Creating a deep autoencoder using Deep Learning for Java (DL4j)
A deep autoencoder is a deep neural network that is composed of two deep-belief networks that are symmetrical. The networks usually have two separate four or five shallow layers (restricted Boltzmann machines) representing the encoding and decoding half of the net. In this recipe, you will be developing a deep autoencoder consisting of one input layer, four decoding layers, four encoding layers, and one output layer. In doing so, we will be using a very popular dataset named MNIST.
Note
To learn more about MNIST, visit http://yann.lecun.com/exdb/mnist/. If you want to know more about deep autoencoders, visit https://deeplearning4j.org/deepautoencoder. to complete the command. Close windows opened along the way. command. command. and click Other... until you reach the following window. In this window, fill out the Group Id and Artifact Id as follows or with anything you like. Click on Finish.
How to do it...
Start by creating a...
