“I’m not saying I want to forget deep learning... But we need to be able to extend it to do things like reasoning, learning causality, and exploring the world .” - Yoshua Bengio, not unlike what I have been saying since 2012 in The New Yorker.https://www.technologyreview.com/s/612434/one-of-the-fathers-of-ai-is-worried-about-its-future/ …
-
-
How do we "reflect on where things stand" without empirical measures? I mean proofs would work, but don't seem nearly sufficient.
-
you have start by looking hard at failures, and what causes them. i documented some, now we have many adversarial cases, and things that are buried in footnotes like BERT’s failure on Winograd schemas
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.