Massachusetts Institute of Technology
Visual Recognition in Primates and Machines
1:00 – 3:00pm Monday, December 03, 2007
Understanding the processing of information in our cortex is a significant part of understanding how the brain works and of understanding intelligence itself, arguably one of the greatest problems in science today. In particular, our visual abilities are computationally amazing and we are still far from imitating them with computers. Thus, visual cortex may well be a good proxy for the rest of the cortex and indeed for intelligence itself. But despite enormous progress in the physiology and anatomy of the visual cortex, our understanding of the underlying computations remains fragmentary. I will briefly review the anatomy and the physiology of primate visual cortex and then describe a class of quantitative models of the ventral stream for object recognition, which, heavily constrained by physiology and biophysics, have been developed during the last two decades and which have been recently shown to be quite successful in explaining several physiological data across different visual areas. I will discuss their performance and architecture from the point of view of state-of-the-art computer vision system. Surprisingly, such models also mimic the level of human performance in difficult rapid image categorization tasks in which human vision is forced to operate in a feedforward mode. I will then focus on the key limitations of such hierarchical feedforward models for object recognition, discuss why they are incomplete models of vision and suggest possible alternatives focusing on the computational role of attention and its likely substrate – cortical backprojections. Finally, I will outline a program of research to attack the broad challenge of understanding in terms of brain circuits the process of image inference and in particular recognition tasks beyond simple scene classification.
Tomaso A. Poggio, is the Eugene McDermott Professor at the Department of Brain and Cognitive Sciences; Co-Director, Center for Biological and Computational Learning; Member for the last 25 years of the Computer Science and Artificial Intelligence Laboratory at MIT; since 2000, member of the faculty of the McGovern Institute for Brain Research and member of the steering committee of the Center for Collective Intelligence. He is author or co-author of over 400 papers in the fields of learning theory, computer science, computational neuroscience, and nonlinear systems theory and he belongs to the editorial board of several scientific journals. He is an honorary member of the Neuroscience Research Program, a member of the American Academy of Arts and Sciences and a Founding Fellow of AAAI. He received several awards such as the Otto-Hahn-Medaille Award of the Max-Planck-Society, the Max Planck Research Award (with M. Fahle), from the Alexander von Humboldt Foundation, the MIT 50K Entrepreneurship Competition Award, the Laurea Honoris Causa in Ingegneria Informatica for the Bicentenario dell'Invenzione della Pila from the University of Pavia and the 2003 Gabor Award. His research has been interdisciplinary, between brains and computers. It is now focused on the mathematics of learning theory, the applications of learning techniques to computer vision, bioinformatics, computer graphics and especially on computational neuroscience of the visual cortex in close collaboration with several physiology labs.