Cognitive lecture at ELTE

Hasonloan a Cognitive Center holland diakoknak (angolul) tartott eloadasaahoz egy eloadas lesz az ELTE-n is. Mindenkit szeretettel varok. Lorincz Andras http://people.inf.elte.hu/lorincz Cim: Is neocortical encoding of sensory information intelligent? Eloado: Lorincz, Andras Abstract: The theory of computational complexity is used to underpin a recent model of neocortical sensory processing. We argue that encoding into reconstruction networks is appealing for communicating agents using Hebbian learning and working on hard combinatorial problems, which are easy to verify. The model allows us to provide a computational definition for the concept of intelligence. Simulations illustrate the idea. Motivation for reconstruction network models: According to one view , intelligent agents learn by developing categories (Harnad, 2003). For example, mushroom-categories could be learned in two different ways: (1) by ‘sensorimotor toil’, that is, by trial-and-error learning with feedback from the consequences of errors, or (2) by communication, called ‘linguistic theft’, that is, by learning from overhearing the category described. Our point is that case (2) requires mental verification: Without mental verification trial-by-error learning is still a necessity. In our model, 'mental verification' shall play a central role for constructing the subsystems, our agents. Idopont es hely: Date: 16 April, 2004 Time: 10:00-12:00 A.M. Place: Room 0-823 (Kitaibel Room, ground level) West side of the South Building of ELTE (Danube is on the East side) Pazmany Peter setany 1/C