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 may be fruitful & fashionable to say we dont understand anything about the brain & so cant model it. But that's simply not how modeling works. Its iterative and you go with your best guess until contradictory evidence provides you with a better one.
for 30 years I have seen neural net fans say "I will use this until I see evidence against", but precious few have inventoried limits of their own approaches and genuinely sought something new. Sadly, most get too attached to their own ideas to actually follow this methodology
-
-
I wont speak to the past, but at present there are a lot of people working to extend these models, adding more bio-inspired elements & testing on more realistic tasks exactly because they have observed where the simpler models fall short. So the boundaries are being pushed.
-
could you be more specific?
- 3 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.