@Ylecun perpetuates false dichotomy here, between nature & nurture, without presenting data. Is there any evidence primates have fewer innate priors than mountain goats? Any proof that more innate priors actually entails less adaptivity? Better priors can yield *better* learning.https://twitter.com/ylecun/status/1180171721481113602 …
-
learning =/= adaptivity, though. Better priors, if known, can indeed confer better performance. At an extreme you hand code the solution directly and have zero free parameters. But the more priors/structure, the less a model can be applied to different tasks (adaptability)
again where is the evidence for this? if you have a prior that tells you that the objects exist and persist in space time vs a pure blank slate i strongly believe you will be better off. without MCTS alphago wouldn’t “adapt” to go nearly as well
-
-
The evidence is just deductive logic: I can hand-code a solution for a gravity problem but it'll be useless for telling me about chemistry. Also, I think you're conflating learning speed, final performance, and model adaptability across different tasks in the words "better off".
-
if you know algebra you can use it in many domains; ditto for logic.
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.