Calculus For Machine Learning

Calculus is an important field in mathematics and it plays an integral role in many machine learning algorithms. If you want to understand what’s going on under the hood in your machine learning work as a data scientist, you’ll need to have a solid grasp of the fundamentals of calculus.

In this Calculus for Machine Learning course, you will learn the mathematical concepts for algorithms such as the gradient descent algorithm and backpropagation to train deep learning neural networks.

You’ll learn about linear and nonlinear functions. You will learn the fundamental parts of a linear equation to decompose a linear equation into slope and y-intercept. You will also build up an intuition for what slope is and how to calculate the slope.

You’ll also dig into what limits are, and learn how to compute them in Python using SymPy, which is a Python library for symbolic computation. And of course, it wouldn’t be a calculus course if you didn’t learn about derivatives!

After you complete this course, you can feel confident that you know the necessary calculus fundamentals for intermediate machine learning techniques.
By the end of this course, you’ll be able to:

  • Understand the key ideas from calculus for understanding how mathematical functions behave.
  • Apply the calculus concepts learned to intermediate machine learning techniques.

Calculus For Machine Learning Lessons List

Understanding Linear and Nonlinear Functions

Learn the basics of slope to understand mathematical functions.

Understanding Limits

Learn how to calculate slope for nonlinear functions at specific points using limits.

Finding Extreme Points

Learn how to use a function derivative to find extreme points.