Bayesian Scale mixtures for dropout in neural net. New weight pruning beats SNR,matches retraining with soft targets. http://goo.gl/DbePEU
12:25 PM - 14 Jun 2015
0 replies
2 retweets
8 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.