Computer vision seminar

Machine learning methods are a systematic approach to designing high performance information processing systems. The methods of machine learning have been around for nearly fifty years, yet there is now a revolution ongoing with methods such as the fully Bayesian approach and conditional random fields. There is also a move to discover the broad underpinnings of a unified theory, to describe a range of seemingly ad-hoc methods, by using graphical models and the discriminative-generative taxonomy. The talk will begin with a tutorial approach to the central concepts underlying newer methods and then describe some results in the context of MINDS (Machine learning, Information retrieval, Natural language processing, Document analysis/ recognition and Speech recognition). Bio: Sargur (Hari) Srihari is a SUNY Distinguished Professor at the State University of New York at Buffalo. He teaches and does research in pattern recognition and machine learning in the Department of Computer Science and Engineering. He served as Principal Investigator on a project that led to the first large scale deployment of automatic reading of handwritten postal systems in the world. He is presently serving on a U.S. National Academy of Sciences committee on “Identifying the Needs of the Forensic Community”. An author of over 300 papers he has received several honours including Fellow of IEEE, Fellow of the International Association for Pattern Recognition (IAPR) and Distinguished Alumnus of the Ohio State University College of Engineering. Srihari received a B.E. from the Indian Institute of Science, Bangalore and a PhD from the Ohio State University, Columbus.

Back