They basically agreed on everything except what "symbol" and "hybrid model" mean. Wish these topics had been discussed more. Interesting way to announce @jeffclune's new job though (congratulations to Jeff!
)https://twitter.com/MelMitchell1/status/1208811044409200645 …
Neural networks can and do learn all of that too. (I agree that many practitioners may not have realized the need to train it into their models, but I don't think that LeCun, Bengio or Schmidhuber see it differently.)
-
-
happy to have that discussion after you have read chapter 3 of algebraic mind, and engaged with it (now free on MIT oress websitr) but unwilling to cram the nuance of that particular argument into a tweet
-
I disagree. One should be able to concisely cram one's ideas into tweet form. If not one but in a thread.
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.