Anybody else see a problem with highly-paid researchers at leading institutions refusing to engage in reading outside their own discipline? (Aside: book in question-The Algebraic Mind-is not general audience; it's a technical book in MIT Press's prestigious Bradford series.)https://twitter.com/zergylord/status/1200694810904018945 …
-
Top down (symbolist) vs bottom up (connectionist). What other direction do you propose?
I propose that we have to find a framework that allows us to learn (what ML tries to do) over symbolic abstractions (which people use routinely when they talk, write and read). many processes, top-down and bottom-up, must fuse the two.
-
-
I also disagree. We talk, write and read using neural networks and not a symbolic machine.
-
you are back to empty assertion. that's an empirical claim, and you have given no evidence.
- 4 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.