Gary Marcus

Watch anyone of my talks of the last 4 years. Many even have the title "the power and limits of deep learning" More obvious answer: limitations are pretty much everything everyone in the field is doing research on: self-sup learning, model-based control, reasoning, causality...

agree with @ylecun on much of this list, and tried (among other things) to explain many of them (sometimes with slightly different terms) to the general public in http://rebooting.ai , because few seem to be widely understood or appreciated.

Lack of generalization outside of the training set makes DL (maybe not all *possible* ML) inappropriate for many problems. Ultimately, the limitation of ML is our own: failure to architect solutions that lever it but also (will) use other tech to advantage

that of course has been my central point since 1998; it rarely appears in discussions of deep learning results, though at this point it is widely known within the field.

What even is "ML"? I think it's trivial to point to a specific model is rattle off its limitations. Well-defined class of models: basically the same. General toolkit and way of approaching a problem: more difficult. ML is more the latter, no?

so what are the well-defined classes of models for which you personally publicly acknowledge limitations @roydanroy? (and which limitations).

can you list here a couple examples of specific limits?

AI can't reason by analogy. Everyone should acknowledge that.