Re:Keras-based molecular autoencoder
by InquilineKea on Tuesday October 25, 2016 @11:12AM
(#12788627)
What's the point of the autoencoder? Why use those instead of CNNs?
[ Parent
| on HN ]
autoencoders are unsupervised learning where CNNs are supervised. Learning the input space can be thought of as a form of regularization when training data is scarce. http://www.deeplearningbook.org/ is a wonderful resource to learn more about why and when to use different architectures.