April 17, Wednesday
12:00 – 13:00
Balanced information flow in sensing and acting - the fundamental principle of adaptive behavior
Computer Science seminar
Lecturer : Prof. Naftali Tishby
Affiliation : School of Engineering and Computer Science, Hebrew university of Jerusalem
Location : 202
Host : Prof. Shlomi Dolev
Living organisms and intelligent agents are characterized by the flow of sensory information from a stochastic environment and the value of their decisions and actions. We first argue that the future value can be related, in Partially Observed Markov Decision Processes (POMDP), to the information needed for controlling the process. This leads to a simple relationship between sensory information, control information and reward rate, which completely characterizes metabolic information processing. Next, we argue that efficient planning and learning are related to the predictive information (mutual information between past and future) of the environment. We further argue that the sub-extensive nature of predictive information is responsible for the emergence of hierarchies and reverse hierarchies in planning and perception, the fundamental building blocks of cognition.