Building a perceptron

Let's start our neural network adventure with a perceptron. A perceptron is a single neuron that performs all the computation. It is a very simple model, but it forms the basis of building up complex neural networks. Here is what it looks like:

The neuron combines the inputs using different weights, and it then adds a bias value to compute the output. It's a simple linear equation relating input values with the output of the perceptron.

How to do it…

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

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

2. Define some input data and their corresponding labels:

   # Define input data
   data = np.array([[0.3, 0.2], [0.1, 0.4], [0.4, 0.6], [0.9, 0.5]])
   labels = np.array([[0], [0], [0], [1]])

3. Let's plot this data to see where the datapoints are located:

   # Plot input data
   plt.figure()
   plt.scatter(data[:,0], data[:,1])
   plt.xlabel('X-axis')
   plt.ylabel('Y-axis')
   plt.title...