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 …
-
-
We know enough of the basics of how individual neurons turn inputs to outputs to create an abstraction of that process. That is the solid statement that supports (1). (2) is dependent on how neurons interact & what further complexities are needed to capture all the brain does.
-
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.
- 6 more replies
New conversation -
-
-
These are two different levels of abstraction. I agree that we can simulate how neural processing works at a micro level without understanding how the brain works at a macro level.
-
Electrical signal transfer over ethernet can be physically detected and can be simulated. But without the understanding of TCP/IP, a meaningful communication can never happen. If a map of physical nodes and links of entire Internet is drawn, it will look similar to a neural net.
End of conversation
New conversation -
-
-
Because "abstraction".
-
New conversation -
-
-
The fields of AI and neuroscience get into all kinds of pointless beefs simply because people confuse and conflate all sorts of things.
@element_ai@ylecun@GoogleAI@facebookai@zacharylipton@dileeplearning@realGeordieRose@albertwenger@kaifulee@sama@BaiduResearchpic.twitter.com/pM3S9Jz5kG
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.