Chevron Left
Back to Mathematics for Machine Learning: Multivariate Calculus

Learner Reviews & Feedback for Mathematics for Machine Learning: Multivariate Calculus by Imperial College London

4,348 ratings
779 reviews

About the Course

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....

Top reviews

Nov 12, 2018

Excellent course. I completed this course with no prior knowledge of multivariate calculus and was successful nonetheless. It was challenging and extremely interesting, informative, and well designed.

Nov 25, 2018

Great course to develop some understanding and intuition about the basic concepts used in optimization. Last 2 weeks were a bit on a lower level of quality then the rest in my opinion but still great.

Filter by:

751 - 775 of 778 Reviews for Mathematics for Machine Learning: Multivariate Calculus

By Lee j

May 23, 2019

Too fast to understand what instructors says.. but lecture contents are good

By Akeel A

Aug 29, 2020

It was a lot of fun at points. Would recommend to anyone else.

By Gurrapu N

Apr 7, 2020

Strong disconnect between teaching videos and assignments.

By joseph k

Apr 13, 2020

Course would enhanced if pdf's of lectures were provided.

By Alkis G

Jul 14, 2019

There is a decent space for course improvement.

By prudhvi

Jun 23, 2019

week 6 content is not clear at least for me .

By Ahmad A

Feb 22, 2021

Too many Assignments and Quizzes to pass

By สิทธิพร แ

Jun 12, 2020

Week 5 and 6 Lecture quite poor

By Leigh F

May 29, 2019

Concepts not clearly explained.

By Aviv P

Dec 6, 2018

many topic were explained badly

By Vivek P D

Sep 10, 2019

Explanation is not in depth

By Mahmoud T

Mar 30, 2020

Dr.Sam Cooper is the best.

By Abdelftah M

Apr 5, 2020

Change the bald man.

By Rishabh J

Mar 8, 2019

Not very challenging

By Reena J

Dec 5, 2020

contents Are Useful

By Tianchi M (

Jul 4, 2018


By chanhee

Apr 17, 2020

It's nice

By Alexander M

Jan 23, 2020


By Alois H

Feb 18, 2021

The material is great and very relevant to anything connected to data science, however, I didn't enjoy this course half as much as the first in the series.

It's way too dense, things appearing on the screen where it's not clear where they're coming from, explanations feel scripted and read out at high speed, frequently unclear.

If you're using screen shots for taking notes (as I do), that's not ideal either because they're writing on a glass pane while they're standing behind it.

I'm working full-time and had to take this course stretched out over a long time. Again, the presentation being so dense doesn't help there either.

All in all it feels like a published first draft of the course, it doesn't seem the instructors are trying to improve the course at all.

By Paul K M

Oct 24, 2019

I am not sure if this course is for people who know calc, and want to learn python coding or people who know coding and want to learn some calc? Frankly it isn't a great course for either group. I knew some calc, and some python going in, and I did expand my knowledge and gain some useful practice. But it left me craving rigor.

By Mohammed A A

Jul 17, 2020

you must first give e more example and intuition

By Mariya O

Mar 6, 2020

I am extremely disappointed with these classes... if you think you would learn something/ especially as a beginner/, well, you won't...material is not well organized and presented, topics jump from one place to another, the quiz and assignments have nothing to do with the lectures...nothing is well could get more information/explanation from wikipedia ...if you are here so you can get a certificate- do it...but you are here to actually learn something- run away, you can learn more for free from Khan Academy lectures.

By Steve

Aug 5, 2020

The ideas the course hopes to present are good and relevant but the presentations are so poor that most of my learning of the material came from finding outside sources like Khan Academy. Often, important new ideas were roughly and quickly explained with not enough detail to give the student the intuitions needed for understanding. Often the practice quizes asked questions that were not properly covered in the videos so you need to go to the forums or elsewhere to gain the understanding needed.

By Hendrik V

Nov 5, 2020

The time required is not realistic. Had to put in exponentially more hours than suggested. Instructors are not involved in the course. You ask a question and in a couple weeks another student might help.

By Kimberely C

Dec 27, 2019

Definitely, not for beginners. Just as bad as the last one. They need to have more examples, which walk you through the ones like they give you on the homework as well as an example of how to do Python.