John Baras, Professor of Maryland University, USA, to speak at ECE NTUA on Monday 4 June, 2018 at 17:00
Lecture title: Neuromorphic Artificial Intelligence: From Mathematical Foundations of Deep Learning to “Cortex-on-a-Chip”
(The lecture will be held at the Amphitheater 1, New ECE building)
Abstract
Deep Learning and Artificial Intelligence have attracted enormous attention recently. The race to design and manufacture “brain-like” computers is on and several companies have produced various such chips. Yet, the current state of affairs is very unsatisfactory and ad hoc.We describe a mathematical framework we have developed that provides a hierarchical architecture for learning and cognition. The architecture combines a wavelet preprocessor, a group invariant feature extractor and ahierarchical (layered) learning algorithm. There are two feedback loops, one back from the learning output to the feature extractor and one all the way back to the wavelet preprocessor. We show that the scheme can incorporate all typical metric differences but also non-metric dissimilarity measures like Bregman divergences. The learning module incorporates two universal learning algorithms in their hierarchical tree-structured form, both due to Kohonen, Learning Vector Quantization (LVQ) for supervised learning and Self-Organizing Map (SOM) for unsupervised learning. We demonstrate the superior performance of the resulting algorithms and architecture on a variety of practical problems including: speaker and sound identification, simultaneous determination of sound direction of arrival speaker and vowel ID, face recognition. We demonstrate how the underlying mathematics can be used to provide systematic models for design, analysis and evaluation of deep neural networks. We describe current work and plans on mixed signal (digital and analog) micro-electronic implementations that mimic architectural abstractions of the cortex of higher-level animals and humans, for sound and vision perception and cognition. The resulting architecture is non-von Neumann (i.e. computing and memory are not separated in the hardware) and neuromorphic. We call the resulting chip class “Cortex-on-a-Chip”.
Short Bio
John S. Baras received the Diploma in Electrical and Mechanical Engineering (with Highest Honors)from the National Technical University of Athens, Athens, Greece, in 1970, and the M.S. and Ph.D. degrees in Applied Mathematics from Harvard University, Cambridge, MA, USA, in 1971 and 1973, respectively. Since 1973, he has been with the Department of Electrical and Computer Engineering, University of Maryland at College Park, MD, USA, where he is currently a Professor. He is also a Faculty member of the Applied Mathematics, Statistics and Scientific Computation Program, and Affiliate Professor in the Fischell Department of Bioengineering, the Department of Mechanical Engineering, and the Department of Decision, Operations and Information Technologies, Robert H. Smith School of Business. Since 2013, he has been Guest Professor at the School of Electrical Engineering of the Royal Institute of Technology (KTH), Sweden. From 1985 to 1991, he was the Founding Director of the Institute for Systems Research (ISR) (one of the first six National Science Foundation Engineering Research Centers). In 1990, he was appointed to the endowed Lockheed Martin Chair in Systems Engineering. Since 1992, he has been the Director of the Maryland Center for Hybrid Networks (HYNET), which he co-founded. He has held visiting research scholar positions with:Stanford University; Massachusetts Institute of Technology; Harvard University; University of California Berkeley; Institute National de Resercheen Informatiqueet en Automatique (INRIA), France; Linkoping Univ., Royal Institute of Technology (KTH), Lund University, Sweden; Technical University of Munich, Germany.
He is an IEEE Life Fellow, SIAM Fellow, AAAS Fellow, NAI Fellow, IFAC Fellow, AIAA Associate Fellow, Member of the National Academy of Inventors (NAI) and a Foreign Member of the Royal Swedish Academy of Engineering Sciences (IVA). Major honors and awards include the 1980 George Axelby Award from the IEEE Control Systems Society, the 2006 Leonard Abraham Prize from the IEEE Communications Society, the 2014 Tage Erlander Guest Professorship from the Swedish Research Council, and a three year (2014-2017) Senior Hans Fischer Fellowship from the Institute for Advanced Study of the Technical University of Munich, Germany. In 2016 he was inducted in the University of Maryland A. J. Clark School of Engineering Innovation Hall of Fame. He was awardedthe 2017 Institute for Electrical and Electronics Engineers (IEEE) Simon Ramo Medal and the 2017 American Automatic Control Council (AACC) Richard E. Bellman Control Heritage Award.
He has coauthored more than 850 technical papers in refereed journals and conferences, one book (Path Problems in Networks, 2010)), and co-edited three others. He has given many plenary and keynote addresses in major international conferences worldwide. He has educated 85 doctoral students, 112 MS students and has mentored 50 postdoctoral fellows. He has been the initial architect and continuing innovator of the pioneering MS on Systems Engineering program of the ISR. His research interests include systems and control, optimization, communication networks, applied mathematics, signal processing and understanding, robotics, computing systems, network security and trust,systems biology, healthcare management systems, model-based systems engineering. He has been awarded eighteen patents and has been honored worldwide with many awards as innovator and leader of economic development.