The level of hype around deep learning has become so high, there's no way it can live up to the expectations. No matter how much it delivers
-
I've wanted to write about realities of ML/AI but there's no way that gets popular. Ranting about bots gets you front page though.
-
-
http://smerity.com/articles/2016/architectures_are_the_new_feature_engineering.html … was a (technical) first pass. Next planned post is vanishing / exploding gradients. Maybe after that?
-
@etzioni had a great article recently that's less technical, so likely to hit a broader audience, at http://www.wired.com/2016/06/deep-learning-isnt-dangerous-magic-genie-just-math/?mbid=social_twitter …
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.