Вернуться к Mathematics for Machine Learning: Linear Algebra

4.7

звезд

Оценки: 6,077

•

Рецензии: 1,162

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....

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.

Apr 01, 2018

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:

автор: Pavel S

•Dec 13, 2019

The biggest problem of this course is that dot-products are introduced before linear transfomations. I understood dot products through 3blue1brown videos and they are more intuitively explained as the product of the lengths of the projection and the vector projected onto. It is a subset of linear transformation a matrix vector multiplication where one of vectors is transposed.

автор: Fang Z

•Jun 11, 2019

The course generally is good. However I think there are some problems in this course: 1. The course pace is too fast, some concepts are hard to understand with few minutes lecture 2. The after-practice didn't help me to boost my understanding to the lecture. Even after I finished the practice, I still wonder why this happens 3. The final quiz has too much calculations.

автор: 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.

автор: Musiboyina Y

•May 27, 2018

The course content was spot-on, covering some of the most important basics for math in machine learning. I wish there were more programming exercise based assignments and less hand-calculation based quizzes to make it close to real world applications. Overall, loved this course and highly recommend it to data science enthusiasts taking baby steps towards deep learning.

автор: Shashank S

•Aug 05, 2018

This course has provided everything that it had promised. The professors of this course are really knowledgeable about the topics and the use of real life examples by them to explain each concept proves really helpful. Overall, this course would be a really good starting point for anyone willing to start their journey in the world of Machine Learning and Data Science.

автор: Julio V

•Sep 27, 2018

I feel like some part should've gone a bit more in depth. Due to time constraints for the course, I guess that's why some topics where not developed further. Would be quite nice in these cases if you could point to other sources, books, etc. Or maybe do a compilation of sources based on what the students have used to get unstuck on particular issues.

автор: Régis M

•Dec 28, 2018

As paletras e numero de exercios foram muito bons. Porem o forum não é muito bom, existe questões abertas a 4 meses que ainda não foram respondidas, e muita repetição de duvidas.

Poderia ter apos os exercicios praticos, um video explicação de como resolver. Porque se a media é 80%, é presumivel que o aluno pode não saber alguma coisa e ainda passar

автор: rakesh c c

•Oct 23, 2018

I loved doing this course. I did this course to revisit the concepts I have learned in my undergraduate, I remember most concepts but there are few moments where I have to watch videos again and again to follow along, anyone who is beginner might find it a bit intimidating, but don't give up just follow along and connect the dots between concepts.

автор: Matteo L

•Apr 20, 2020

I think this is a great review of linear algebra, especially for someone who has already previously studied the topics.

The example with the PageRank algorithm was very interesting and a great add to the course.

Possibly a downside of the course was a lack of practice of the material, especially considering how easy the notebook assignments are.

автор: Yazhini P

•Jan 26, 2020

The course and the faculty were amazing altogether. All my queries regarding linear algebra were cleared and I began to look at linear algebra in a new eye.

The only flaw was inaccessibility to the correct Notebook link. Only after going through the forum was I able to get the correct link as it was, luckily, posted by someone.

автор: Vinayak

•Oct 15, 2018

Good for starters. It gives a holistic view of linear Algebra. Geometric interpretation of Eigen Vectors was the highlight of the course for me as I wasn't aware of it before and the instructor helped me understand the concept very well! Thanks for putting forth this course and hope to see more in the forthcoming sessions :)

автор: Rick M

•Jul 21, 2019

Overall, I thought this course was worth the time. Some of the material was challenging, but the instructors were pretty good at explaining clearly. Just a head's up: there is relatively little reading material here, so if you struggle to learn through videos you might have a hard time. That part was a challenge for me.

автор: Subham K S

•Jan 30, 2020

Great course!! The instructors taught in a great way with proper visualization and real-world applications.

But more examples of implementing in machine learning could have been included and a bit more concepts could have been taught.

Overall great one. Thank you coursera, Imperial college and both instructors.

автор: Beyza A

•May 03, 2020

I have 2 years of experience with coding. I took this course to refresh my knowledge of mathematics before I start using machine learning techniques. This course sometimes gave us the basic knowledge which helped to apply real-world situations. However, I feel like I need more exercises, basic explanations.

автор: Chip B

•May 25, 2019

Filled in a lot of knowledge gaps that I should have learned in high school or undergrad. I feel much more prepared for graduate studies in data science.

4 stars because the last module felt rushed. I felt that I learned more from trial and error on the quiz than from the lecture videos.

автор: Frank G

•Apr 14, 2018

Very good class. Outstanding instructors very clearly teaching key concepts in linear algebra.

I only docked one star for two reasons:

I wish they explained in more depth how the linear algebra topics are used in machine learning.

I wish the class were a little longer and more in-depth.

автор: Sydney F

•Jul 26, 2019

While they explain the basic concepts of linear algebra, sometimes the programming assignments are tricky and some of the quizzes are too complicated to complete with our current knowledge. However, the course is worth taking if you want a solid math background for machine learning.

автор: saurabh p

•Mar 05, 2019

the lectures were very good and on point, obviously referring the prescribed textbooks will further improve one's knowledge about the subject. i really enjoyed the programming part of the assignments, which were made to help students without any prior experience of python language.

автор: Md. M H

•Nov 01, 2018

It would be better if it pointed out the pre-requisites of this course. Besides, the submission process of Jupyter notebook doesn't work directly. These issues need to be solved. Other than these issues, the course itself is pretty informative and the instructors are well prepared.

автор: Nikhil G

•Mar 30, 2018

Great course, offers a nice introductory base you can use to further your knowledge without having to take a full three month course on linear algebra, allows you to dig into some interesting stuff earlier on. Could have used a bit more feedback for quizzes and assignments though.

автор: Kevin E

•Apr 27, 2020

The examples were relevant, and I could follow along with them on my own. The programming assignments helped to complete the understanding of the processes. I would've liked more examples to work through for practice, and to improve understanding. Otherwise, it was great.

автор: DAVID R M

•Jul 10, 2018

The basic geometry explained by the tutor is amazing especially the dot product, determinant, etc. Although the program assignments suffices for its purpose, I would have enjoyed more if it would have been little more challenging. Overall, this course rocks on its purpose.

автор: Syed Z N

•May 21, 2020

The last module seemed a bit hurried. More videos could have been made regarding the topics in the last module. The video on PageRank algorithm should have more illustrative examples for allowing the students to visualize. Apart from that, this was an amazing course!

автор: Wu X

•Mar 12, 2020

The first three weeks' courses are a little too primary for me, while the last two weeks' courses bring some good insights with interesting examples. In a nutshell, this course is qualified as an introduction to the core of linear algebra and deserves a thumb-up!

автор: Jean S

•Aug 20, 2019

Excellent course and very practical; it's really focused on machine learning and there's the opportunity to learn some coding in Python. I would recommend it to everyone interested in machine learning. I give it 4 stars because there's always room to improve.

- Искусственный интеллект для каждого
- Введение в TensorFlow
- Нейронные сети и глубокое обучение
- Алгоритмы, часть 1
- Алгоритмы, часть 2
- Машинное обучение
- Машинное обучение с использованием Python
- Машинное обучение с использованием Sas Viya
- Программирование на языке R
- Введение в программирование на MATLAB
- Анализ данных с Python
- Основы AWS: введение в облачные приложения
- Основы Google Cloud Platform
- Обеспечение надежности веб-сервисов
- Разговорный английский язык на профессиональном уровне
- Наука благополучия
- Научитесь учиться
- Финансовые рынки
- Проверка гипотез в здравоохранении
- Основы повседневного руководства

- Глубокое обучение
- Python для всех
- Наука о данных
- Прикладная наука о данных с Python
- Основы бизнеса
- Разработка архитектуры на платформе Google Cloud
- Инженерия данных на платформе Google Cloud
- От Excel до MySQL
- Продвинутое машинное обучение
- Математика в машинном обучении
- Беспилотные автомобили
- Блокчейн для организаций
- Бизнес-аналитика
- Навыки Excel для бизнеса
- Цифровой маркетинг
- Статистический анализ в здравоохранении на языке R
- Основы иммунологии
- Анатомия
- Управление инновациями и дизайн-мышление
- Основы позитивной психологии

- ИТ-поддержка Google
- Специалист IBM по привлечению клиентов
- Наука о данных IBM
- Прикладное управление проектами
- Профессиональная сертификация IBM в области прикладного ИИ
- Машинное обучение для Analytics
- Пространственный анализ данных и визуализация
- Проектирование и управление в строительстве
- Педагогический дизайн