Many of the autoencoder examples I see online use relu() activation for interior layers. The relu() function was designed for use with very deep neural architectures. For autoencoders, which are ...

A limitation of the autoencoder architecture presented in this article is that it only has a single hidden layer. Neural autoencoders with multiple hidden layers are called deep autoencoders.

Fig 2. The deep learning architecture of the Breast Cancer Risk Calculator system. We developed the model with two autoencoder deep networks and one multilayer perceptron. The medical image ...