Creating a Deep Belief neural net using Deep Learning for Java (DL4j)

A deep-belief network can be defined as a stack of restricted Boltzmann machines where each RBM layer communicates with both the previous and subsequent layers. In this recipe, we will see how we can create such a network. For simplicity's sake, in this recipe, we have limited ourselves to a single hidden layer for our neural nets. So the net we develop in this recipe is not strictly speaking a deep belief neural net, but the readers are encouraged to add more hidden layers.

How to do it...

1. Create a class named DBNIrisExample:

           public class DBNIrisExample { 
   

2. Create a logger for the class to log messages:

           private static Logger log = 
             LoggerFactory.getLogger(DBNIrisExample.class); 
    
   

3. Start writing your main method:

           public static void main(String[] args) throws Exception { 
   

4. First, customize two parameters of the Nd4j class: the maximum number of slices to print and the...