(Thread) On the heels of the recent @GaryMarcus & @ylecun Twitter "debate", here's one of my gripes. I find myself constantly frustrated in any deep learning vs. symbolic debate because symbol pushers tend to claim ownership over capacities like "reasoning".
i think learning for symbol binding might actually be sort of like what i have been advocating; if not, why not?
-
-
i think it would move the conversation forward if you were to answer this yourself. deepmind, one of the big DL labs, is pursuing a line of research that "uses symbols" in some sense. is your reaction "this is great -- but not enough DL research does this"?
-
I keep mentioning eg
@grefen’s work at DeepMind@littlebimble ‘cuz I like it.
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.