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.
- This event has passed.