Chevron Left
Mathematics for Machine Learning: Linear Algebra(으)로 돌아가기

임페리얼 칼리지 런던의 Mathematics for Machine Learning: Linear Algebra 학습자 리뷰 및 피드백

8,172개의 평가
1,646개의 리뷰

강좌 소개

In this course on Linear Algebra we look at what linear algebra is and how it relates to vectors and matrices. Then we look through what vectors and matrices are and how to work with them, including the knotty problem of eigenvalues and eigenvectors, and how to use these to solve problems. Finally we look at how to use these to do fun things with datasets - like how to rotate images of faces and how to extract eigenvectors to look at how the Pagerank algorithm works. Since we're aiming at data-driven applications, we'll be implementing some of these ideas in code, not just on pencil and paper. Towards the end of the course, you'll write code blocks and encounter Jupyter notebooks in Python, but don't worry, these will be quite short, focussed on the concepts, and will guide you through if you’ve not coded before. At the end of this course you will have an intuitive understanding of vectors and matrices that will help you bridge the gap into linear algebra problems, and how to apply these concepts to machine learning....

최상위 리뷰


Dec 23, 2018

Professors teaches in so much friendly manner. This is beginner level course. Don't expect you will dive deep inside the Linear Algebra. But the foundation will become solid if you attend this course.


Aug 26, 2018

Great way to learn about applied Linear Algebra. Should be fairly easy if you have any background with linear algebra, but looks at concepts through the scope of geometric application, which is fresh.

필터링 기준:

Mathematics for Machine Learning: Linear Algebra의 1,638개 리뷰 중 51~75


May 17, 2019

This course reviews the essential concept of linear algebra in the context of machine learning. However, it would be much better if it provided more optional exercise and reading materials.

교육 기관: Ralph T

May 04, 2019

decent course. It gives a good enough background to understand the mathematics necessities of many areas of data science. could be more thorough and dive deeper into some of the content.

교육 기관: Mark J T

Aug 02, 2019

Good course because it shows how to understand geometrically, things that I had hitherto only understood computationally.

교육 기관: Philip A

May 16, 2019

Excellent Instruction

교육 기관: Neel K

May 10, 2020

For the most part, I enjoyed this course. Most of the math explained is fairly easy to understand. They cover the fundamentals of linear algebra, and provide plenty of assignments and practice exercises to test your knowledge. However, some of the video explanations are extremely confusing and feel rushed. For example, some videos in Week 4 and 5 like Reflecting in a plane using Gram-Schmidt and the PageRank algorithm were so hard to understand that I had to learn about them from elsewhere on the internet (I used MIT OCW a lot). This isn't very convenient, especially if you're paying for the course. Furthermore, I felt like more videos explaining the applications of linear algebra in machine learning could've been made, and the ones that were already made could've been made in more detail (for example, the term 'span' was never formally explained). Lastly, I would've loved it if there was another week dedicated solely to introduce the coding bit, because it's really difficult and takes a while if you have little or no prior experience in python. All in all though, I enjoyed this course, and I would recommend trying to complete both Linear Algebra and Multivariate Calculus in one month, because it's not worth paying more than that.

교육 기관: Maytat L

Nov 20, 2019

Challenging course. Much more difficult that I expected. It took me 7-9 hours a week. The overall course material itself was good building-blocks to further understand application of machine learning. However, explanation in some topics should have more detailed explanation and examples to further understand the concept. There were many times, I need to re-watch each video over and over again, paused it, and figured things out on my own. The programming assignments were the most challenging task. I just began to learn Python and found it very difficult because there were so many codes I haven't learnt before. I think for those who has not learnt Python at all may find really really difficult to pass the assignments.

교육 기관: Peter B H

Nov 27, 2019

The content was good, but a couple of times what was said didn't gel with what was being drawn/written/done. Since I'm learning, this took me longer to double check when I misunderstood something whether it was the concept or a mistake in the delivery.

교육 기관: Pedro C O R

Aug 02, 2019

The topics could be improved in the way they are presented. I always had to search for additional material.

However, the course is okay, it could be better, the forum is not that active, and some assignments are good.

교육 기관: kai k

May 05, 2019

many of the activities are excellent, but videos hard to follow along to at times - play them at 0.75 speed if you can. Also, the faculty is not super responsive it seems on discussion boards creating some confusion

교육 기관: Girisha D D S

Aug 27, 2018

Although the course content is good, I feel it could have been done better. I enjoyed the multivariate calculus course compared to this course.

교육 기관: Maximilian P

Dec 12, 2018

Some exercises are completely incoherent to the preceding videos, which makes it very difficult to solve them. very frustrating

교육 기관: Mesum R H

Aug 26, 2018

The course tries to cover every edge of Linear Algebra but fails to integrate each step with what relationship it has with Machine Learning. Core Formulas and Mathematical derivations are shoved down from throat without any respect for learners from non-engineering or computer science background. Other than week 1,2 rest was completely case study or example less UN-intuitive lectures of matrix formations and transformations. Needs a severe revamp with better examples and broader picture.

교육 기관: Anonymous

May 09, 2018

The content and the speed are not satisfactory.

The speed totally hampers the content, lots of things aren't explained especially after Sam took over in the last module.

Other than the first 2-3 intuition videos and the programming assignment nothing was good in the 5th module/week.

It was very very difficult to follow the page rank video. I still don't understand it. For eigen basis I had to refer to other material outside this course.

교육 기관: Jorge N G

May 02, 2018

Mainly explains how to operate with matrices and vectors. Not how to use those in machine learning. If you expect to have a clear view of the usefulness of eigenvectors and eigenvalues in machine learning, this is not your course.

교육 기관: Arno D

Dec 19, 2018

Some concepts were not clearly explained and there were a lot of issues with assignment grading working properly.

교육 기관: PRAKHAR K

Mar 11, 2018

Not good, concepts not explained clearly.

교육 기관: Richard C

Oct 16, 2018

Does not explain mathematics in videos


Jul 31, 2020

Why can't I give this course ZERO stars? Because that is what this course deserves.

The first course in the specialization was a train wreck. For starters, the videos were heavy on theory and light on examples, so when it came time to do the practice exams, each student needed to go to outside sources to learn, from the top, what they needed to do to complete the questions. This expectation is unacceptable. Secondly, no mention in the course information, videos, etc. was there any indication that there was coding. These coding assignments are delivered with no hint given as to what we would need to do, how, and why, which is entirely unacceptable. Lastly, the course creators are available nowhere. There are hundreds of questions on the forums for each week of each course, with not one answer coming from any of the course creators. I even went out of my way to find the email for the leading course creator and ask for additional resources/help but received zero response in return. I have been an avid supporter of Coursera for a long while now, but this specialization is terrible enough that I would consider never utilizing this site again. Mathematics for Machine Learning is an embarrassment to the entire service and devalues all of the work individuals have put into learning through this platform. It does this by diminishing the quality of the certificate by demeaning the level of competence acquired upon completion. If I were in charge of content, I would remove this specialization as well as thoroughly review all content published by the same institution. David Dye and the Imperial College of Londen should be ashamed.v

교육 기관: Dmitry R

Jan 13, 2019

Authors try to teach babies. Might be good, it is hard to judge for me as I know linear algebra. Definitely boring to me. For example 3Blue1Brown (which they reference btw) is ingenious in my opinion, so it might be not me who is the problem.

But the quizzes just don't make sense! The ones where solving problems involved might have 2 numerically right answers but only one of two is treated as the right. And there are just idiotic or not covered in lectures answers for quizzes without problems.

교육 기관: Patrick B J

Jul 25, 2018

Hands down the worst course I've ever taken in my life! Poorly put together and extremely short videos that don't provide an adequate amount of knowledge especially in relationship to the given quizzes. I truly hope this course is removed.

교육 기관: sitsawek s

Sep 14, 2018

Quite difficult for learner who didn't know about linear algebra.It jump and few example and skip a lot of part for understand.But good for recall.

교육 기관: Parichit S

Aug 25, 2020

It's an amazing course but apart from the feedback that I have in the post-course survey - I would also like to share the following things.

1) In the quiz on 'Eigenvalues and eigenvectors' in the Week-5 module -- I personally faced a lot of problems in completing the quiz. I understand the concepts pretty well from the lectures but still, I could not figure out the questions in this particular quiz. Particularly the questions about finding the effect of using a particular Link matrix on the eigenvectors. These questions were not easy to answer as intuitively speaking I did not learn how to interpret the meaning of different values in the eigenvectors matrix to answer those questions forex. it makes the eigenvalues small or It makes the eigenvalues we are looking for larger.

Overall - it is a really useful and much-required course to fill in the gap between the mathematical fundamentals and the practice of machine learning. I am glad that the Professors came up with this idea to design this course.

교육 기관: Bram D

Apr 29, 2020

In reviewing this course it is important to state what this course is and what it is not. It is not an in-depth formal introduction to the mathematics of linear algebra. For those who are looking for that, the course simply does not deliver. Secondly, while it is technically possible to complete this course without any beforehand knowledge of the topic, I think this would be incredibly challenging to do. Indeed, the course is not intended to be a first primer in linear algebra. The ease with which the instructors just juggle the cosine rule, or calculate the inverse of a 2 by 2 matrix indicates that they do assume you know such things. So also absolute beginners will be disappointed with this course. However, if you have had linear algebra in your past, and you are using this course to refresh your mind, it is absolutely brilliant. I can confidently say that nobody has ever presented this material to me in as intuitive a way. A well deserved five stars from me.

교육 기관: John T S

May 07, 2020

Above all I found this course well oriented toward becoming useful. The conscious avoidance of heavy mathematical description was a good choice for the online medium. As a learner, I suppose I might have learned better with a bit more... testing, I suppose is the word? To work through a few more examples? But actually, a few well-chose gulfs between the presented materials and (especially the last) testing materials brought some useful questions and explanations. The eigenvector materials are conceptually slippery. Maybe one more example to work through, with clumsier numbers? Although, maybe that would have been boring and confusing...

Which is why I'd give the course five stars. It makes complex material usefully simple, while acknowledging that some things are of necessity left out.

교육 기관: Ritobrata G

Jul 12, 2020

As a student with Physics background, I though that this course will be a quick recap for me. But was I in for a surprise! This course completely changed how I see matrices and vectors. The instruction videos were very edifying. The teachers were great. I am fervently thankful to Imperial College, London and Coursera for such a great course.

There could be some improvements- the assignments felt ambiguous at times. They were not clearly worded and what was expected was not clear. And there could be some very practical excercises in ML where the concepts I learned could be directly applied.

A special note- the instructors were great. Their method was well thought, cordial and the videos were very informative.