Deep Learning: Practical Neural Networks with Java

The neural network class

Finally, let's define the neural network class. It has been known so far that neural networks organize neurons in layers, and every neural network has at least two layers, one for gathering the inputs and one for processing the outputs, and a variable number of hidden layers. Therefore our NeuralNet class will have these properties, in addition to other properties similar to the neuron and the NeuralLayer classes, such as numberOfInputs, numberOfOutputs, and so on:

public class NeuralNet { private InputLayer inputLayer; private ArrayList<HiddenLayer> hiddenLayer; private OutputLayer outputLayer; private int numberOfHiddenLayers; private int numberOfInputs; private int numberOfOutputs; private ArrayList<Double> input; private ...