Back to Mathematics for Machine Learning: Multivariate Calculus

stars

5,631 ratings

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....

SS

Aug 3, 2019

Very Well Explained. Good content and great explanation of content. Complex topics are also covered in very easy way. Very Helpful for learning much more complex topics for Machine Learning in future.

JT

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.

Filter by:

By Christian S

•Apr 17, 2021

Very solid introduction into Calculus. Keep in mind that this is a course meant to give you an intuition and basic understanding. Sometimes there are small gaps in the curriculum to the quiz (but you will easily be able to make up for them by just reading the according Wikipedia page). Was a pleasure.

By Abhirup B

•Aug 30, 2020

exercise and programming assignments are good ....and i can grow a sound concepts after completeing them.lectures are also good ...but some lecatures are too quick and a little elaboratiion in some places would have been helpful(particularly those in the last couple of lectures)

By Kevin E

•Jun 15, 2020

Excellent course. It covers so much without making me feel overwhelmed. I would like to see more hands-on demonstration on linear and non-linear regression, but I was able to complete the quizzes and assignments. This without any previous multivariate calculus instruction.

By Divyang S

•Aug 8, 2020

Overall a good course to give us a better idea of what sort of math is used in ML. But I feel they went too fast in this course, so I personally lagged a bit in understanding certain crucial concepts. Also, it'd be much help if the instructors could mention reference books.

By Michelle W

•Nov 17, 2019

I would say this entire series is better advertised as a quick *review* of the pertinent concepts. Otherwise, someone with no background in the topics covered may struggle (unless they are particularly talented with quickly learning new mathematical concepts).

By Shintya R R M

•Mar 6, 2021

This course is good to start learning Machine Learning. There are also labs practice so that I can acquire deeper understanding by the visualization. However, some materials are not explained clearly, such as Newton-Raphson method and Lagrange Multiplier.

By Glendronach 3

•Mar 22, 2020

This felt like time well spent. A really good course which I should have taken before doing the Machine Learning Course by Andrew Ng. That would have made life easier.

Beware, the 'gradient of the learning curve' at any point during this course is steep.

By 胡震远

•Aug 30, 2020

Generally, it is a good course. Many new tools and fancy representation method, but for mathematical idea and explanation, it is just too simple. Maybe the biggest contribution to me is that It lets me know the Kahn Academy and 3b1b courses.

By Aditya J

•Apr 13, 2020

Could have explained in a way that the audience requires a slower and better and little more in-depth explanation. Some places felt a little rushed, so had to spend more time in forums and other resources to get more idea. Overall was great.

By Tai N

•Jun 25, 2021

This course assumes some knowledge of Python. Some topics are taught quite quickly, and overall this is not a comprehensive course. A good introduction to multivariate calculus. I suggest learners use Khan's Academy in supplement to this.

By Sirigiri S K

•Jan 13, 2020

Need a bit more clarity in terms of integrating the calculus in the last week sessions.

I agree they are very good but would be great if there is some more additional clarity. And also some project using the whole course would be helpful.

By Ankit C

•Mar 28, 2020

It gives you a good head-start to the math required in Machine learning. Some major concepts are touched just on the surface level but the mathematics involved in those concepts is explained quite well. Overall, it's good experience

By sujith

•Sep 16, 2018

Very good course to start of with mutivariable calculus basics. Helps to refresh your memory if already familiar with concepts, additionally helps in getting fresher perspective because of geometrical intuition presented very well.

By Switt K

•Jul 27, 2020

Good details, great at building intuitions. Instructors are pleasant to listen to :)

As expected, it's enough to get you going in the right direction, that if you want to know more, you'd have enough knowledge to build on from.

By Γιώργος Κ

•Sep 21, 2018

Lack of support from the staff. Some parts/lectures are not clearly explained (for example, constrained optimization) and some quiz questions are not directly related to the course content. Otherwise, it's a very good course.

By Jacqueline B

•Apr 6, 2020

up to week 5 , it was masterpiece.

week6 (although it should be the most important one) was a mess and disappointing.. as it was not explainable, i couldn't link what is happening with previous weeks.. require to be enhanced

By Jae N

•May 5, 2022

This was a good course. The instructors kept me interested in a rather dry subject. The exercises were well designed. There are courses on Coursera which are not worth the time. This course is not one of those.

By Izzan D

•Mar 29, 2020

The first 3 weeks is really good, the fourth week is okay but the last 2 weeks is kinda confusing. The explanation is quite clear but it is quite hard to grasp the intuition and relationship between each material.

By Peiyuan C

•Sep 29, 2018

Along with the advanced and popular technique, this course gives me impressive insight over how machine learning works. But it would be much better if the concept in linear algebra combines more with this course.

By Girisha D D S

•Aug 26, 2018

I thoroughly enjoyed this course. The materials were good and the course content was good enough to pass all the assignments and quizzes. This is way better than the linear algebra course in this specialization.

By Igor C A d L

•Apr 3, 2022

All was great until weeks 5 and 6. For these weeks, there weren't enough explanations in order to really understand the subject. Some very important steps were simplified, which made understanding difficult.

By Mrinal S

•Jun 7, 2018

i think some of concepts touched the surface and it was difficult to get a deep understanding .Probably the course could have provided some external links for those topics where people could read .

By Ashish k

•Jul 28, 2019

Superb quality. The way instructors teach is really innovative. The course is good in terms of the area it covers but lacks depth, but is a good starting point if you want to dwell more in detail.

By Keshav B

•Jul 24, 2020

Very informative refresher on the basics of differentiation, though some of the later topics could have been fleshed out more (i.e. Taylor Series, Lagrange Multipliers, etc). Overall very good.

By Marcus V C A

•May 18, 2022

This course is good in general. But some parts, like the Lagrange Multipliers, needed better explanation and more exercise before testing. I also missed more supplementary material.