Building a recurrent neural network for sequential data analysis

Recurrent neural networks are really good at analyzing sequential and time-series data. You can learn more about them at http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns. When we deal with sequential and time-series data, we cannot just extend generic models. The temporal dependencies in the data are really important, and we need to account for this in our models. Let's look at how to build them.

How to do it…

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

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

2. Define a function to create a waveform, based on input parameters:

   def create_waveform(num_points):
       # Create train samples
       data1 = 1 * np.cos(np.arange(0, num_points))
       data2 = 2 * np.cos(np.arange(0, num_points))
       data3 = 3 * np.cos(np.arange(0, num_points))
       data4 = 4 * np.cos(np.arange(0, num_points))

3. Create different...