Chevron Left
返回到 Mathematics for Machine Learning: Linear Algebra

學生對 伦敦帝国学院 提供的 Mathematics for Machine Learning: Linear Algebra 的評價和反饋

4,157 個評分
750 個審閱


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....



Sep 10, 2019

Excellent review of Linear Algebra even for those who have taken it at school. Handwriting of the first instructor wasn't always legible, but wasn't too bad. Second instructor's handwriting is better.


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.


701 - Mathematics for Machine Learning: Linear Algebra 的 725 個評論(共 746 個)

創建者 Idriss M

Sep 23, 2019

great intro to linear algebra

創建者 Prasad N R

Sep 30, 2019

I was expecting a lot from the course. But, it covers only the very basic portions. For example, I am not sure if I can start understanding the difficulties with normal equations and portions of linear algebra based on calculus. Also, it does not discuss parallelism of ML with linear algebra. I am not sure if this will help me read and understand Andrew Ng's ML papers.

創建者 shashank s

Sep 29, 2019

The course was good but it could have been better if the exercises had more difficult questions or probably a section with more difficult questions using the concepts that were taught.

創建者 Mohammad O B S

Sep 29, 2019

Instructors have done a really good job at introducing the fundamentals specially from a graphical point of view which allows you to build your grasp strongly around the topics in a way that is not accomplished in a traditional college classroom. However, I would say perhaps there could be more challenging questions on the real world applications of linear algebra in machine learning followed by in-depth step-by-step solutions in order to really get the application-based learning inside your meat.

創建者 Alexander L

Nov 01, 2019

Great instructors, excellent content. I would like to see more practical use cases of the material (at least as a self-study reading). And please add an explanation behind formulas for the eigenvectors part.

創建者 Avery W

Nov 04, 2019

This is a great course, but some of the quizzes are quite difficult. If there were more explanation on the quizzes, this course would be just perfect!

創建者 Marwa A E K M A Z

Oct 18, 2019

I learned and developed intuition of the concepts covered in this course, which I'm happy with.

創建者 Saurabh G

Nov 07, 2019

This is one of the most important courses for someone who wants to build career in the machine learning field.

創建者 Cindy X

Dec 21, 2018

I think this course is a little bit hard for a beginner with python. And I hope that the teacher can talk more about the Machine learning part.

創建者 Nathan C

Jan 26, 2019

Having no background in linear Algebra made it difficult to complete the quizzes, assignments and exams. Even with the instruction (which was good) I found the hands on portions to be different from what was being explained in the videos. I will instead have to take the key concepts and do more research on my own to fully understand them.

創建者 Manuel M

Jan 26, 2019

The course feels very disorganized in general. Some quizzes are about 10 standard deviations from the average difficulty, which is befuddling to say the least.

創建者 Matt

Feb 24, 2019

This course would be perfect if more elaboration on the maths required to complete the quizzes, was provided.

創建者 Carlos R T G R

Mar 19, 2019

The videos need to be updated, there are quite some errors that are already identified...

創建者 Adam R

Nov 16, 2018

Some of the quizzes go beyond what is in the videos and often spent ages on them.

創建者 Fernando B d M

May 14, 2018

Like most of Coursera's courses there are no staff members available in the forums (which is extremely shameful for Coursera - repeating the same boring pattern over the years). Don't even try it if you have never seen linear algebra or python before. Otherwise, it's useful for practicing a few concepts or refreshing others.

創建者 Jared E

May 26, 2018

Overall good, but some nasty difficulty with the programming assignments... especially the last one.

創建者 Nicholas K

Apr 20, 2018

Enough gaps that I finished feeling like I really had no idea what was going on.

創建者 Flávio H P d O

May 12, 2018

explanation not very clear

not enought examples

創建者 Anweshita D

Jun 29, 2018

Your discussion forum really needs to be better. It seems to be the only place where any sort of doubt clearing can be done and very rarely have I seen TA's answering unless it's a grading issue. The problem with this sort of answering is that if any coding concepts are unclear, either they are solved by trial and error or after going through Google multiple times. And for a course that is paid for, I shouldn't have to make this much of an effort just to have my doubts cleared.

創建者 Mattia P

Mar 30, 2018

Nice course, with many insights. Sometimes the topics are given too quickly, I would have rather preferred less arguments but discussed more thoroughly. Nevertheless, I think this is a good one, especially if you've already got some background and you're looking for some general content to build upon it using academic books.

創建者 Alexander D

Aug 07, 2018

Not enough focus on how material connects to machine learning. A case study example would help, as would a very slow, detailed step-by-step illustration.

創建者 Neha K

Oct 09, 2018

The style of teaching is great.

創建者 Vignesh N M

Sep 12, 2018

Transition from explanation of basic to advanced concepts could have been better. There was an assumption that few things was already know to the learner.

創建者 丁榕

Aug 30, 2018

I think the course is more suitable for those who have had comprehensive theoretical knowledge in linear algebra and intend to learn more about its practical use and its relevance to code.

創建者 Reed R

Jul 14, 2018

The stated goal of the course is to provide a sufficient base of knowledge in linear algebra for applied data science i.e. (a) to teach linear algebra without gory proofs or endless grinding through algorithms by hand and (b) to foreground geometric interpretations of linear algebra that can be recalled for many data science techniques and visualized with common data science tools. While I appreciate this goal and enjoyed the early foray into projection, I never felt the "a ha" moments I did as an undergrad in a class that used Gil Strang's "Introduction to Linear Algebra" (which I reread alongside this course as a supplement). The course seems to ask for some faith that various concepts introduced earlier in the course will be united by the end, but never makes good; opting instead for a kind of sleight of hand: having students implement the Page Rank algorithm with the intention that this will draw together the core concepts of the course. It could be that I was just looking for a more complete treatment of the subject than the course ever intends to offer, but I strongly felt that with a bit of restructuring, that the subject could be presented primarily intuitively, but with a level of clarity and artfulness in its conclusion that will ensure that students remember the core concepts beyond when they remember its presentation.