Вернуться к Mathematics for Machine Learning: Linear Algebra

звезд

Оценки: 9,184

•

Рецензии: 1,859

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.

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.

Фильтр по:

автор: Georg K

•8 сент. 2018 г.

This course is not suited for beginners and people looking for an introductory lecture to Linear Algebra! Unfortunately the topics are extremely hastily presented and lack depth of explanation, sufficient examples and often leave out content required to complete the assignments. The material is not presented in a coherent way, and, for someone new to Linear Algebra like me, requires a great amount of self-study outside the course (e.g. Khan Academy) to comprehend the content. The team of lecturers is very likeable and enthusiastic. However, I do not comprehend where this course seeks to position itself: it is not suited for students new to Linear Algebra, and, not extensive enough for someone seeking to learn underlying mathematics for Machine Learning as this course simply doesn't cover Machine Learning. Finishing this course, I have some vague understanding of certain concepts and I am left longing for proper and structured content that I could feel confident about.

автор: Atul A

•13 мар. 2019 г.

I can't follow what is happening. There is a huge gap between what is being taught and what is being asked in the assignments.

автор: Andrew M

•15 мар. 2019 г.

Disclaimer: If you are familiar with Linear Algebra, you may love this course. This review is not for those people. This review is for the people who went to the course details, saw that the recommended audience was 'Beginner' level, and decided to give it a try, thinking it involved a low barrier of entry. You'd be thinking incorrectly. Here is why.

Let me start off by stating two things. First: I am terrible at all things mathematics, and wanted to improve my capabilities in this area. Second: This is by far the worst Coursera course that I've taken to date. I put all my effort into not only completing the course, but doing so on time, so that I don't dump more money into a course than completely necessary. With this course, I found myself loathing the prospect of torturing myself with the material, that I kept putting it off. I eventually had to come to terms that I hated this whole experience, and canceled my subscription prior to completing even the first course!

1.) The videos are absolutely useless - Up-to-date on all the latest and great math jargon? Well, you'd better be, or else you'll find yourself Googling terms like a madman and re-watching the videos over and over, just to get a grasp on what is going on. All this is topped off with the instructor talking a mile a minute (does he even breathe?) and making numerous mistakes throughout the videos. This will then prompt you to pause the video you were watching to go search the forums in order to see if the way you were taught to do something in a previous video was incorrect all along, just to find a post that confirms that the video did in fact have an error. Do yourself a favor and skip directly to the practice quizzes. You'll be equally clueless as to what is going on, but you won't have wasted time by watching pointless videos.

2.) I'm assuming the assignments and practices quizzes are in some way correlated to the subject matter depicted in said useless videos in point 1. If there is, then the questions therein are massively beefed up version of the subject. Nothing made me feel quite as stupid as practice quiz 1 of week 4 (this is where I finally gave up and called it quits). The only redeeming factor is that I'm not the only doofus in the room. The student forums are full of equally clueless people.

3.) For the price of $50 a month, I expected this course to house all I would need to ease me into the topic of Linear Algebra. Instead, it feels like I've been thrown into the ocean with cinder blocks strapped to my feet without knowing how to swim. Logically, I started grasping for the life boats that are Khan Academy and YouTube. I shouldn't have to go to external resources if I'm paying money to be taught something, but I did. Even though these external resources helped me better understand the concepts, the quiz material still looked like absolutely gibberish to me. That's when I knew this was no "Beginner" course.

All said, just buy a Linear Algebra text book off of Amazon if you want to learn this topic. It's cheaper in the long run, and coupled with Khan Academy, it'll get you farther. The only reason it isn't a single star for me is the fact that maybe it is beneficial for people who actually like math.

автор: Pirkka P

•23 апр. 2019 г.

Too many sessions and quizzes which appear to require previous knowledge of the taught subject, concept and the details. If I had that knowledge already, I would not be taking the course to begin with. The programming assignment do require previous Python/other programming experience. I would not categorize this as a 'beginner' class.

автор: Juan D

•20 мар. 2019 г.

The teacher's explanation videos are excellent, really really clear: it makes you feel as though they really paid attention on how to deliver the content in the most understandable way possible. The teacher speaks clearly, the audio and the subtitles are on point, etc.

Unfortunately, this all goes in flames when compared to the mess that is the evaluation system, which seems to jump two or three orders of magnitude in difficulty compared to what is actually taught in the lessons. This, in turn, makes it impossible to know whether the failure to get correct answers is due to one's own lack of competence, the bad quality of the lessons, or the lack of competence on the part of those tasked with creating the quizzes.

Based on my experience, as well as on the comments by other people equally baffled by the quizzes -not to mention the almost absolute absence of mentors willing to help out-, I strongly suspect it is the latter.

In my opinion, the course's effectiveness could dramatically increased if it included a lot more exercises at different levels of difficulty, in order for the students to really absorb each unit's contents. This would also have the advantage of preparing them for the really difficult questions on the "big quizzes".

автор: Chad S

•1 апр. 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.

автор: Nikhil S

•23 дек. 2018 г.

Professors teaches in so much friendly manner. This is beginner level course. Don't expect you will dive deep inside the Linear Algebra. But the foundation will become solid if you attend this course.

автор: Francisco R A

•17 окт. 2019 г.

I came to this course after starting other ML courses feeling the need to refresh/update the mathematical foundations to follow those previous courses. I have really enjoyed it and think of it as a great course in general.

Having read some other opinions here I find it a little bit odd to read people complaining about the python tasks. If you come to a course like this one is because you are interested in ML so python is something you will surely be using, so learning a bit before engaging this course would be a first step.

Regarding the maths, this course doesn't go in depth in maths theorems and stuff like that, it explains in a visual way what you need and then use the maths to accomplish it.

автор: Tim R

•13 янв. 2019 г.

The autograding of python notebooks in week 3 does not work. Submission by alternative upload did grade properly either. Just trying over and over to get the test to pass, took longer than coding the assignment. Until this is fixed, I think this course is a unfortunately incomplete.

автор: Laszlo C

•15 нояб. 2018 г.

This is a great course for those people who want to get started with ML and need a refresher on linear algebra. It's focused on the important part without overwhelming the audience with unnecessary details. I'd highly recommend this course and also the entire specialization.

автор: naveen s

•28 апр. 2018 г.

If you are looking for overview on Linear Algebra, you can save USD 40, refer to free material all over Web. Some videos on Youtube are visually more capturing than blackboard style teaching here. Knowledge of Python is required for this course, though not obvious from start. Would have been good to begin with end in mine - a 5 minute video to explain why Linear Algebra is required for M/c learning can be motivating.

автор: Darren T

•4 февр. 2019 г.

The spends an insane amount of time on easy topics, but glosses over the most difficult conceptual topics in about 3-4 seconds. The quizzes/assessments are either trivially easy, or too difficult to do given what has been covered previously. No relevance for ML is given for the topics covered.

автор: Patrick L

•26 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.

автор: Baccouche M S

•25 февр. 2019 г.

One of the best courses i studied in coursera

автор: Christoph A S

•18 дек. 2018 г.

Great and comprehensive course. Videos are very understable and interesting - however the quizzes jump a few times from 1 to 100 in terms of the difficulty and require further study besides what is taught in this course.

автор: Ehsan G

•21 янв. 2019 г.

No one cares about the homework! The Homeworks are not graded properly. Moreover, in the last module the lecturer speaks only without properly writing everything down or explain the subjects mathematically.

But honestly the first 4 Modules were explained very good.

автор: Марков Д А

•13 нояб. 2018 г.

This course is very usefull for beginners in machine learning. I've learned too much from Linear algebra, and that's more important i understood the intuition of linear math. This course contains real usefull exercises in Python that can help me improve my skill in math.

Extra thanks for clear English, because i'm from Russia and don't have enough background for understanding speech, but your lecturers have beautiful language.

автор: Evgeny C

•10 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.

автор: Tim K

•9 мар. 2019 г.

Mostly a very solid course. There are some poor descriptions of certain concepts, though, and students are expected to fill in some gaps to what I perceive as an unreasonable degree.

автор: Lochan N

•25 мар. 2019 г.

Eigen vector concept was not clearly explained as to how it applies to real world. But in general great course.

автор: Peter S

•21 сент. 2018 г.

Material is good, the exercises are insane, and you'll spend hours Googling stuff that was breezed over in the videos.

автор: 周玮晨

•6 июня 2018 г.

I want to handle the concept in a short time, so I take this course. This course really meet expetation.It really help understand a lot linear algebra and build me intuitions.Now i'm confident in learning ml.

As for the course content,The content is abundant,i really love the visualization and programming work.The programming work is fully explained , and help me in understand the materials. The programming work is a little bit easier.

Mostly, i love David! Especically his brilliant smile ,excited expression and body language which inspiring me a lot!表白David Dye，比心！

автор: Dr. K A S P

•28 мая 2019 г.

Very good course: well paced, well structured, just the right scope.

автор: João S

•10 апр. 2019 г.

The course is very good, almost perfect for my purposes. I liked specially the effort to make the students get the necessary intuition instead of pushing a lot examples as many other MOOC usually do. But I've noticed some negative points. I ask you to take my critic as a sincere effort to improve the course and eliminate some mistakes that really matters to the students. The last quiz seems quite disconnected with the lectures and there isn't a support guide or tutorial not even a mentor answering the questions in the week 5 forum. Some mistakes on videos (eigenvalues and eigenvectors) were confirmed by the lecturer but never corrected. Not even a errata on resources section. Talking about the resources, I think it is very poor. Cousera has many better examples.

автор: Miguel A F B

•29 мар. 2019 г.

This course is phenomenal, It helped me to refresh a lot of skills that I learned at my college and at the same time I learned a bit on how to introduce all this matrixes into a programming assignment which are by the way extremely hard because I am a novice at programming. It helped me to see other subitems such as Gramm Schmitt and eigenvectors that I did not see on college, I understood them but not a 100%, I guess an 75% is an average. Thanks Coursera and Imperial College London for this awesome course. I had to search other books to comprehend the subject, but next time, be more detailed.

- 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