Sunahara Memorial Lectures

 

Lecture (1)

On the Differences Between Discretized and Continuous Stochastic Systems as Demonstrated by Learning Automata

Prof. John Oommen (Carleton University)

 

Abstract


Stochastic Learning Automata (LA) are probabilistic finite state machines which have been used to model how biological systems can learn. The structure of such a machine can be fixed, or it can be changing with time. A LA can also be implemented using action (choosing) probability updating rules which may or may not depend on estimates from the Environment being investigated. Traditionally, these updating rules have worked with the continuous probability space. In this talk, we will describe how LA can also be designed by discretizing the probability space. The talk will describe the design and analysis of both continuous and discretized LA, and will highlight the subtle differences between the corresponding learning machines, their convergence properties, and their learning capabilities.

 

Biography of Dr. John Oommen

 

Dr. John Oommen was born in Coonoor, India on September 9, 1953. He obtained his B.Tech. degree from the Indian Institute of Technology, Madras, India in 1975. He obtained his M.E. from the Indian Institute of Science in Bangalore, India in 1977. He then went on for his M.S. and Ph. D. which he obtained from Purdue University, in West Lafayettte, Indiana in 1979 and 1982 respectively. He joined the School of Computer Science at Carleton University in Ottawa, Canada, in the 1981-82 academic year. He is still at Carleton and holds the rank of a Full Professor. Since July 2006, he has been awarded the honorary rank of Chancellor's Professor, which is a lifetime award from Carleton University. His research interests include Automata Learning, Adaptive Data Structures, Statistical and Syntactic Pattern Recognition, Stochastic Algorithms and Partitioning Algorithms. He is the author of more than 290 refereed journal and conference publications, and is a Fellow of the IEEE and a Fellow of the IAPR. Dr. Oommen is on the Editorial Board of the IEEE Transactions on Systems, Man and Cybernetics, and Pattern Recognition.

 

Lecture (2)

Modeling Problems in Animal Vision and Gaze Control

Prof. Bijoy Kumar Ghosh (Texas Tech University)

 

Abstract

Animals routinely rely on their eyes to localize fixed and moving targets. Such a localization process might include capturing motion cues from the dynamic visual world, prediction of future location of moving targets and for the motor control circuit, actuating a successful eye and head movement. In this talk, I shall introduce how visual signals are captured by intensity and motion sensitive neurons in the retina and how these signals are subsequently processed by the visual cortex. Typically, the retino-cortical circuit plays a major role in encoding motion cues using which the animal makes prediction of future target locations. We discuss a possible encoding and decoding algorithm using principal component analysis. A Biophysically detailed simulation model of the visual circuit is introduced using neurons that are believed to play a major role in animal vision. In order to keep a moving target in view, it is also important to track the target by a suitably shifting gaze. In this talk, I shall introduce how this is achieved by a combination of eye and neck movement. The eye movement is posed as an optimal control problem using quaternion and numerical algorithm to solve the associated two point boundary value problem is introduced.

 

Biography of Prof. Bijoy Kumar Ghosh

 

Professor Bijoy Ghosh received his doctorate in engineering from the Decision and Control group of the Division of Applied Sciences at Harvard University in 1983. During 1983 and 2006 he was a faculty member in the Department of Systems Science and Mathematics (now Electrical and Systems Engineering) at Washington University. Currently he is a Professor in Department of Mathematics and Statistics and Director of Center for BioCybernetics and Intelligent Systems in Texas Tech University in Lubbock Texas.
In 1988 Professor Ghosh received the American Automatic Control Council's Donald P. Eckman Award in recognition of his outstanding contribution in the field of automatic control. In 2000, he became a Fellow of the Institute of Electrical and
Electronics Engineers (IEEE).