Abstract: I will discuss a notion of Information for the purpose of decision and control tasks, as opposed to data transmission and storage tasks implicit in Communication Theory a' la Wiener-Shannon. It is rooted in ideas of J. J. Gibson, and stands in contrast to entropy, complexity or coding length of the data regardless of the use, and regardless of nuisance factors. I will describe the relationship between such "Actionable Information" and the sufficient statistics for a typical decision task, and argue that the "information gap" between the two can only be filled by controlling the data acquisition process. I will discuss the consequences of such an "Actionable Information" Theory in understanding the so-called "signal-to-symbol barrier" problem, and in understanding information processing in biological systems. Data formation processes that include scaling and occlusion phenomena play a key role in the theory, vision being a prime example.
Professor Soatto received his Ph.D. in Control and Dynamical Systems from the California Institute of Technology in 1996; he joined UCLA in 2000 after being Assistant and then Associate Professor of Electrical and Biomedical Engineering at Washington University, Research Associate in Applied Sciences at Harvard University, and Assistant Professor in Mathematics and Computer Science at the University of Udine, Italy. He received his D.Ing. degree (highest honors) from the University of Padova- Italy in 1992. Dr. Soatto is the recipient of the David Marr Prize (with Y. Ma, J. Kosecka and S. Sastry of U.C. Berkeley) for work on Euclidean reconstruction and reprojection up to subgroups. He also received the Siemens Prize with the Outstanding Paper Award from the IEEE Computer Society for his work on optimal structure from motion (with R. Brockett of Harvard). He received the National Science Foundation Career Award and the Okawa Foundation Grant. He is a Member of the Editorial Board of the International Journal of Computer Vision (IJCV), the International Journal of Mathematical Imaging and Vision (JMIV) and Foundations and Trends in Computer Graphics and Vision. See http://vision.ucla.edu for more details.