News for hackers. Stuff that matters.

A comment on Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer. Parent comment

Re:Outrageously Large Neural Networks: The Sparsely-Gated Mi... by Aeolos on Monday January 30, 2017 @08:07AM (#13520785)
> 2. You usually flatten right before the final layers.

The newer trend appears to be fully-convolutional networks even for classification, since they appear to overfit less, compared to flattening+dropout.

[ Parent | on HN ]
Re:Outrageously Large Neural Networks: The Sparsely-Gated Mi... by deepnotderp on Monday January 30, 2017 @10:20AM (#13521826)
Yup, but he asked me about where to use flatten, not whether to use flatten. But you're right, fully convolutional is the way to go in classification.
[ Parent | on HN ]