Epstein Secrets

ence and human-like embodiment; and partly due to a more specific intuition regarding the value of action for perception, as reflected in Heinz von Foerster's dictum "if you want to see, learn how to act". We suspect there are important cognitive reasons why perception in the human brain centrally involv

spacetime is necessary for achieving humanlike AGI using feasible resources. As an argument against the necessity of this sort of prior knowledge, Ben Kuipers and his colleagues ISNIK 21 have shown that an AI system can learn via experience that its perceptual stream comes from a world with three, rather

a 168 9.4.5 What Kind of Physics Is Needed to Foster Human-like Intelligence? 169 9.5 Folk Psychol

urations that carry out sensorimotor and categorization tasks. The emergence of higher-level cognition from this approach seems rather unlikely. • Ben Kuipers and his colleagues INIK07, MKOS, NIKOalhave pursued an extremely innovative research program which combines qualitative reasoning and reinforcement

ocesses. 9.4.5 What Kind of Physics Is Needed to Foster Human-like Intelligence? We stated above that w

r the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of

e eee 168 9.4.5 What Kind of Physics Is Needed to Foster Human-like Intelligence?..... 169 9.5 Folk Psych

igurations that carry out sensorimotor and categorization tasks. The emergence of higher-level cognition from this approach seems rather unlikely. e Ben Kuipers and his colleagues [MK07, MIX08, MIXO09]have pursued an extremely innovative research program which combines qualitative reasoning and reinforcement

ocesses. 9.4.5 What Kind of Physics Is Needed to Foster Human-like Intelligence? We stated above that we

er the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of s