News for hackers. Stuff that matters.
Re:Building autoencoders in Keras by _0ffh on Monday May 16, 2016 @11:13AM (#11706787)
"The old argument was that unsupervised pretraining helps get proper weights faster, but this has largely been disproven."

Do you hold that to be true in general, or only when using dropout?

There are no comments on this comment yet.