As we learned in the first chapter, supervised learning is one of two major branches of machine learning. In a way, it is similar to how humans learn a new skill: someone else shows us what to do, and we are then able to learn by following their example. In the case of supervised learning algorithms, we usually need lots of examples, that is, lots of data providing the input to our algorithm and what the expected output should be. The algorithm will learn from this data, and then be able to predict the output based on new inputs that it has not seen before.
A surprising number of problems can be addressed using supervised learning. Many email systems use it to classify emails as either important or unimportant automatically whenever a new message arrives in the inbox. More complex examples include image recognition systems, which can identify what an image...
