Wednesday, Dec 12, 2007

 

IEEE Computational Intelligence Society

Silicon Learning Machines

Speaker: Prof.  Gert Cauwenberghs, UCSD

 

 

About the program: Learning and adaptation are key to biological and artificial intelligence in complex and variable environments.  Advances both in machine learning and in system-on-chip very large scale integration (VLSI) make it now possible to construct silicon learning machines with pervasive real-time adaptive intelligence that embed learning mechanisms at the cellular and sensory level, and that attain high levels of efficiency in large-scale parallel adaptive computation.  The talk will focus on kernel learning machines for pattern recognition from sparse training examples, which include support vector machines and extend to sparse probability estimation and maximum a posteriori forward sequence decoding. Implemented in massively parallel analog and digital VLSI, these learning systems-on-chips offer throughput and energy efficiency in the TeraMACS (10^12 multiply accumulates per second) per milliwatt range.  Applications will be illustrated with examples in vision and speech processing.

 

About the Speaker:  Gert Cauwenberghs received the Ph.D. degree in electrical engineering from California Institute of Technology in 1994.  He is Professor of Biology at University of California San Diego where he directs the Integrated Systems Neuroscience Laboratory.  Previously he held positions as Professor of Electrical and Computer Engineering at Johns Hopkins University and as Visiting Professor of Brain and Cognitive Science at Massachusetts Institute of Technology.  His research aims at advancing silicon adaptive microsystems to understanding of biological neural systems, and to development of sensory and neural prostheses and brain-machine interfaces. His activities include design and development of micropower analog and mixed-signal systems-on-chips performing adaptive signal processing and pattern recognition.  He received the National Science Foundation Career Award in 1997, Office of Naval Research Young Investigator Award in 1999, and Presidential Early Career Award for Scientists and Engineers in 2000. He was Distinguished Lecturer of the IEEE Circuits and Systems Society in 2003-2004, and chaired its Analog Signal Processing Technical Committee in 2001-2002.  He serves as Associate Editor for IEEE Transactions on Circuits and Systems I, IEEE Transactions on Neural Systems and Rehabilitation Engineering, and IEEE Sensors Journal.

 

Time/Place: Wednesday Dec 12, 6:00 P.M. Lockheed Martin, 4770 Eastgate Mall San Diego, California 92121. Food served starting at 6:00 p.m., talk will begin sharply at 6:30.  Directions and lecture background materials available at the SD CIS website. http://ewh.ieee.org/r6/san_diego/cis/

 

Information: Andrew Diamond (IEEE CIS San Diego Chapter Chair) (858) 509-3115, adiamond@EnvisionSystemsLLC.com