First Meetup: Deep Learning, FPGAs and Genetic Algorithms

I am happy to announce that our first meetup will take place next  Monday 27/03 – 19:00  at City College (Auditorium, 5th floor).

Let’s learn, network and socialize. Looking forward to meeting all of you!

Agenda:

– 19:00: Welcome

– 19:10: Introductory speech 

   Doropoulos Stavros, Meetup Organizer

– 19:30: First Talk

   ‘Deep Learning for Digital Media Analysis‘ 

    Dr. Anastasios Tefas, Assistant Professor at the Department of    Informatics, Aristotle University of Thessaloniki

– 20:10: Break 

– 20:20: Second Talk 

  ‘Intrinsic Evolution of Digital Circuits Based on a Reconfigurable Hyper –  Structure using Genetic Algorithms‘  

   Dimitris Bogas, Computer Engineer at DataScouting

– 21:00: Networking and socializing

——


‘Deep Learning for Digital Media Analysis’ 

Dr. Anastasios Tefas

Abstract: Recent advances in technological equipment, like digital cameras, smart-phones, etc., have led to an increase of the available digital media, e.g., videos, captured every day. Moreover, the amount of data captured for professional media production (e.g., movies, special effects, etc) has dramatically increased and diversified using multiple sensors (e.g., 3D scanners, multi-view cameras, very high quality images, motion capture, etc), justifying the digital media analysis as a big data analysis problem. As expected, most of these data are acquired in order to describe human presence and activity and are exploited either for monitoring (visual surveillance and security) or for personal use and entertainment. Basic problems in human centered media analysis are face recognition, facial expression recognition and human activity recognition. Such a data growth, as well as the importance of visual information in many applications, has necessitated the creation of methods capable of automatic processing and decision making when necessary. This is why a large amount of research has been devoted in the analysis and description of digital media in the last two decades. In this talk a short overview on recent research efforts for digital media analysis and retrieval using machine learning and deep neural networks will be given. Deep neural networks are very powerful in analyzing, representing and classifying digital media content through various architectures and learning algorithms. Both unsupervised and supervised algorithms can be used for digital media feature extraction. Digital media representation can be done either in a synaptic level or at the output level. Automatic content descriptions can be extracted using Recurrent Neural Networks combined with Convolutional ones. User feedback can be incorporated in the neural learning process and attention models can be used in order to enhance the results.

Biography: Anastasios Tefas received the B.Sc. in informatics in 1997 and the Ph.D. degree in informatics in 2002, both from the Aristotle University of Thessaloniki, Greece. Since 2013 he has been an Assistant Professor at the Department of Informatics, Aristotle University of Thessaloniki. From 2008 to 2012, he was a Lecturer at the same University. From 2006 to 2008, he was an Assistant Professor at the Department of Information Management, Technological Institute of Kavala. From 2003 to 2004, he was a temporary lecturer in the Department of Informatics, University of Thessaloniki. From 1997 to 2002, he was a researcher and teaching assistant in the Department of Informatics, University of Thessaloniki. Dr. Tefas participated in 12 research projects financed by national and European funds. He has co-authored 72 journal papers, 177 papers in international conferences and contributed 8 chapters to edited books in his area of expertise. Over 3600 citations have been recorded to his publications and his H-index is 32 according to Google scholar. His current research interests include computational intelligence, pattern recognition, statistical machine learning, digital signal and image processing and computer vision, biometrics and security.

——

‘Intrinsic Evolution of Digital Circuits Based on a Reconfigurable Hyper-Structure using Genetic Algorithms’  

Dimitris Bogas

Abstract: This work presents an intrinsic implementation of Evolvable Hardware, for evolving optimal digital combinatorial circuits. The evolutionary optimization is performed by an enhanced Genetic Algorithm that works on binary encodings of solutions. Potential circuits are built and evaluated on a reconfigurable Cartesian hyper-structure that is pre-configured on a FPGA circuit, together with communication and control logic. Test results are provided for a number of well-known digital circuits. The results are promising and show the effectiveness of the proposed implementation.

Biography: Dimitris Bogas is a Computer and Communications Engineer currently working as Software Engineer at DataScouting. He is specialized in FPGA/Electronic design, Software engineering and lately in Machine learning. He has been collaborating successfully with developers, researchers and administrative staff from European Universities and companies for the last three years. 

This entry was posted in . Bookmark the permalink.