Comentários e feedback de alunos de Mathematics for Machine Learning: Multivariate Calculus da instituição Imperial College London

If you do not have a background in programming, some of the assignments will be intimidating and hard to do but if you go over it sequentially you will get the hang of it but it will take you time to do so. The lectures are too short and I feel that some concepts were not clarified enough because of how fast the lecturers go over them. The course, in general, is good for having an overview of the material so do not expect to cover these topics deeply. The presentation and the way some concepts were tough were enjoyable and enriching.

I really love Samuel's teaching style. He strived to make people understood by showing a lot of graph and I can easily follow him step by step. However, David's teaching I couldn't follow up his mind much maybe because less explanations given during the lecture.

In addition, I found some quiz have huge amount of calculated amount which I really spent a lot time to verify the answer.

Finally, I hope more detailed explanations could be given if I made mistakes in some quiz so I could boost what I've learned so far.

Thanks,

Fang

The first 4 weeks of the course were amazing: great content, clear explanations and fair and interactive assessment activities. However, the last 2 weeks weren't as good as the previous ones. That's why I don't give this course 5 stars. By and large, the first two courses of this specialization are the best resources available on the internet to learn the foundations of mathematics for Machine Learning. I recommend that instead of doing the last course, you had better try to read the related book wrote by Deisenroth.

this course contains good lessons, and the level of assignments is proportional to what is being taught. there are some minor issues at some of the videos, but it´s possible to clear the doubts in foruns, in general, I´ve found this course the best one by far compared to other courses in coursera in which you have to spend a lot of time searching for extra information and content to accomplish the assignments. for the first time I felt the instructors actually taught the content.

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.

This course teaches multivariate calculus and its applications. In particular, Jacobian and Hessian Matrix are introduced as Matrix versioned derivatives (first order and second order), along with gradient descent optimization based on them. The structure of the course is a little bit loose, so it's not a good choice for those who want to seek systemically arranged learning materials. But it still worth taking for a better perspective and ideas.

Good course. I wish it had more sections as in a total of 12 sections or weeks and more steps to gain a more thorough graphical understanding (and perhaps even a more mathematical/algebraic understanding however overall that's much easier for me on that front...).

From a Data Science or Machine Learning perspective Week 6 (linear regression and non linear regression with chi-squared methods etc) were the most interesting.

Nice balance between rigor and developing intuition (again as in the previous linear algebra course in this series). I would’ve liked some “homework” reading about backpropagation for training the simple neural to prepare for the future courses. Also, more references for additional reading on least squares minimization techniques to tie more into the statistics underlying the techniques. I love the stuff, thank you!!

This course gives a great intuition about the calculus required for machine learning. Meanwhile the lecturers do not explain some concepts completely which is really bothering. In those situations always check the forum because you are not alone and other students probably had the same problem and someone would have explained it in more details or posted a link to a video that explains that concept in more details.

The course accomplishes its goal of connecting concepts in calculus to machine learning, and is appropriately paced for students who have covered calculus in the past and are seeking a refresher or deeper understanding of its applications to real-world problems. For those who don't already have a certain minimum familiarity with the mathematics, however, the course will probably move at too fast a pace.

Great class - very informative and eye opening - even with quite a bit of linear algebra background. Really liked the eigenvector and eigenvalue section - great descriptions. I wish the neural network discussion went on a bit further. I found some of the programming assignments' instructions a bit vague and confusing - what should have taken a few minutes ends up taking a half hour.

This course is great in the sheer efficiency with which it goes through the content required to prepare you for machine learning. It builds an intuition for what's going on, which is amazing. Some parts are confusing, and I recommend looking at Khan Academy for the lectures on Jacobians and steepest ascent, and 3Blue1Brown for feedforward neural networks.

Well the course is generally good, the only problem is that David sometimes may just skip the process and lack more explanation when performing the calculation, it's easy to lose track of what he is calculating if not reviewing the video over and over again, but anyway, the whole class is worth recommendation, thank you for your teaching, professors

This is a good calculus refresher and exploration of optimization processes and techniques. It goes rather fast and if you are rusty on the concepts you will need help from other sources such as Khan academy. I would have liked hands-on examples of using the functions in python libraries and matlab, as this was just a footnote on the last lecture.

It was exciting at some points. However, I left the course with the feeling that some subjects were not covered properly. The technical aspect of the course (e.g. video quality, visualizations, practice with python) were really great, lots of interesting and new teaching methods (at least for me). I wish this course was longer and more detailed.

Very valuable training course from the insight/intuition point of view. This is more of an overview of the calculus for machine learning giving the student a good direction of what to study and where to start from. I think that actually mastering the subject will require extensive additional exercises from other sources

Very helpful to review and get introduced to mathematical concepts behind machine learning. There is a fair bit of practical exercises as well. The only thing I am less happy about this cousre was a lack of additional suporting materials and references to other resources to help gain more knowledge on the subject.

I had no previous experience with multivariate calculus. This was a nice introduction to the topic, but in my opinion it does not allow me to say that "I know" multivariate calculus. Nevertheless, I think it is work taking as an introduction before going to more complete courses in multivariate calculus.

I think Samuel Cooper is an amazing instructor. However, the last two weeks taught by David Dye were very difficult to follow. I think David should improve his explanations because I did not enjoy too much his course on linear algebra, and this course was great until he started with the last two weeks.

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.

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)

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.

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.

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).

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.