Chevron Left
Вернуться к Mathematics for Machine Learning: Linear Algebra

Отзывы учащихся о курсе Mathematics for Machine Learning: Linear Algebra от партнера Имперский колледж Лондона

4.7
звезд
Оценки: 8,565
Рецензии: 1,730

О курсе

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....

Лучшие рецензии

EC
9 сент. 2019 г.

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.

CS
31 мар. 2018 г.

Amazing course, great instructors. The amount of working linear algebra knowledge you get from this single course is substantial. It has already helped solidify my learning in other ML and AI courses.

Фильтр по:

126–150 из 1,725 отзывов о курсе Mathematics for Machine Learning: Linear Algebra

автор: Alina I H

18 нояб. 2020 г.

Really good overview and while explained perfectly by the instructors (using different media that would have been amazing to have back in school...) still challenging enough to get the brain cells running. Fun to do, yet one should take time and really concentrate. Thanks for this amazing opportunity! I'm sure this knowledge will really help me along the way.

автор: Sridhanajayan S

31 мая 2020 г.

This is an exceptional course for learning Linear Algebra in an intuitive way. i would recommend this course to everyone who is fond of mathematics. This course will also have programming assignments with python and numpy packages. Overall I had a wonderful experience and a handful of knowledge. Thank you for the course creators and professors and lecturers.

автор: Ollie D

9 июля 2020 г.

For someone having already graduated with a degree in Mathematics, the mathematical concepts centred around this course were easy to understand, but then applying this knowledge in to code was challenging. Which I was expecting it to be given my lack of experience with python and jupyter notes. A worthwhile course for anyone looking in to data science.

автор: David P

10 июля 2018 г.

Great content, lecture videos are brilliant. I would make one suggestion; it would be great to have more examples or even recommend text books that we as learners can download or purchase, this will assist those who wants to learn these techniques in practical examples. Other than that I have learned alot and will continue using coursera, good job guys

автор: Ahmed R

22 апр. 2018 г.

This is a very good introduction and review of Linear Algebra. The particular highlights are the use of geometric perspectives to give intuition rather than just labouring through the mathematics. I also learned where I need to learn more in order. Overall will recommend either as a review or a stepping stone to learning more about Linear Algebra.

автор: Kohinoor G

24 апр. 2018 г.

One of the best Linear Algebra [LA] courses for beginners/novices. It takes away the drudgery of algebra and formulae and tries to explain the "essence" of LA. This is by no means comprehensive LA course - but good enough for people who are fed up with "this is how to calculate the Eigen vector/determinant/<insert pet peeve>" mode of teaching LA.

автор: Kerr F

23 июня 2020 г.

Brilliant course which helped me to re-learn/learn linear algebra methods for machine learning! The course instructor videos, course structure, worked examples and assessments were all extremely useful and allowed me to achieve my learning goals. I would recommend this course to anyone (but would maybe first suggest brushing up on basic python).

автор: Jonathan S Y P

11 апр. 2020 г.

Me parece un curso muy bueno, es básico pero la verdad hay que practicar mucho haciendo ejercicios y no conformarse únicamente con la información de los vídeos, si no, buscar otras fuentes para complementar. Para ser básico fue un desafío porque hay problemas que aparecen en los exámenes que requieren de mucho análisis. Vale la pena; me gustó!

автор: Kisan T

9 мар. 2020 г.

This course has helped me to understand the basics of linear algebra and it's application in computer science. I was aware of mathematical calculations of the linear algebra, but I did not know reason and meaning of those calculations. I am grateful to Imperial College London and Coursera team for giving me opportunity to take this course.

автор: Divyaman S R

31 окт. 2020 г.

Excellent course with the just right amount of detail to expose beginners to the concepts of linear algebra. I look forward to other courses from ICL in coursera in the filed of mathematics, data science and machine learning.

Thanks to this course, I am in love with linear algebra and am continuing further self-study on this subject.

автор: Duc D

22 сент. 2019 г.

Awesome content and very clear lectures. Would be great to have links to more in-depth explanations of certain unexplained assumptions. For instance, it's unclear how the characteristic equation comes about (by assuming that the characteristic matrix does not have an inverse) and also why the page rank matrix is setup the way it is.

автор: 谢仑辰

27 февр. 2019 г.

I really appreciate staff of ICL's effort to bring us such an intuitive and straightforward course. It's totally different from those linear algebra courses I've received in China. From your idea on explaining this course on space and transformation, I started to build a strong foundation about linear algebra, and machine learning.

автор: Gabriel W

23 мая 2020 г.

I did the 3 specialization lessons "Mathematics for Machine Learning" (Linear Algebra, Multivariate Calculus, PCA). I really had a lot of fun and learnings in the first one (5 stars for Linear Algebra): David Dye is an increadible teacher. Thank you for your enthousiastic Knowledge Transmission: Mathematics are very cool with you!

автор: Niju M N

9 апр. 2020 г.

This course lays the groundwork for the Algebra required in ML. The basics are covered really well.There are quizzes and assignments to strengthen the ideas learnt in the course.At times felt the assignments are very easy .It can be used to brush up the basic Algebra or learn from Zero. The instructor explains every thing clearly

автор: Paul K M

9 окт. 2019 г.

This course gives a good overview of linear algebra using python numpy arrays. It doesn't go super deep into the topic, but I wouldn't call it superficial. It requires you to do some basic vector and matrix algebra by hand, build agorithms to do some of those calculations, and introduces some numpy methods for those operations.

автор: Michelle W

3 июля 2018 г.

Excellent course. I have never taken a linear algebra course before, so it took me longer to complete this as I had to learn the basics to follow the material in this course. The course is designed as a review of linear algebra, but if you are motivated and have time, it's possible to complete without having had linear algebra.

автор: Alex H

9 февр. 2020 г.

This is exactly what I wanted from an online course! I took linear algebra at university decades ago, but made the mistake of learning just enough to pass the next test. The lectures in this course laid out and solidified concepts for me which were previously abstract. The presenters were clear, concise and, I daresay, fun!

автор: Benjamin E

24 февр. 2020 г.

This is a good course that allows you to develop a high and low level understanding of linear algebra...unlike a certain university professor I had who made us do 5x5 matrix transformations by hand. I highly recommend doing outside reading alongside the course to expand your knowledge, especially regarding the coding aspects.

автор: Mthandeni M C

14 апр. 2020 г.

Great balance between Mathematical rigor and Computer Science applications. This course is deliberately not easy to ensure you leave with a strong intuition behind the Mathematics of Machine Learning. Python exercises brings this cause alive. It has given me the confidence to continue with my Machine Engineering journey.

автор: Shubham D

9 мая 2018 г.

Amazing course.Do not let the easy content distract you from the fact that this is one of the best/well taught MOOCs on Coursera.These professors are experts at helping student develop an intuition for mathematics.Way different from what was taught in my school/university and also much more useful in a practical sense.

автор: Luka

16 мая 2020 г.

I enjoy attending this course. I consider this course really good, mostly due to a lot of intuitive examples about particular subjects of study, explanations that were clear and enthusiastic professors. Finishing this course gave me motivation to learn more about machine learning and mathematics that it's based upon.

автор: AVADH P

3 окт. 2018 г.

The course and the content is quite fruitful for anyone who wants to go ahead in the area of Machine Learning. The course instructor gives a detailed understanding of each topic and insight of the methods of vector calculus and linear algebra. For building the basic fundamentals of ML, this course is must for anyone.

автор: Christos P

2 июля 2018 г.

It was honestly great. The first two weeks didn't have much new for someone who'd already taken Linear Algebra, but the last three weeks were very informational. It really helped me understand the concepts geometrically/spatially in ways I hadn't seen before when I had taken general linear algebra at my university.