Invited Session
Keynote Speech #2
Divergence, Signal Decomposition
and Information Geometry
October 6, 9:00-10:00, Room A
Prof. Shun-ichi Amari
RIKEN Brain Science Institute, Japan

Divergence measures between two probability distributions or more generally two signals play a fundamental role in designing algorithms of signal processing and adaptation. We first elucidate geometrical and invariant structures of divergence measures such as Kullback-Leibler and Bregman divergences. They are useful for designing algorithms in vision analysis, signal processing and optimization. Algorithms and frameworks of signal separation will be surveyed from the geometrical point of view.

Prof. Shun-ichi AMARI, after completing his professorship at The University of Tokyo, moved to The Institute of Physical and Chemical Research - RIKEN where he holds the position of vice-president of Brain Science Institute, director of Brain Style Information Systems Group and team leader of Mathematical Neuroscience Laboratory. He also serves on boards of numerous scientific journals and committees.

Academic qualifications:
1958 B.Eng. University of Tokyo, majoring in Mathematical Engineering
1963 Ph.D. University of Tokyo, Mathematical Engineering

Professional qualifications:
Fellow of IEEE
Professor Emeritus at the University of Tokyo

Social Activities:
1996 President of the International Neural Network Society
Council Member of the Bernoulli Society of Mathematical Statistics and Probability Theorem
President of the Institute of Electronics, Information and Communication Engineers, Japan

1964 Inada Award from the Institute of Electronics, Information and Communication Engineers (IEICE), Japan
1965, 1987
Best Paper Awards from IEICE Japan
1987 Yonezawa Special Award, IEICE Japan
1987 Kodansha Best Scientific Publication Award for "Biocomputer", Iwanami (1986)
1990 Academic Research Award, International Foundation for Artificial Intelligence
1992 IEEE Neural Networks Pioneer Award
1993 Neurocomputing Best Paper Award
1993 Best Paper Award (Japanese Neural Network Society)
1993 Best Research Achievement Award (Japanese Neural Network Society)
1994 INNS Neural Networks Leadership Award
1995 Japan Academy Award
1997 IEEE Emanuel R. Piore Award