Gary Marcus

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 …

Many limitations in the sense that they're active topics and we don't have answers yet (out-of-distribution testing, not "understanding" at the right level of abstraction, causality, etc), but I wouldn't classify any needing a paradigmatic shift of techniques

Given it's not really falsifiable to say "a neural network can't do this", and yet there may be things out there that work much better than deep learning for much of this - at what point would you say a paradigmatic shift *is* needed? What's the threshold?

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.)