![Szilard [Deeper than Deep Learning]](https://pbs.twimg.com/profile_images/1016878602653085696/9RaALXe__normal.jpg)
I think most ML researchers would agree. The problem is that abstraction & reasoning are pretty vague concepts. The challenge is to operationalize these notions in a way that yields measurable improvements on hard benchmark tasks.
-
-
-
no, the problem is not just about operationalizaron.
@allenAI’s science exams are an example of reasonable task that rests partly on reasoning ; the deeper problem is that we as a field currently lack the tools to make measurable progress there. - 1 more reply
New conversation -
-
-
This Tweet is unavailable.
-
why did you pass
#godzilla2?
End of 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.