Kernel Methods
Our remaining chapters will now focus on more advanced topics. Due to their advanced nature, we will not attempt to cover them in the same level of detail as we have done for the topics of earlier chapters. Instead, we will focus on getting the essential concepts and ideas behind these topics across. The aim is not to make you an expert in these topics but to introduce you to them so that you can recognize them when you see them again, or if you want to learn more at a later date. This focus on the essentials means that each of these chapters on advanced topics will be shorter than previous chapters.
The first of our advanced topics is kernel methods. Kernel methods, or kernelized learning algorithms, are very widely used. The math they are based on is both advanced and elegant. That math relates to machine learning algorithms that make use of similarities between feature vectors. To understand kernel methods, we will need to understand why similarity-based learning...
