Building a deep neural network

We are now ready to build a deep neural network. A deep neural network consists of an input layer, many hidden layers, and an output layer. This looks like the following:

The preceding figure depicts a multilayer neural network with one input layer, one hidden layer, and one output layer. In a deep neural network, there are many hidden layers between the input and the output layers.

How to do it…

1. Create a new Python file, and import the following packages:

   import neurolab as nl
   import numpy as np
   import matplotlib.pyplot as plt

2. Let's define parameters to generate some training data:

   # Generate training data
   min_value = -12
   max_value = 12
   num_datapoints = 90

3. This training data will consist of a function that we define that will transform the values. We expect the neural network to learn this on its own, based on the input and output values that we provide:

   x = np.linspace(min_value, max_value, num_datapoints)
   y = 2 * np.square(x) + 7
   y /= np.linalg.norm...