Towards a Syntactic/Probabilistic Framework for Vision/Speech Recognition and Biological Processes

Event Start
Event End
Location
Building 9, Level 2, Room 2322
Prof. Basilis Gidas, Professor of Applied Mathematics, Brown University, Rhode Island, USA

Abstract

The goal of computer vision is to build “intelligent” machines that interpret scenes, in the sense of recognizing objects or other structures in a scene, and provide succinct descriptions of context, actions, and intentions. In computer speech the goal is similar – “interpret” or recognize speech. In the past few decades, important advances have been made in concrete applications such as industrial inspection, medical imagery, remote sensing, animation, robotics, and airline reservation. Such applications have motivated the development of powerful statistical/mathematical tools such as statistical learning theory and Monte Carlo optimization and simulation algorithms. But a coherent conceptual and mathematical framework for high-level vision and speech recognition tasks, is missing. The same is the case for complex biological processes such as protein folding or the collective behavior of genes, proteins and cells. In this talk we will present a probabilistic syntactic/grammatical framework, reminiscent to Chomsky’s grammatical systems in linguistics, for studying vision/speech recognition tasks as well as biological processes. The framework will be motivated by isolating some key sources of difficulty in vision/speech systems which exhibit regularities from local to global – regularities which can be modeled only by syntactic/grammatical rules. The framework will be used to define a finite automata representation of genes (analogous to the grammatical representation of languages) and a statistical algorithmic procedure for finding genes in the human genome.

Brief Biography

Basilis Gidas is a Professor of the Divisions of Applied Mathematics at Brown University, USA. He  was one of the founders of CCMB (Center for Computational Mathematical Biology) at Brown. He  has made contributions in Mathematical Physics (especially quantum field theory), in Partial Differential Equations, and, the last 30 plus years, in Artificial Intelligence (especially computer vision) and  Statistical Inference. He holds a B.S. from the National Technical University of Athens, Greece, and a  Ph.D. joint in Nuclear Engineering and Physics from the University of Michigan. He is an Elected  Member of the Institute of Mathematical Statistics, and has served as an Advisory Member in the National Research Council, National Academy of Mathematical Sciences.

Contact Person