News for hackers. Stuff that matters.
Re:A Probabilistic Theory of Deep Learning by Nvn on Friday April 03, 2015 @04:20PM (#9318230)
> If this model can provide an explanation for the small noises impacting NN performance on images (from karpathy.github.io, posted to HN earlier today) then that would be rocking

This paper [0] does a pretty good job of giving an explanation for that.

[0] http://arxiv.org/abs/1412.6572

Re:A Probabilistic Theory of Deep Learning by disgruntledphd2 on Friday April 03, 2015 @06:14PM (#9318913)
Honestly, that abstract makes me more upset. If these are due to NN's nature as linear classifers, then we are all in trouble, given that almost everything useful is based off linear models. Given the title of the paper though, I should probably be more hopeful :)