“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/ …
-
-
Nature DL Review ends with "new paradigms are needed to replace rule-based manipulation of symbolic expressions by operations on large vectors" Bengio promoting DL & Unsupervised for at least 10 years. "From Machine Learning to Machine Reasoning": https://arxiv.org/abs/1102.1808 (2011)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Gentlemen, the most important thing is that field has come this introspection collectively. Now it is essential that another hype cycle isn't created, but this momentum to investigate intelligence decoupled from the brain workings, is sustained for decades to come.
@fcholletThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
(a useful reminder that there are some things humans do that AI will never do)
- 1 more reply
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.