Re:The Measure of Intelligence: towards more human-like arti...
by joe_the_user on Friday November 15, 2019 @03:49PM
(#21548611)
Interesting: "To avoid local-generalization systems that artificially "buy" performance on a specific task, Chollet restricts priors to 'Core Knowledge' found in developmental science theory: such as elementary physics, arithmetic, geometry and a basic understanding of intentions."
I can see the plausibility of this but it raises an objection that the hardest tasks for a computer are those seemingly simple for a human being while tasks involving analysis and abstraction are often easiest for computers, Moravec's "law"[1]. I think one could also put it as solving neat problems is simple for machines, solving the messy intersection of several problems and exigencies is what's hard (and what's required for generality, since most things turn out to be messy).
I can see the plausibility of this but it raises an objection that the hardest tasks for a computer are those seemingly simple for a human being while tasks involving analysis and abstraction are often easiest for computers, Moravec's "law"[1]. I think one could also put it as solving neat problems is simple for machines, solving the messy intersection of several problems and exigencies is what's hard (and what's required for generality, since most things turn out to be messy).
[1] https://en.wikipedia.org/wiki/Moravec%27s_paradox