Machine Learning, 2nd Edition

CHAPTER 8Support Vector Machines

With most machine learning tasks, the aim is usually to classify something into a group that you can then inspect later. When it's a couple of class types that you're trying to classify, then it's a trivial matter to perform the classification. When you are dealing with many types of classes, the process becomes more of a challenge. Support vector machines help you work through the challenging classifications.

This chapter looks at support vector machines: how the basic algorithm works in a binary classification sense, and then an expanded discussion on the tool.

What Is a Support Vector Machine?

A support vector machine is essentially a technique for classifying objects. It's a supervised learning method, so the usual route for getting a support vector machine set up would be to have some training data and some data to test the algorithm. With support vector machines, you have the linear classification—it's either that object or it's that object—or nonlinear. This chapter looks at both types.

There is a lot of comparison of using a support vector machine versus the artificial neural network, especially as some methods of finding minimum errors and the Sigmoid function are used in both.

It's easy to imagine a support vector machine as either a two- or three-dimensional plot with each object located within. Essentially, every object is a point in that space. If there's sufficient distance in the area, then the process of classifying is easy ...