Great! New thread then: What are the ways in which people in the neural net community think that today's ANN's are NOT perfect models of the brain? Where do you want to dig deeper, and why?https://twitter.com/timkietzmann/status/1200159447651438592 …
-
What I think other approaches (eg explicit symbol manipulation) offer is shortcuts. Humans know things, so it would be more efficient to embed things we know into a system (vs learning everything). But I don't think we need it, and it has always been more brittle than learning.
i am hearing a bunch of opinions here, but not really hearing arguments; not on a level with the analysis in your excellent blogs, sorry.
-
-
As I said, not a neuroscientist. These are opinions. I've seen great neuroscience/AI overlap work from people like
@neurograce so I will defer to them. But isn't the counter-position, that we need more than these three blocks, also opinion? -
well, the difference is that I wrote a whole carefully argued book (The Algebraic Mind, MIT Press 2001) advocating several others, which to my knowledge has never been refuted.
End of conversation
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.