Python Machine Learning Cookbook - Second Edition

How it works...

In this recipe, we used a single neuron that performs all the computations. To train the perceptron, the following parameters are set. The number of epochs specifies the number of complete passes through our training dataset. The show parameter specifies how frequently we want to display the progress. The lr parameter specifies the learning rate of the perceptron. It is the step size for when the algorithm searches through the parameter space. If this is large, then the algorithm may move faster, but it might miss the optimum value. If this is small, then the algorithm will hit the optimum value, but it will be slow. So, it's a trade-off; hence, we choose a value of 0.01.