astonished that anyone knowledgeable could claim that neural nets are (obviously) an “abstraction of neural processing” when we don’t yet know how brains work. if you don’t know how Y works you can’t really speak with certainty about whether X is an abstraction of Y. Period.https://twitter.com/tyrell_turing/status/1200072223299657728 …
-
Could it not be possible for a neural network to generate the 'potential abstractions' needed for complex cognition? ANNs the best models we have today for generating complex behavior. So why should he
@tyrell_turing be taken to task for using the best known tools for his job?
sort of like claiming democracy is perfect when it’s not? current models haven’t come close to@solving vision, language, planning etc, so they are invitation to do serious out of box thinking.
-
-
I don't disagree with the need for alternative models. But the methods required for research don't need to approximate human complete cognition. DL affords tools that are very good at mimicry and thus it makes sense for neuroscientists to drive their research using DL.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.