What you'll learn
What is calculus?
Multivariate chain rule and its applications
Taylor series and linearisation
Intro to optimization
This course offers a brief introduction to the multivariate calculus required to build many common machine learning techniques. We start at the very beginning with a refresher on the “rise over run” formulation of a slope, before converting this to the formal definition of the gradient of a function. We then start to build up a set of tools for making calculus easier and faster. Next, we learn how to calculate vectors that point up hill on multidimensional surfaces and even put this into action using an interactive game. We take a look at how we can use calculus to build approximations to functions, as well as helping us to quantify how accurate we should expect those approximations to be.
We also spend some time talking about where calculus comes up in the training of neural networks, before finally showing you how it is applied in linear regression models. This course is intended to offer an intuitive understanding of calculus, as well as the language necessary to look concepts up yourselves when you get stuck. Hopefully, without going into too much detail, you’ll still come away with the confidence to dive into some more focused machine learning courses in future.
Access to a computer or mobile device with an internet connection.
Motivation to learn!
There are no special materials or prerequisite knowledge required for this course.
Who this course is for
Students who are new to this field
Students willing to put in a couple hours to learn about Mathematics for Machine Learning: Multivariate Calculus
Advanced students wanting to add another skill to their portfolio
David Dye – Professor of Metallurgy – Department of Materials
A. Freddie Page – Strategic Teaching Fellow – Dyson School of Design Engineering
Samuel J. Cooper – Lecturer – Dyson School of Design Engineering
This course includes
Option for learning at your own pace
Videos and reading material about the course
Assessed tasks with feedback from other course participants
Evaluated tests with feedback
Evaluated programming tasks