Programming Machine Learning

Enter the Perceptron

To understand what a perceptron is, let’s take a look back at the binary classifier we wrote in Chapter 6, ​Getting Real​. That program sorted MNIST characters into two classes: “5” and “not a 5.” The following picture shows one way to look at it:

This diagram tracks an MNIST image through the system. The process begins with the input variables, from x₁ to x_n. In the case of MNIST, the input variables are the 784 pixels of an image. To those, we added a bias x₀, with a constant value of 1. I colored it a darker shade of gray, to make it stand apart from other input variables.

The next step—that yellow square—is the weighted ...