Chevron Left
Voltar para Mathematics for Machine Learning: Multivariate Calculus

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

4.7
estrelas
4,874 classificações
870 avaliações

Sobre o curso

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....

Melhores avaliações

DP
25 de Nov de 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.

SS
3 de Ago de 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.

Filtrar por:

801 — 825 de 873 Avaliações para o Mathematics for Machine Learning: Multivariate Calculus

por Elnur M

24 de Mar de 2020

Didn't like last two week

por Manuj M

10 de Jun de 2020

Professors were awesome

por danthedoubleD

14 de Mar de 2019

hopefully it is useful

por Philip A

16 de Mai de 2019

Excellent Instruction

por Kamlesh K

19 de Jun de 2020

It's just amazing.

por Dr. T C

19 de Jun de 2020

Very Good Course

por Jannatul F A

28 de Abr de 2020

Its very helpful

por raghu c b

2 de Abr de 2020

Less detailing

por Stathis

19 de Out de 2019

Good refresher

por Suyoun K

15 de Set de 2021

Good Course.

por Alfian A H

22 de Mar de 2021

Very good

por Hemant D K

17 de Dez de 2018

Its good.

por henry c

19 de Jan de 2020

It is ok

por R. D B D

7 de Mar de 2021

so hard

por MUTHUKUMAR P

26 de Set de 2021

Good

por Prof(Dr) S R

24 de Ago de 2019

nice

por Long Q

10 de Out de 2018

g

por Tony J

19 de Ago de 2020

Pretty good in terms of material covered. This course does a much better job of balancing what you should know vs pace than the linear algebra course (which breezed through or skipped a couple concepts that made it difficult to complete assignments or subsequent lessons).

Both courses so far would really benefit from another couple turns at the wheel in terms of polish, making sure that concepts are covered adequately and nothing is lost in the gaps. Also there is room for more and better 'further reading' pointers for those who are interested.

The biggest issue in both courses so far is the discontinuity when the lecturers (for whatever reason) switch in the last 2 weeks of the respective courses. Things seem to get lost or forgotten.

For example, in this course there's no mention in week 5 of how the previous week's topic relates to the material being covered, even though in the assignment there is a very interesting application of the topics in week 4 being presented, but it's completely hidden. And, judging from the forum posts from that week, the vast majority of students missed that insight.

I'm not sure why this course hasn't received any updates since it launched over 2 years ago. It's rough in more than a couple spots, but it could polish up really nicely.

por Maksim U

3 de Jan de 2019

I did learn quite a lot throughout the course. The problem is that most of my knowledge came from elsewhere while the explanations by the course instructors were quite unclear till I referred to extra resources. At the same time, some other explanations were on the obvious side, so I'd say the instructions are kind of inconsistent in their difficulty. The real-life examples were relly good though. The same concerns the quizzes, some are absolutely great and intuitive, while the others just leave you puzzled about what you are even expected to do with no extra info offered when failed.

The course is kind of sloppier than the first one and the reviews say the third one is even worse, so I won't be doing it.

Finally, I cannot even complete the last graded assignment and get my certificate as well as some other learners because the thing just throws an error all the time. There is zero reaction from the crew that is supposed to be moderating the forums.

All in all, a fine "guideline" course. But do not expect to be presented much inside the course itself.

por Pritam D

13 de Set de 2020

While the topics covered in the course are good, the depth and clarity with which each topic deserves to be explained, remains unfulfilled. The lectures are easy to understand, but sometimes you'll have to jump to other resources to get a better understanding of the topics covered. The difficulty of assignments is relatively very high, compared to their respective lectures.

Moreover, I feel that categorizing this course as a "beginner" course is somewhat questionable, as a complete beginner will face a lot of hurdles, given the number of new topics introduced in each lecture, the succeeding (often difficult) assignment, and the brevity of explanation. This course is more of an intermediate level, and some prior experience of Multivariate Calculus is required. I personally had glazed over Multivarious Calculus during my undergraduate, and even with that background, the difficulty seemed frustrating. For me, other resources, such as 3blue1brown youtube videos and Grant's KhanAcademy videos were necessary to complete the course.

por Leandro C F

22 de Mar de 2021

I've took the first course about linear algebra and it was brilliant. Unfortunately I did not have the same impression on this course.

The contents of the course is very important, but some topics were covered very quickly and superficially.

I also noticed that many people liked the first instructor, but for me the fact that he emphasizes one in every four words annoyed my learning experience. I spent more time paying attention in the emphasis than in the contents.

por Harsh D

14 de Jun de 2020

After the first course of the series, I expected more out of this. Certainly, the course covers basics but there's a gap in between the weeks. May be it was done to ensure the course could be restricted to 6 weeks, but then again course 3 is just 4 weeks. Not sure what happened there, this one certainly requires restructuring.

For Imperial College: If you would like to know what I am talking about, please go through the discussion forums.

por Paul F

10 de Mai de 2020

Towards the end, you see that the lecturers and the Team lost their motivation for a bit. Explanations are done very quickly and the exercises lack proper programming. The last one for example can't be passed if you write the functions in two different cells (as it is displayed in the workbook when you start), you need to copy them to one cell. This is really badly designed.

por Oliver K

1 de Fev de 2020

The first few weeks were a great introduction to derivatives, but the further it got the more the content seemed rushed and the exercises lazy. I will now go back and read secondary literature to really understand those parts, and not just calculate derivatives over and over. Samuel was a fantastic instructor though, kudos!