advocates of #machinelearning, I am told that you all know that (current) #ML is limited. fair enough. but which limits are you willing to *publicly* acknowledge?https://twitter.com/NotSimplicio/status/1173373706674085888 …
-
Maybe this isn't really answering your question, but like you say there are many (known) techniques that work better than deep learning for certain problems. Hence, no paradigmatic shift needed, since we already have the tools. Maybe just a new way of putting pieces together?
yes, for sure we need new ways of putting pieces together, and probably some new pieces. but that's not germane to this particular thread, which is trying to ascertain how forthcoming DL researchers are about limitations with their approach. (mostly, save @ylecun, not very.)
-
-
I personally feel ambiguous towards the question because I don't know if it's asking for current, surpassable limitations or categorical (unsurpassable) limitations
-
I suspect
@GaryMarcus believes certain limitations (hopefully enumerated like a well-crafted wager) are unsurpassable. I say@ylecun place a wager like any gentleman should do in an unresolvable disagreement. Let's put a stop to this nonsense! - 3 more replies
New conversation -
-
-
The original question was for machine learning in general, which is a vast superset of DL
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.