good

I liked the course specially because I finally understood Backpropagation, an old frustration from Andrew Ng's Machine Learning course. It covers the main topics for Mathematics for Machine Learning as promised. Two weak points: (1) the Newton-Raphson convergence problems, superficially covered in the lectures, but has a challenging test, no forum support, no other source indicated for helping us. (2) The forum is abandoned. I've set two problems, one of them about an error in a lecture and the second about the problem with Newton-Raphson lecture. No responses from the lecturers or mentors.

The course was ok. Specially the first four weeks. However, on week 5 and week 6, there is a change of instructor. He talks very fast, and do not stop to explain with greater detail the concepts, nor he visualise with examples. He just declares what's happening. with now emphasis on the underlaying concept, which makes the subject, already complicated, more challenging. Conversely, the first instructur has a gift for teaching. He really knows how to portray calculus in an easier way to visualise.

It starts brilliantly, but the last 2 weeks are quite bad. It has nothing to do with the new teacher taking over that part, I think he is as good as the other one. It's a matter of goals and focus. It seems like everything you learn in those weeks are just random things and little 'magic tricks', it's hard to see why they're relevant to the subject and everything seems disconnected.

Still, I really enjoyed the first 4 weeks. Awesome content, they made me realize I love calculus.

At points you feel you got the hang of it and next thing you know the information comes in big waves and too suddenly that you feel lost. General experience was okay but I'm not too sure if this course series suits a beginner on the subject.

Relevant content. Great instructions. Likable instructors. Very bad coding assignments.

I'd have loved to give a 5 or at least a 4-star but really the explanations on each topic have gaps, which make it super hard to know what really was going on. One could have never completed this entire specialization with only the materials in the course. A lot of further research is required to understand the concepts and to complete the assignments. The 2 stars I gave are mainly for the assignments which help to reinforce the learning and the help that other students provide in the forum. However, I don't regret having taken this course. I'm just little disappointed because I thought I'd have gotten more out of this course than I actually did.

Course videos and quizzes are good and content is clearly explained. However, too many concepts are covered with too little depth. For example least squares and non-linear least squares involve fundamental concepts that should be covered and alone, would at least 2 weeks to teach. Lagrange multipliers and Taylor series are barely introduced with very little mathematical derivation involved. I had the impression that I would learn more mathematical theory than machine learning in this course, it didn't turn out to be so.

This mathematics for machine learning course is not a mathematics course. It starts well, explaining mathematical concepts and, suddenly: neural networks, python programming, numpy, scikit... The speed at which the concepts are explained makes it impossible to assimilate anything unless you already know the concepts beforehand, which means this course only serves as a refresher course.

Instructions were very poor in many cases , Khan Academey is much better source for explanation of concepts

Instrructions on PCA are so Awful , that I decided to drop from the course

pathetic course

A truly amazing course!

The Calculus course from the Mathematics for ML specialisation is a really fun and effective way of learning. I think that it takes lots of skills and hard work to prepare course like that. It starts very gentle so that it's easy for those who haven't done calculus for a long time, but after refresing on the basics, it jumps to more interesting topics to end up in Taylor series for approximations, Lagrange multipliers, the chain rule application for deriving backpropagation algorithm and some basic optimisation algorithms.

All along they way they're showing everything visually, so that we can build intuitions to have confidence in using the math later on, when there are too many dimensions to visualise the function. The exercises are enough to start feeling comfortable with doing calculations by hand, while the programming assignments shows how to do that in code. Really nice bonus are interactive materials where we can really feel what the math and the algorightms are about (it's great for building intuitions).

Extremely well built course. The quality of materials is excellent and practice exercises really help to deepen the understanding. But what I did like the most were programming assignments, where students are asked to implement mathematical equations as python scripts. The reason I liked such assignments so much was that I needed to build a general understanding (and sometimes come up with general solutions on paper) before writing the code. I did not need any background knowledge of python, because I only needed to write arithmetical equations, pretty much using python as a calculator. In that way I had a chance to focus on the subject matter while leaving python do all the calculations. Now, if I screwed up something in my equations, there were tests written for me, where I could check my solution (e.g. presenting visually how well my script did etc.). That really helped the learning process.

Although the course doesn't cover all of the details of a traditional calculus course, it helps you build an understanding of the fundamentals in the language of calculus, as well as some intuition as to where it might be usefully applied in machine learning.

The lecture videos are top notch and overall both instructor do an amazing job in teaching and developing the intuition required to understand the meaning of the tools used in multivariate calculus. The quizzes are strongly related to what's taught and even what's best, the programming assignments (for which is not required any programming ability) show how to use in practice what you learned.

I think the enthusiasm of the instructor is the cherry on top since it makes a huge difference when it comes to delivering the content precisely and effectively.

It's great, however if you are hoping that they would teach you to differentiate like teachers in high school then you are in the wrong place. But, if you want to build an intuition about calculus, optimization techniques, neural networks then you are in the right place. Personally, I was good at calculus in school so it was relatively easy for me, but if that's not the case for you I would recommend that you brush up your basic differentiation. Also basic knowledge of python numpy library would be super useful. Also this course will introduce some really scary looking formulas, so don't be intimidated they just look scary. Best of Luck !

A solid course, recommended for those who want a deeper understanding of the math behind machine learning. It is well taught and organized, with many quizzes so students work through problems themselves,

However,

a) don't think for a moment that a six minute video can be absorbed in six minutes, or a quiz can be completed in the suggested time. From my experience, count on taking twice as long

b) there are so many concepts introduced that I needed to refer a number of times to outside resources like Khan Academy or 3 Blue 1 Brown

Overall, a worthwhile course.

D

David and Sam are amazing: The found the right balance between bulding up intuition and mathematical rigor. Also their use of coding labs is spot on: Not too much coding language related complexity that would distract from the real objectives of the course, while not making out of the labs a trivial exercise of code copy/paste.

While I did Multivariate Calculus in depth back in University, that was 30 years ago, and I needed a good refresher before taking on some advanced ML/AI courses. This Maths for ML specialization did hit the spot.

You will need the basics of Calculus in place. You can't just wake up and start Calculus with this course. With that said, the basics covered serve to be a good revision of the calculus. Certain applications such as the Neural Networks have been done hastily as others say on the forums (and I wholeheartedly agree) but then again this is not a course on Machine Learning. still some more examples from the instructors wouldn't hurt :) The exercises are great. Neither too hard nor too tough.

Simply excellent course. The breadth of topics one needs to cover is astounding. I liked the way the topics and ordered, and following a common structure. The best part is the assignments - one really needs to understand every word of what the instructor says to solve it. They are tough in general to anyone who's done their bachelors/masters long time ago. For those who are not used to programming, the assignments can be difficult.

Amazing instructors and well designed course. Definitely a recommendable course to get intuitive knowledge on mathematical concepts that are relevant for machine learning. What I especially loved about it: it neither went too much into annoying and exhausting detail, nor was it simple. If you take this course, take some time to concentrate and get the brain cells running - will be a satisfying and rewarding experience! 11/10!

It took me at least 3 hours every day to understand and absorb the contents. It's that I'm not a native English speaker and I'm almost in the dark about mathmetics which is covered at university. Nevertheless, every step in the course was worth investing. I could know why I, as a would-be developer, should understand and keep mathmetics in my head. I downloaded all videos of this course and I'm gonna repeat them.

This is my first encounter with Multivariate Calculus and surely the course has been extremely helpful beginner-friendly. I recommend investing in practical mathematics courses as this specialization if you are new to machine learning field. You will be equipped with enough math background and should feel confident to enter more technical machine learning/deep learning courses.

A truly fundamental stepping stone!

I learned limit, derivatives and integrals in high school. Afterwards, I took a few calculus lessons at university. However; I have never got a chance to see this theoretical background to put into practice. For this reason, I have never learned the essence of which means is calculus. I wouldn't have gotten a detailed education on this topic anywhere in Turkey. It was crucial for me, thank you for all !

The videos are well designed and are direct in teaching the course material. For those with Calculus experience, it acts as a nice refresher and further expands it through higher dimensions. For those planning to learn more about Machine Learning and data science, the course also bridges mathematical gaps. Overall, I learned a lot and had fun while taking the course.