Вернуться к Mathematics for Machine Learning: Linear Algebra

4.7

звезд

Оценки: 8,847

•

Рецензии: 1,788

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....

PL

25 авг. 2018 г.

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.

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:

автор: Navya V

•18 июля 2020 г.

good

автор: Amit V

•8 сент. 2020 г.

1.) This is definitely not a course for beginners, especially if one does not know how to code OR if he/ she is weak in coding.

2.) As far as lectures are concerned, the faculty members/ lecturers are energetic. While some topics have been explained really well, many topics are either left without much explanation. There are some occasional mistakes on the part of faculty, which must've been edited and rectified. They have done good job in converting the lectures in to text. However, there were some mistakes in those texts too.

3.) There is no support in discussion forums from the lecturers of this course. I have seen many questions remain unanswered for many months. This is a very big drawback.

4.) There is a huge gap between what is being taught in videos and what is being asked in assignments. We can understand this by the following corollary: In the video tutorial one teacher is showing that 1 + 2 = 3. In the assignment, students are being asked to find the roots of a quadratic equation.

5.) Some questions and even their answers too technical to be understood by many students. The attempt to explain after the completion of assignment is also too technical. There should be an attempt to dive deeper to help weaker students. If time is the constraint, then make another basic course and let that be a prerequisite of this course. But please, do not mention in the introduction of this course that there is no prerequisite.

автор: Fuad E

•22 мая 2019 г.

It is a little messy: there are no clear definitions of Vector Space, Normed Vector Space, Euclidean Vector Space. Functions as COS and SIN are used to show basic concepts, orthogonal base, and so on. "Projection" concept always relies on base being orthogonal, projection being under 90 degree (what is 90 degree in vector space?), and space being Euclidean, although it is much simpler and applicable for just Vector Space (space without "norm" defined). Good introductory course for high-school; bad for University. Good for kids who just finished learning Pythagoras Theorem, SIN, COS, and basis of Euclidean geometry. Example of house (with number of rooms which is positive Integer number, and price which is positive Decimal) is not really a vector. Examples of non-Euclidean spaces and their applications in machine learning not provided (geometrical deep learning on graphs for example). Basic course for those completely unfamiliar with what "vector" is. Provided tests in Python are confusing because in the context we write vectors (and "base" vectors which matrix consists from) vertically, and in Python - horizontally. For example, [[1,2],[3,4]] is matrix, but it won't transform base vector [1,0] into [1,2]. This is confusing and should be mentioned before test begins.

Thank you for helping me to recall this knowledge. I finished three weeks; I may need to update review later.

автор: Mirian A

•23 июля 2020 г.

Course: Definitely target for people that have solid understand of linear Algebra

Professor:

Pluses: Nice and clear voice, nice demeanor, good energy

Minuses: Long and sometimes messy samples presented on the board, not following through with the samples given (changing subjects causing confusion)

Area of improvement: It would make more interesting if would make connection with real life situation where we could make use of the classes. The instruction video made the class appealing because started with an example of a real life situation that could be resolved. It would be wonderful if full course would bring same excitement.

Exercises/Tests:

Pluses: Unfortunately there was no plus on the exercises. I hate to say that was all pretty bad.

Minus: They were confusing. A lot of time did not make connection with what was taught.

Area of improvement : Give explanation of the answers on the test itself and not referring back to the class. Resolving one to one exercise help making sense of the course being studied.

Course overall was not good. I am very glad I did not pay for this class. However I do think if the professor changes a few things he can nail this class same way he nailed the intro.

автор: eklektek

•25 июля 2020 г.

The course seemed rather lazy using classical presentation methods not going the extra mile and benefitting from more model methods of visualisation and interaction. Instead the student has to hear a lot of words and try decipher the language and sketches of the speaker. I'm a native english speaker and I had problems. Complex subjects need a language that everybody can understand - visualisation.

There was finally some interactive visuals, in the fifth and final week, but these seemed more of an after thought. Also they were not integrated into the course. They would have yielded greater benefit if the lecturer used them too and pointed out specific points. Instead this information came from a few lines of explanatory text.

Generally the course material seemed like the minimum they could get away with, almost as if coursera charges hosting space.

In conclusion, the course has been beneficial, but it could have been so much more beneficial. So next I will look for a course more tightly coupled to my learning style and requirements. If this search fails I may return.

автор: Matthew L

•8 апр. 2020 г.

I am new to Coursera so I have no idea of what is standard on here. Maybe this course is good relative to other courses on here, I don't know. However I do know that based on my experience I can not recommend paying for a coursera membership to take this course. This course comes with a total of less than 3.5hrs of instructional video. Considering linear algebra is usually taught with ~45 hrs of classroom instruction, this may seem short.. and it is. The course does a good job at explaining things at a conceptual level however it has few worked through example problems. The course uses quizzes and programming assignments as a way of reinforcing skills that you learn however the correct answers to the questions on quizzes are never reviewed. So if you get something wrong you'll never know what you did wrong unless you figure it out for yourself. Also the forums don't seem to be useful at all. If you are lucky another student might reply.

автор: Hendrik V

•23 июля 2020 г.

The time commitment is not realistic unless you are a math wiz and experienced programmer. Take the timelines and multiply it by at least 5. Videos do an excellent job of presenting theory and application, but there is no supplemental learning material. You can have to find all of that on your own. In general the other students in the course are lost and have no idea what is going on. I recommend that you watch the videos and follow up the subject on something like Khan Academy where you can work through multiple examples. As for the coding part you need to find someone that knows how to code math in python. Would not recommend.

автор: Jennifer L

•5 июля 2020 г.

This course was pure torture. Lessons were great and interesting but then you are testied on something entirely different! You would be wise to have some knowledge of Python before starting. Be prepared to spend days trying to pass assessments that were never explained. Oh, and there's no supporting materials to help you navigate! Just thousands of pleas from other students begging for help and guidance. Took me three months to finally complete. I would have dropped by I needed it as a pre-requisite.

автор: Oliverio J S J

•16 апр. 2020 г.

I don't think this is a good course. The explanatory videos are not bad and they are easily understood, but they seem to be a series of unrelated concepts, you wouldn't know why those concepts are explained and where the lecturers want to go. There were tasks that had a much higher level of complexity than the videos and other tasks that were trivial. As if that weren't enough, I had repeated problems due to text format in the questions, since it was difficult to distinguish the vectors and matrices.

автор: Graham A

•15 мая 2019 г.

Very challenging to follow instruction at times. Needs to update videos so a bit longer in order to effectively teach the content. Errors with calculations in week 3 with the Composition or combination of matrix transformations video. I've also had to utilize external resources to adequately understand what is being taught. I've taken other courses through Coursera and not had this level of frustration with the other courses.

автор: Oliver W

•14 янв. 2021 г.

Not a fan of this course unfortunately. They jump straight into examples before going through the formula and whatnot prior. For the most part this is fine as it is all fairly straight forward, but a few times the lectures where hard to follow.

Most annoyingly were the programming assignments. Not explained at all in lectures, and for someone with Jo programming experience it was really frustrating to get my head around

автор: Vinicius M

•21 окт. 2020 г.

This course isn't for someone who is going with no knowledge of algebra, the examples are superficial and on the quiz they ask for what they didn't teach. I recommend to learn algebra before hand, I took more time to learn in other platforms what they were trying to teach over here learning with them. So go buy an algebra course and then come back here, you will be able to take more advantage of this course.

автор: Tony J

•21 июля 2020 г.

Useful insomuch as it highlights the aspects of linear algebra that are key for machine learning. The lectures and exercises help you get the basics, but if you have any questions, don't expect any help from the forum. I would strongly recommend following MIT 18.06 alongside this course to gain a more solid foundation and because the lectures in 18.06 are genuinely enjoyable.

автор: Saman A

•31 янв. 2020 г.

Too many important elements are skipped in the videos. Either the videos should present the material needed for the quizzes or they should pause and link out to other resources that explain things in useful detail.

The instructors' enthusiasm, while very inspiring, does not compenstate for the fact that material relevant to the quizzes is either glossed over or missing.

автор: Benjamin F

•22 окт. 2019 г.

Great instructions. Instructors appear knowledgeable and eager to convey the subject.

Programming exercises are however of very poor quality. Even correct answers are not accepted by the automatic grading system due to its brittle design. Fledgling python programmers run the risk of picking up bad coding habits due to poor code style.

автор: Mayank C

•16 мая 2020 г.

I think that the course is fast-paced and skips building conceptual knowledge. It is understandable that the online course may not be as interactive as classroom programs, in which case, instructors should give some reference to reading material or exercise books to come up to pace with the speed they are flying with in this course

автор: HEMNATH R

•15 мая 2020 г.

please don't keep the programming quiz ,its irrelevant for what we are learning, because many may not have programming knowledge but they may be strong in maths this will restrict them from appearing .

but overall the video classed are awesome.thank you so much for giving us this opportunity.once again thanks a lot.

автор: Nicholas E

•11 июня 2020 г.

Not enough explanation. You learn how to do problems but you dont really understand it on a deeper level. I was able to pass the course but I dont think I learned much passed the examples given. Also, I think for the practice quizzes it would be beneficial to show how to get the correct answers.

автор: Dave D

•20 апр. 2020 г.

Quizes and practice material were either overly repetitive or were not supported by the materials. If the course is based on exercises, then a bit of time should be spent on review of the solutions and methodologies for solving. The forum is fairly disorganized so did not solve this purpose.

автор: Tama H

•18 июля 2020 г.

1) There are not enough examples on some subjects 2) The instructors explained the theories and intuitive behind it very well, but the exercises are sometimes too difficult 3) Coding exercises are very challenging and I'm not sure what good it could bring to my data science journey

автор: Hayden R

•3 сент. 2020 г.

This course does a poor job of teaching Linear Algebra, it skims through the topics and gives pretty difficult coding work with poor instruction. This course should only serve as a refresher, do not expect to learn much past the first 3 weeks.

автор: Venkata S M B

•12 сент. 2020 г.

Not a great course. It started alright but really it lost track after two weeks. No references were made to the actual ML applications. This was more like a pointless Matrix knowledge.

автор: Gurrapu N

•5 апр. 2020 г.

There is hardly any relation between videos and assignments. There should be a way to let the students know the right answers after completing the course to rectify the mistakes.

автор: Shrinath I

•12 апр. 2020 г.

It was a decent course, but the teachers weren't particularly good. I had to often rely on other resources to figure out what was going on. That kind of ruined it for me.

автор: Muhammad Z A

•9 июня 2020 г.

Not a Good Course for Biggner's. Instructor do not have ability to simply topics taught in this course. They were just copy pasting its materiel from other slides.

- Поиск цели и смысла жизни
- Понимание медицинских исследований
- Японский язык для начинающих
- Введение в облачные вычисления
- Основы самоосознанности
- Основы финансов
- Машинное обучение
- Машинное обучение с использованием Sas Viya
- Наука благополучия
- COVID-19: отслеживание контактов
- Искусственный интеллект для каждого
- Финансовые рынки
- Введение в психологию
- Начало работы с AWS
- Международный маркетинг
- C++
- Прогнозная аналитика и интеллектуальный анализ данных
- Получение навыков обучения от Калифорнийского университета в Сан-Диего
- Программирование для всех от Мичиганского университета
- Программирование на языке R от Университета Джонса Хопкинса
- Курс CPI для CBRS от Google

- Обработка естественного языка (NLP)
- Искусственный интеллект в медицине
- Мастер слова: письмо и редактирование
- Моделирование инфекционных заболеваний
- Американское произношение английского языка
- Автоматизация тестирования программного обеспечения
- Глубокое обучение
- Python для всех
- Наука о данных
- Основы бизнеса
- Навыки Excel для бизнеса
- Наука о данных с Python
- Финансы для каждого
- Навыки общения для инженеров
- Курс по продажам
- Управление карьерным ростом
- Бизнес-аналитика от Уортонской школы бизнеса
- Позитивная психология от Университета Пенсильвании
- Машинное обучение от Вашингтонского университета
- Графический дизайн от Калифорнийского института искусств

- Профессиональные сертификаты
- Сертификаты MasterTrack
- ИТ-поддержка Google
- Наука о данных IBM
- Инженерия данных от Google Cloud
- Прикладной искусственный интеллект от IBM
- Облачная архитектура от Google Cloud
- Аналитик по кибербезопасности от IBM
- ИТ-автоматизация с помощью Python от Google
- Специалист по работе с мейнфреймами на IBM z/OS
- Прикладное управление проектами от Калифорнийского университета в Ирвайне
- Сертификат по педагогическому дизайну
- Сертификат по проектированию и управлению в строительстве
- Сертификат по большим данным
- Сертификат по машинному обучению для аналитики
- Сертификат по управлению инновациями и предпринимательству
- Сертификат по экологии и устойчивому развитию
- Сертификат по социальной работе
- Сертификат по искусственному интеллекту и машинному обучению
- Сертификат по пространственному анализу данных и визуализации

- Степени в области компьютерных наук
- Степени в области бизнеса
- Степени в области общественного здравоохранения
- Степени в области науки о данных
- Степени бакалавра
- Бакалавриат в области компьютерных наук
- Магистр в области электротехнического проектирования
- Степень бакалавра
- Магистр в области управления
- Магистр компьютерных наук
- Магистр общественного здравоохранения
- Степень магистра в области бухгалтерского учета
- Магистр компьютерных и информационных технологий
- Диплом магистра делового администрирования онлайн
- Магистр прикладной науки о данных
- Международная программа MBA
- Магистр в области инноваций и предпринимательской деятельности
- Магистр компьютерных наук в области науки о данных
- Магистр в области компьютерных наук
- Магистр здравоохранения