Classifying with Real-World Examples

The topic of this chapter is classification. In this setting of machine learning, you provide the system with examples of different classes of objects that you are interested in and then ask it to generalize to new examples where the class is not known. This may seem abstract, but you have probably already used this form of machine learning as a consumer, even if you were not aware of it: your email system will likely have the ability to automatically detect spam. That is, the system will analyze all incoming emails and mark them as either spam or not spam. Often, you, the end user, will be able to manually tag emails as spam or not, in order to improve its spam detection ability. This is exactly what we mean by classification: you provide examples of spam and and non-spam emails and then use an automated system to classify incoming emails...