MA! Here for a workshop, a few free hours in a beautiful park in beautiful weather. My summer project is catch up on ML as much as I can.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Heh. My question is more like what are all the other things going on besides bias-laundering from human-generated training data.
-
Feel like we need more imagination about what else could go awry or weird.
End of conversation
New conversation -
-
-
@goodfellow_ian 's Adversarial examples that fool image classification algorithms by carefully adding noise http://karpathy.github.io/2015/03/30/breaking-convnets/ …pic.twitter.com/iuZey1n1Q9
-
thank you!
- Show replies
New conversation -
-
-
Just realized that the Google cat recognition paper is... merely five years old. A doctoral student who started before may not even be done.
-
A lot of people refer to deep learning papers from 2014 as "classic"
- Show replies
New conversation -
-
-
Read what you can find about AlphaGo.
-
Feel free to rec papers too. So many interesting papers.
- Show replies
New conversation -
-
-
thank you!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.