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 …
-
It is an abstraction, though, of some processes known to take in the brain which are believed to underlay important parts of its working
meh. the evidence in this regard is still equivocal in part because our knowledge of neuroscience is so large. and for that matter we don’t even have that much theory about ANNs. so mapping between them is sloppy at best.
-
-
I tend to think it the other way around. Current Neuroscience theory qualitatively predicts ANN. So any departure of natural cognition from ANN means theory should be amended, revised or dropped altogether (cf Gallistel). And the way to do it is by making a better theory.
- 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.