As I understand it, the only difference between them is the way the two networks are trained. Deep autoencoders are trained in the same way as a single-layer neural network, while stacked autoencoders are trained with a greedy, layer-wise approach. Hugo Larochelle confirms this in the comment of this video. I wonder if this is the ONLY difference, any pointers?


Autoencoders with multiple hidden layers are called stacked autoencoders or deep autoencoders.*

They are the same thing.

*See Hands-On Machine Learning with Scikit-Learn and Tensorflow by Aurélien Géron for a good overview of the different types of autoencoders.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.