This chapter establishes why calculus is a useful tool for understanding and working with machine learning algorithms. We'll start by looking at the general role mathematics plays in ML before focusing on foundational concepts needed for calculus.

You will learn about:

• Functions: What they are, how they represent relationships between inputs and outputs (like mapping data features to predictions), and how to visualize them using graphs. We'll look at common types like linear functions, often represented as $y = mx + b$.
• Limits: The idea of approaching a specific value in a function. This concept forms the theoretical base upon which derivatives are built. We'll build intuition for what a limit signifies.
• Connection to ML: How these initial concepts relate to building and understanding machine learning models.

By the end of this chapter, you'll understand the necessity of calculus in ML and be familiar with the basic building blocks of functions and limits.