Understanding ML

In the introduction, we broadly defined the concept of ML as it pertains to this book. With that definition in mind, let's now take a look at some examples to elaborate on our definition. In its broadest sense, ML can be divided into four areas: classification, regression, clustering, and dimensionality reduction. These four categories are often referred to as the field of data science. Data science is a very broad term used to refer to various applications relating to data, as well as the field of AI and its subsets. We can visualize the relationships between these fields in Figure 5.1:

Figure 5.1 – The domain of AI as it relates to other fields

With these concepts in mind, let's discuss these four ML methods in more detail.

Classification is a method of pattern detection in which our objective is to predict a label (or category) from a finite set of possible options. For example, we can train a model to predict a protein...