Chevron Left
Back to Mathematics for Machine Learning: PCA

Learner Reviews & Feedback for Mathematics for Machine Learning: PCA by Imperial College London

4.0
stars
3,045 ratings

About the Course

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....

Top reviews

WS

Jul 6, 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.

JS

Jul 16, 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.

Filter by:

101 - 125 of 758 Reviews for Mathematics for Machine Learning: PCA

By Shawn H

•

Jun 18, 2023

The worst course among the three.

By Andrei

•

Nov 1, 2018

terrible assignments

By ABHI G

•

Aug 21, 2018

not so good

:(

By Pradeep K

•

Apr 30, 2020

Very Poor course on PCA, My recommendation. Don't watch it, Please don't waste your money on it.

Reasons:

1) The course on algebra and calculus was intuitive geometrically and well taught. Here the instructor bothered only doing derivations. No intuition based thinking, no analogy to real world. Just plain hard notations.

2) I don't think even the instructor would understand what was taught in the course. The excercises were completely unrelated to what was taught. Not much given examples. The examples choosen uses values like 0,1,2. Why can't you pick some odd numbers to make it bit more non confusion and clear.

3) At the end there was a review / Survey for every course. The review for this course is disabled. Clearly everyone knows how bad this is. Remove this course or make it better that is what the recommendation. There is no provision for zero stars, Had there one I would not given that also.

Really frustrated with the PCA course. Please don't waste your time and money . Get Gilbert Strang's book. That will do justice for every penny. I was able to complete the course, All thanks to Gilbert's book on Linear Algebra. Thanks

By Ivan F G

•

Jul 1, 2020

The technical issues with Jupyter Notebooks really made me waste too many days, a lot of my time not learning but just fighting a poorly implemented exercise. And the technical issues did not help the teacher, the notebooks had a role to give us a place to learn new concepts that he mentioned in the fly, but there were no small sets of data to test the functions. I wasn't very patient with the way he will say things like "this is the formula from the previous video", and show a different formula from what he had on the previous video. Really? Why making things obscure on purpose? You can just have said, we had our previous formula and them used properties of the transpose of a product to get this other formula. Please make an effort to redo the notebooks. Even better, do some of the examples in Phyton during class for what you do in paper, and then let us take those examples and make a general function on the notebooks. Give smaller databases, something easy to plot and test, without waiting 20+minutes to have a result.

By Anurag G

•

Sep 13, 2020

I started this course with lots of enthusiasm since the previous two courses were exceptionally well structured and helpful, but I can not compare this course with those two.

The biggest problem for me was that Programming assignments are not well written and most of the time beyond the course material shared. It challenges your previous skills and may hit your self-confidence.

There are also few mistakes or/and skipped steps in the video, and they make progress little tricky.

My classmates were very helpful, and I would suggest relying more on the forums than video lectures when you need help. I would not recommend this course at all to anyone, but if you have done the first two, may complete the last one to complete the specialization.

Also, the first two courses are a few of the best certificates that I did on Machine Learning, and I have done six other mathematics for machine learning, currently enrolled for a degree course in Data Science.

All the best!

By Diego M E

•

Apr 2, 2021

This course by no means retains the quality of its two predecessors. The difficulty of the programming assignments simply does not match that of what you watch in the videos and have to face in the practice quizzes. You need to have at the very least an intermediate understanding of both python and numpy. It should be stated somewhere that, if you really want to try and complete the assignments with a passing grade you'd need to invest **a lot** of your time. The course does not even remotely give you the tools necessary to complete these assignments; you'll need to research on your own and consult forums, videos, manuals, etc. My advice would be to learn python to an intermediate level first, then really practice with numpy, and just after that take this course. Otherwise you'll probably get very frustrated and quit.

By Alistair K

•

May 16, 2020

The instructor is extremely dry and monosyllabic and does a very poor job of explaining topics, he frequently introduces topics by jumping straight into formulas without bothering to explain the topic or the use of the subject he is supposed to be explaining.

The majority of lectures are no more that the lecturer reading our a formula parrot-fashion onto the screen, he makes no effort to make the subject informative or explain what is going on. In many cases, he doesn't even bother creating a lecture, he simply posts a link to Wikipedia.

Lectures, quizzes and assignments are littered with bugs and omissions.

A negative mark on an otherwise excellent specialisation. This lecturer has no place teaching, he made the whole subject unapproachable.

By Nuria C

•

Nov 3, 2020

I did the other two courses of the specialization, which I found great. They clearly explain concepts and give examples. In this course, the professor basically writes down definitions as you can find in any maths book, with no explanation and barely no examples. So, I found myself lost on the quiz and programming assignments. I am quitting the course even if I paid for it, since I feel is it not being a good use of my time. It is true that it is indicated as intermediate level, while the other two courses were for beginners, so I guess I am just in a course which is not for my level. I just don't know then why they included all three in the same package? :/

By Aniket D B

•

Oct 2, 2020

Do not take this course. This course is just a waste of time, money, and effort. The instructions in this course are vague and useless. You have to learn everything from the internet in order to answer the quiz. The programming assignments are so poorly designed that there is no difference between a blank notebook and programming assignments in this course. The grader will grade everything wrong even when your code is correct. You have to do extra maneuvers in order to get your assignment graded correctly. IF I HAD AN OPTION OF GIVING A NEGATIVE RATING I WOULD HAVE GIVEN THIS COURSE A MAXIMUM NEGATIVE RATING. EVEN 1 STAR RATING IS TOO MUCH FOR THIS COURSE.

By Pavel S

•

Dec 12, 2019

The course has two problems:

complete lack of participation of staff in maintaining it. This leads to students giving each other incorrect advice and sharing incorrect code which passes the grader function check ( the grades are assigned automatically). The advice students give each other are frankly so wrong it is shocking.

the teacher focuses on formalised proof rather than concepts. Hence the lectures turn into lecturer applying mathematical transfomations which end in a formal argument without any intuitive understanding of the underlying subject. This course is the worst of the module with linear algebra and multivariate calculus being much better

By Ryhor G

•

Sep 25, 2023

Course is unfinished from technical perspective: -lab files should be manually re-uploaded in order to be properly graded -some quiz questions go before material is covered -Symmetric, positive definite matrices code block is unrunnable, due to using undefined function -Question in one quiz explicitly tells to copy-paste code block result, but copying is disabled there Non-technical issues: -There are a lot of quizzes where you have to do a lot of identical matrices multiplications just with different numbers -Course is deprived of real-live examples, no application of PCA

By Indira P

•

Mar 26, 2021

I'm sorry but it is hard to understand. My expectation before starting this course is I'll be able to understand mathematic in an easier and better way but this is too complex to understand. I think you need to simplify this or make the course in a more fun way. Other than that, the course give me so much knowledge and it was so fun to learn all of these even though it require most of my time

By Raghav G

•

Jul 13, 2020

The course is very monotonic and boring and it is quite difficult to understand much of what the extremely mathematical terms that the instructor does. I am an M.Sc. Mathematics student and even I could not understand nor enjoy more than half of the course. I would strongly advise against taking this course, however the other two courses from this specialization are good and interesting.

By Deleted A

•

Jul 31, 2019

Feedback for the assignments sucks! The discussion forums don't help. I have to submit the last assignment last 6 times until it work, and I still don't know why my previous versions didn't pass. Other than that, the lectures are actually very good, but the only one worth the time is the fourth one, the other three are just the first course (Linear Algebra) all over again.

By Galina F

•

Jan 8, 2020

Mathematical concepts are clear, but no explanation how to apply them to python to solve machine learning ussies. But you need this for python assignments.

Scripts checking assignments work uncorrectly such a way that one can submit the same piece of working(!) code and get 0/10 and then submit the same code and get 10/10.

All in all, it's very annoying and disappointing.

By Cy L

•

Jun 9, 2018

The course is mathematics for Machine Learning. Yet, they require that you are proficient in python. I understand the mathematics. However, no one will answer my questions on the python we are suppose to code. I passed both of the previous courses. I've taken and passed Statistics with python on edX. I've very disappointed in this course.

By Shubhayu D

•

Jun 13, 2020

The first two courses in the specialization were extremely good. However, this course is nowhere close to them. Neither does the instructor provide enough intuition, nor do the assignments help in the learning process.

By Abhishek S

•

Jun 7, 2020

The first two courses of this specialisation were awesome PCA being a hard topic is difficult to understand but the course was boring and not good compared to previous two.

By Nathaniel F

•

Mar 14, 2021

I think there are broken graded assessment in week 4 'test_normalization'

By Olivia S

•

Feb 26, 2024

TEchnical difficulty and no help at all from anyone

By Gita A S

•

Mar 12, 2021

So many bugs on the programming assignment!

By Anton K

•

Nov 14, 2020

By far, this is the best out of 3 courses in this specialization. It is hard though and in the weeks 3 and 4 I had to pause and rewind almost every 10 seconds of the videos and search some error in code labs on the web. But in the end this course showed me in great detail the process of PCA and I also learned a bit of linear algebra alongside it. Considering problems with this course, there were some points that got me a little bit dissapointed. I still don't get it why are we using the biased version of variance, sometimes the notation changed a little bit, (which is not a big problem but introduces some inconvience if the material is completely new to the learner), some of the math concepts were not covered in the "linear algebra" course. But the worst problem was a technical one: some parts of the labs that are not necessary for grading but are very important for learning were throwing errors. I hope that in the future versions they will be resolved.

By Marco v Z

•

Jul 19, 2020

I was somewhat put off by critical comments about the third course in this series, but have to disagree with the reviewers. Yes, it is tougher and, yes, the instructor doesn't have the "schwung" of the other two instructors, but that doesn't affect the quality of this course. His walkthrough of the derivation of PCA is thorough and systematic, and builds on material that has been presented in the earlier lectures.

In fact, looking back on the entire specialisation, I would retrospectively grade the first two courses a notch lower (even if they're excellent), simply because they "sailed through" a bit too easily. The exercises in those courses required little thinking apart from recalling what was said in the lectures. In this course, exercises tended to go beyond or ahead of the material presented in the lectures. Solving them required active thinking, reading, and problem solving, which in the end brings a more thorough understanding.

By Nikos B

•

Jan 18, 2023

One of the best applied mathematics I have attended. This course provides a graduate-level outstanding analysis of linear algebraic data analysis using the next approach:

- Statistical Learning of Datasets

- Linear Algebra of Transformations: Orthogonal Projections, Inner Products in Finite Dimensions

- Analysis of Covariance Matrix

- PCA Algorithm via a constrained minimization problem.

There are also studied some applications:

1. Numpy Programming

2. KNN algorithm

3. Classification, Logistic Regression

4. Encoding and Decoding Information

The course and whole specialisation is suitable for people who have a solid mathematical background because some of theories are provided in a review, given that other mathematics courses have been studied. The main goal is to formulate the PCA algorithm and related topics. This is a master of Linear Algebra in Data Processing.

Thank you Imperial College!