We will train a neural network to classify two clusters in a 2-dimensional space. The points of the clusters will be randomly created with the help of a line function L: The points of class2 will be above the line and the points of class1 will be below the line.
The neural network will find a line - the so-called decision boundary - that separates the two classes. (This line should not be mistaken for the line, which we used to create the points.)