Re:On Chomsky and the Two Cultures of Statistical Learning
by scott_s on Friday May 27, 2011 @07:13PM
(#2593395)
And why can't that domain-general tool be some kind of statistical machine? I ask this because I don't see why what you said is incompatible with it - in fact, I agree with what you said - but I suspect that the mechanism is probably statistical in nature.
[ Parent
| on HN ]
Re:On Chomsky and the Two Cultures of Statistical Learning
by brockf on Friday May 27, 2011 @11:23PM
(#2593790)
Right, I think we're in agreement then. Statistical learning is the domain-general tool. Or one of them.
It's the domain specific tools that are up in the air, though, and what I'm interested in.