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 …
-
I think you're getting hung up on the phrase "with certainty". ANNs are a model of how brains might work. It's an open question of how good a model they are.
. @tyrell_turing could be making a strong claim - that we know that ANNs are in some respect a good model of the brain - or a weak claim - that some designers intend their systems to model the brain, with no claim as to whether they are correct. i object only to the strong claim.
-
-
After reading through all this, I think the key question is whether you agree with the 'mild' claim - that some models contain at least one aspect that aligns with the brain, even if poorly...
-
quite possibly; just think it is premature to be remotely certain
- 2 more replies
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.