Header image  
Tutorials: Nov 13, 2011, Shanghai, China
Main Conference: Nov 14-17, 2011, Shanghai, China
Workshops: Nov 18, 2011, Hangzhou, China
line decor
   Final program of ICONIP2011 and book of abstracts are available now.  
line decor

Keynote Speaker

Prof.Shun-ichi Amari

RIKEN Brain Science Institute, Japan

Stable and Fast Decision by Neural Networks: Fundamental Problems in Mathematical Neuroscience


        The brain, a network consisting of a vast number of neurons, processes information by dynamic interactions of neurons. A neuron receives signals from other neurons and its decision is based on the weighted sum of other signals. Such a decision is called a generalized majority decision. There are many other biological and social systems subject to the generalized majority decision. We search for the fundamental properties of a network of majority decision compared with Boolean logical decision. To this end, we consider a network of randomly connected binary neurons, having 2**n states, n the number of neurons. We search for the average number of attractors and the average length of transient periods. We show by using the statistical neurodynamic method that these are extremely small compared to those of a random Boolean network. This is a characteristic feature of a neural network which guarantees quick and reliable decision, because of short transient periods.

        We further study dynamics of excitation patterns in a two-dimensional neural field, showing existence of traveling bumps and the way of their control. The collision of traveling bumps shows a possibility of a new style of information processing in a neural field.

Biographical Sketch

        Shun-ichi Amari was born in Tokyo, Japan, on January 3, 1936. He graduated from the Graduate School of the University of Tokyo in 1963 majoring in mathematical engineering and received Dr. Eng. Degree.

        He worked as an Associate Professor at Kyushu University and the University of Tokyo, and then a Full professor at the University of Tokyo, and is now Professor-Emeritus. He served as Director of RIKEN Brain Science Institute for five years, and is now its senior advisor. He has been engaged in research in wide areas of mathematical engineering, in particular, mathematical foundations of neural networks, including statistical neurodynamics, dynamical theory of neural fields, associative memory, self-organization, and general learning theory. Another main subject of his research is information geometry initiated by himself, which provides a new powerful method to information sciences and neural networks.

        Dr. Amari served as President of Institute of Electronics, Information and Communication Engineers, Japan and President of International Neural Networks Society. He received Emanuel A. Piore Award and Neural Networks Pioneer Award from IEEE, the Japan Academy Award, Gabor Award from INNS, Caianiello Award, and C&C award, among many others.

Copyright© 2010-2011 International Conference on Neural Information Processing. All rights reserved.