(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".
-
-
Show you that one-shot learning, compositionality, systematic generalization, etc, are not properties exclusive to symbolic methods? This is a positive claim, and the onus is on symbolists to prove it is true.
-
or show that it’s not.
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.