Depth matters: expressivity in DNNs goes thru a phase transition with depth. https://arxiv.org/pdf/1606.05340v2.pdf … (warning: contains Riemannian geometry)
-
-
Replying to @fchollet
Pretty dense paper. Always happy to see new theoretical work on deep learning. We need more of it.
3 replies 1 retweet 6 likes -
Replying to @fchollet
Totally agreed on needing more theoretical work for DL. Any suggestions for pre-reading if I'm not well studied on Riemannian geo?
2 replies 0 retweets 4 likes
Replying to @Smerity
I found this enlightening and highly relevant to DL: https://www.amazon.com/Information-Translations-Mathematical-Monographs-Tanslations/dp/0821843028 …
8:21 PM - 8 Jul 2016
0 replies
0 retweets
15 likes
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.