Programming Machine Learning

Chapter 12How Classifiers Work

We spent most of this book building classifiers—first a perceptron, and now, in the last few chapters, a full-fledged neural network. And yet, you might struggle to grasp intuitively what makes classifiers tick. Why do perceptrons work well on some datasets, and not on others? What do neural networks have that perceptrons don’t? It’s hard to answer these questions, because it’s hard to paint a mental image of a classifier doing its thing.

The next few pages are all about that mental image. A new concept, called the decision boundary, will help us visualize how perceptrons and neural networks see the world. This insight is not only going to nourish your intellect—it will also make it easier for you to build and ...