational vision and machine learning.
'Deep Learning intro and hands-on tutorial'
Abstract: Deep Learning allows for developing powerful techniques for solving difficult problems in a wide range of domains, such as computer vision, natural language processing, reinforcement learning, load forecasting, analytics, etc. The recent development of efficient GPU architectures, and highly optimized and easy to use libraries were of crucial importance in the success of Deep Learning. Some of the most well established Deep Learning Frameworks, including Theano, Tensorflow, Caffe, Torch, and Keras, will be presented. Several different training and deployment scenarios, ranging from training using a single CPU workstation to using multi-GPU architectures and specialized embedded systems, will be considered. We will also discuss how to overcome some of the most common issues faced during training and deploying deep learning models. Finally, we will present a short tutorial on how to use Deep Learning Frameworks to solve various problems using Deep Neural Networks.
Biography: Nikolaos Passalis is a Ph.D. candidate and researcher in the Artificial Intelligence & Information Analysis Laboratory of the Department of Informatics, Aristotle University of Thessaloniki. He obtained his B.Sc. in Informatics in 2013 and his M.Sc. in Information Systems in 2015 from Aristotle University of Thessaloniki, Greece. His research interests include deep learning, computational intelligence and information retrieval. His doctoral studies are supported by the General Secretariat for Research and Technology (GSRT) and the Hellenic Foundation for Research and Innovation (HFRI).