Hands-on RNNs with Spark

Let's start now being hands-on with RNNs. This section is divided into two parts—the first one is about using DL4J to implement a network, while the second one will introduce using both DL4J and Spark for the same purpose. As with CNNs, you will discover that, thanks to the DL4J framework, lots of high-level facilities come out-of-the-box with it, so that the implementation process is easier than you might expect.

RNNs with DL4J

The first example presented in this chapter is an LSTM which, after the training, will recite the following characters once the first character of the learning string has been used as input for it.

The dependencies for this example are the following:

• Scala 2.11...