Re:Is there a simple algorithm for intelligence?
by eli_gottlieb on Friday July 10, 2015 @07:40PM
(#9867682)
>Kind of renders all of his information theoretic calculations moot.
The stuff in the article isn't information theory. Information theory, in the senses of Shannon and Chaitin, is actually very useful for studying cognition, because it tells us about how much we can try to learn, via what methods, from noisy sensory data.
The stuff in the article isn't information theory. Information theory, in the senses of Shannon and Chaitin, is actually very useful for studying cognition, because it tells us about how much we can try to learn, via what methods, from noisy sensory data.