Chevron Left
Volver a Mathematics for Machine Learning: PCA

Opiniones y comentarios de aprendices correspondientes a Mathematics for Machine Learning: PCA por parte de Imperial College London

2,942 calificaciones

Acerca del Curso

This intermediate-level course introduces the mathematical foundations to derive Principal Component Analysis (PCA), a fundamental dimensionality reduction technique. We'll cover some basic statistics of data sets, such as mean values and variances, we'll compute distances and angles between vectors using inner products and derive orthogonal projections of data onto lower-dimensional subspaces. Using all these tools, we'll then derive PCA as a method that minimizes the average squared reconstruction error between data points and their reconstruction. At the end of this course, you'll be familiar with important mathematical concepts and you can implement PCA all by yourself. If you’re struggling, you'll find a set of jupyter notebooks that will allow you to explore properties of the techniques and walk you through what you need to do to get on track. If you are already an expert, this course may refresh some of your knowledge. The lectures, examples and exercises require: 1. Some ability of abstract thinking 2. Good background in linear algebra (e.g., matrix and vector algebra, linear independence, basis) 3. Basic background in multivariate calculus (e.g., partial derivatives, basic optimization) 4. Basic knowledge in python programming and numpy Disclaimer: This course is substantially more abstract and requires more programming than the other two courses of the specialization. However, this type of abstract thinking, algebraic manipulation and programming is necessary if you want to understand and develop machine learning algorithms....

Principales reseñas


6 de jul. de 2021

Now i feel confident about pursuing machine learning courses in the future as I have learned most of the mathematics which will be helpful in building the base for machine learning, data science.


16 de jul. de 2018

This is one hell of an inspiring course that demystified the difficult concepts and math behind PCA. Excellent instructors in imparting the these knowledge with easy-to-understand illustrations.

Filtrar por:

676 - 700 de 731 revisiones para Mathematics for Machine Learning: PCA

por 周玮晨

8 de jun. de 2018

This course is far far far behind my expectations.The other two course in the specializition is fantastic. There is no visualization in this course, Instructor is always doing his algebra, concepts are poorly explained. I can't understand a lot of concepts in this course because of my poor math background.But why do i take ths course if i have a solid background in math? Programming assignments is not difficult but hard to complete because of vaguely clarification.Plenty of time wasted to find what should i do, its' really frustrating.

por Hannah Q

26 de abr. de 2021

This is the worst course among 3 courses in this math for machine learning specialization, but this is also the most important one as it comprises the other 2 courses. the homework is not well designed, the lecture is not taught enough to finish the homework. the last coding assignment has so many errors. and TA is never available, there are just a group of people tried really hard to help each other in the discussion forum, and please read the discussion forum every one is confused and suffering from your this bad course.

por Adarsh R K S

21 de feb. de 2021

The first two courses in the entire specialization were good. The PCA course was then suddenly so complicated and assumed significant matrix knowledge which was not taught in the previous courses. also, the course kept introducing concepts into the material without any explanation of where this came from and the why behind it. the lecturer needs to understand that most people taking this course are not mathematicians by profession and so we would have learnt better if the PCA was kept at a basic level.

por Srudeep K

6 de abr. de 2021

Alot of the material are to be referred, read and understood from sources outside of the course which is frustrating. There is lack of continuation from first two courses (Linear algebra & Multivariate calculus). At times, lecturer explains concepts without giving any background. Tests front run the course, meaning some questions you get in tests are taught in the video just after the test. I find better resources elsewhere online to understand PCA much better than wasting few days on this course.

por Paul K

2 de feb. de 2023

very unclear. previous courses where very good but this one is just bad.

absolutely no explanation on the notation, confusing examples where the same vectors end up having a different length between them and no explanation why. this lecturer is probably good in his field but cant teach.

finished it to get the total certificate but cant say a understood any of it. a real shame since the first 2 courses of mathematics for machine learning are super but this PCA Course is just an useless

por Hossameldein E

9 de abr. de 2021

The other Two courses are great, really great. But this one is a disaster.

Most of the the first 3 weeks i google the theory again to understand the problems in the quizzes.

The 4th week feels like something from a different course.

This videos are dull . a lot of time just reading the equations without trying to know what is it about in the real life.

please reconsider re-constructing this course. it's really sad that after the two great courses it ends up with this.

por Rameses

18 de ago. de 2020

This has to be one of most nightmarish, ugly, courses I have taken on the Coursera platform. Lousy, boring instructor, assignments that are so full of bugs that even the staff cannot resolve the issues. Add to that very low participation from the mentors and teaching staff in responding to student concerns and questions.

Hey Marc, teaching staff and Imperial College. Get your act together!!

IOW This course sucks big time! Take it at your own risk

por Jose V

5 de dic. de 2022

First assignment of first week not well explained at all and was extremely difficult to pass if you are not already an expert python programmer. Too much confusion from students in the forums and 0 response/support from instructors. Being the 3rd course of the specialization, I had to give up. Do not enrol in the specialization at all if you do not have access to professional python programmers.

por Chen F

27 de oct. de 2021

very few clue for the assignment. same formulars not taught in the class, not founded from materials. actually it's wasting time to pay for the material ignorance.


find a formular for two hours...

I should try another course.....

por Kristina S

24 de ago. de 2018

One of the worst online courses I have had. Inconsistent teaching, relaying on students having previous knowledge about Python and rads (where the heck did that come from?), failing to convey what and where this is practically used for.

por Oliver K

21 de feb. de 2020

PCA was my main interest in this specialization, and it felt very rushed and lazy (i.e. important explanations are fully missing, or just done via pdf from a book). I used *a lot* of Khan Academy to understand what's going on.

por kumar s

11 de ago. de 2020

I would give ONE STAR because the instructor of this course was worst. He don't know the teaching and concepts too. He seems to be so low energetic instructor I have ever seen. A very bad experience after taking this course.

por Deleted A

31 de ene. de 2020

I don't know if this course has been deliberately made hard to understand or I was lacking something. Lectures were pretty useless to me. Coding exercises were not clearly defined. I felt utterly frustrated at times.

por Ashlee H

26 de nov. de 2019

You'll likely catch on pretty early that this course will mostly expects you to learn the content elsewhere. You're paying for mostly just for assignments and quizzes which there are far more of than video lectures.

por Ed W

25 de nov. de 2019

The lectures gave incomplete information for the understanding of the material and the homework assignments. Wish this course was stretched to be a 10 week course so that we can all thoroughly learn the material.

por Christiano d S

10 de ago. de 2020

The lessons are not clear and if one wants to learn and understand what is going on with the math/algebra, has to study with other resources, because the videos of this course just throw up info´s on screen.

por Kimberely C

27 de dic. de 2019

Definitely, not for beginners. Just as bad as the last one. They need to have more examples, which walk you through the ones like they give you on the homework as well as an example of how to do Python.

por Gurrapu N

9 de abr. de 2020

There is hardly any co-relation between videos and assignments, while the lectures were at high school level but the assignments were at graduate level. It is high time to revise the course contents.

por Marcin

19 de ago. de 2018

By far the worst online course that I've ever done. Assignments require a lot of experience in Python, which is not communicated upfront. At the same time, staff doesn't provide any actual support.

por Danielius K

24 de sep. de 2019

You will spend most of your time lost.

Quizes are not clear and ill-prepared.

You will need to spend a lot of time looking for material outside of the course to actually make progress.

por Si L

9 de oct. de 2021

This is the worst course of the specilisation. Content is conveyed poorly. This reminds me of why I always hated math. Not because math is dry or boring but the way is communicated.

por Simon J H

30 de may. de 2021

Nowhere near the standard of the first two Courses in this specialisation.

The videos & practise exercises do not even come close to preparing you for the assignments.

por Vikram G

27 de dic. de 2022

The prgramming assignments dont work at all. This course is not updated. Very poor performance by Imp college London. The coursework is just on the surface level.

por Saransh G

28 de abr. de 2020

1. Not intuitive like first two programs

2. The assignments sometimes jumped concepts and were not cohesive

3. The in-lecture problems seemed rushed through