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 Degree of Dr. of Engineering.
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 moved to RIKEN Brain Science Institute and served as Director for 5 years and is now Senior Advisor. He has been engaged in research in wide areas of mathematical science and engineering, such as topological network theory, differential geometry of continuum mechanics, pattern recognition, and information sciences. In particular, he has devoted himself to 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 applies modern differential geometry to statistical inference, information theory, control theory, stochastic reasoning, and neural networks, providing a new powerful method to information sciences and probability theory.
Dr. Amari is past President of International Neural Networks Society and Institute of Electronic, Information and Communication Engineers, Japan. He received Emanuel A. Piore Award and Neural Networks Pioneer Award from the IEEE, the Japan Academy Award, C&C Award, INNS Gabor Award and Caianiello Memorial Award. He was founding co-editor-in-chief of Neural Networks, among many other journals.
Information Geometry and Its Applications
Information geometry has emerged from a geometrical study of a family of probability distributions. It searches for intrinsic and invariant geometrical structure of the manifold of probability distributions. It is applicable to various information sciences, such as statistical inference, information theory, machine learning, optimization, vision and neural information processing. The present talk will give a brief introduction to information geometry to those who are not familiar with modern differential geometry. We then show how useful the ideas of information geometry are, by giving a number of applications from various fields of information sciences. They include machine learning, computer vision, optimization and neural learning as well as neural spike analysis.