Вернуться к Машинное обучение

4.9

звезд

Оценки: 151,434

•

Рецензии: 38,632

Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI.
This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas....

AQ

2 мар. 2018 г.

An amazing skills of teaching and very well structured course for people start to learn to the machine learning. The assignments are very good for understanding the practical side of machine learning.

JS

16 июня 2017 г.

Everything is taught from basics, which makes this course very accessible- still requires effort, however will leave you with real confidence and understanding of subjects covered. Great teacher too..

Фильтр по:

автор: Zachary L

•5 сент. 2015 г.

The subject of the course concerns how to estimate parameters to make predictions about data and to classify data.

The lectures are very clear and the examples are well chosen. The mentor, Tom Mosher, is also diligent, clear, and patient. In addition to the subject matter itself, it is interesting to learn that these are some of the key methods used in Silicon Valley.

If you have a strong mathematical background, some of the early lectures are too slow. (On the flip side, for someone with less background, the course is self-contained.) However, by about lecture 3, I was glad I stuck with it. Instructors might consider adding some no-credit quizzes to help people "place out" of certain videos. If you can get past the assignment on backprojection for neural networks, you're home free!

автор: Sepehr V

•9 февр. 2018 г.

Andrew Ng's teaching methods are simple and effective. I appreciate his focus on ensuring students understand the underlying ML algorithms and techniques and merely using a tool such as Octave or MATLAB for implementation purposes.

The course structure is effective for a few reasons. One, each video session includes at least one or more multiple choice questions to gage the student's attention and probe inquiries regarding upcoming topics. Two, each larger topic has a 5 question quiz to reinforce learning and information recall. Finally, each week has a mini-project or homework assignment where you get to implement the ideas into actual trained models using the algorithms and methods introduced in the week.

If you're curious about ML or AI, I'd highly recommend starting with this course!

автор: Gabriel P

•20 апр. 2017 г.

Great course.

After also watching some of Professor Ng's Standford lectures on YouTube, it is obvious that he focus on the most robust algorithms in this course (out of the many algorithms out there). It was also very nice that he focus a lot on the application of machine learning. Some of the application discussed included great information on areas such as handling big data, performance oriented approaches to computations and performance analysis to allow developers to focus their work on what matters most. A great benefit of this course is that it is a great foundation for understanding the latest research papers on the topic such as uses of Recurrent Neural Networks and Convolutional Networks which have been shown to be successful in natural language processing among other things.

автор: Sufen F

•25 нояб. 2020 г.

Professor Ng does a great job of making complex concepts simple and reassures the student by sharing what to focus on and what is not important. I also loved the programing exercises that made sure that I understood the material well to get it right. This whole course changed the way I approach problem solving and showed me ways that I learned that were not conducive and how to improve my future learning (e.g. it is easy to write code but 90% of the effort is in debugging; really reading through all the material and understanding what the exercise is asking + reading through FAQ/programming resources was a better strategy than trying to start coding as soon as possible with limited understanding). Thank you Professor Ng and teaching mentors! You've made a huge difference in my life!

автор: Dr C J W

•25 янв. 2019 г.

Excellent course from one of the masters in the field, Andrew Ng.

Students already familiar with regression modelling may be a bit bored initially (though perhaps they didn't know the matrix notation for it?), but by week 4 things are picking up. The Matlab/Octave programming exercises are well-designed, and for someone who didn't know Octave before, learning this was a bonus.

Compared with Hinton's 2012 course, Ng's is better for beginners, covers slightly different topics (Support Vector Machines, but not Boltzmann Machines, Belief Nets, and Autoencoders), and makes a knowledge of calculus optional (though it's more interesting if you have this - especially chain rule). Hinton's course would be a good follow-on from Ng's, to check whether you really understand how the methods work.

автор: Sebastien A

•19 сент. 2017 г.

The best MOOC on Machine Learning I know of. Covers many statistics-based / numerical algorithms, plus Neural Networks and SVMs. I found this course very useful because:

1) It allows students to program most of the algorithms, instead of just "using" pre-made stuff. Programming is not a chore because the language chosen is adapted.

2) It provides relevant and "like in real-life" datasets that allow to carry real tasks (character recognition, image compression, ...).

3) It provides very valuable advice and méthodology on how to deal with Machine Learning tasks and algorithms in practice. This is a real plus compared with other ML courses.

One regret is that some representations / ML algorithms that are not numerical but very useful are not presented (eg. Decision trees / ID3 C5.0, etc.).

автор: Daniel H

•15 окт. 2019 г.

I'm impressed at how clearly the material was communicated and how the quizzes and programming assignments were difficult/complex enough to be challenging and educational but not overwhelming. I also appreciate how clear and well-commented the provided framework code was. This made it easy to understand how the code we needed to write was being used and helped cement my understanding of how the algorithms work. My only complain (very minor) is that it seemed that some formulas and examples presented in the slides were transposed differently from the example data provided in the programming assignments. This required me to really understand what the matrix multiplications were doing (which was good) but was also frustrating at times. In any case, thanks for an overall-great course!

автор: Zzm S

•7 мая 2018 г.

Thanks you so much for putting together this class. I am a young professional in data science area and finally finished this class after more than 3 months. The topics are practical especially the last few weeks about designing pipeline and where to spend your time. At the very beginning, I found it's challenging and I have to watch the videos for a few times, take notes afterwards and refer to the formu to finish code assignment. But after completing week 5, everything works smoothly. Another very good thing about this course is Andrew also give review of relevant knowledge like linear algebra so I don't need to spend time searching for other resources. This is is a great class and I am going to apply what I have learnt to work. I am happy I finished this class on my birthday ; )

автор: Jeffrey W

•13 дек. 2015 г.

This was my first coursera class, and I came out feeling confident in my use of the methods that Prof. Ng taught. The programming exercises do a very good job of guiding students through the implementational details of each learning method and usually provide examples to illustrate the strengths, weaknesses, and options within each. I'm a graduate student in a protein structure/rational drug design lab, and the topics from this class have already weaved their way into my projects. These methods are applicable to almost any quantitative form of data - I strongly recommend this course for other young researchers, either to prepare to implement the methods themselves, or to just start thinking about how to format the conventions of their sceintific domain in a machine-learnable way!

автор: Jadon P

•10 авг. 2019 г.

Andrew Ng did a fantastic job of giving an overview of many different Machine learning algorithms. Professor Ng gave practical checks to perform along the way, questions to ask regarding what to try next, and related all of it to real world examples he has seen. This course is definitely one that many people can accomplish without having an extensive background in mathematics, though the notation can get a bit tricky near the middle. I was a bit disappointed on a few occasions that Professor Ng didn't go into more depth on "the how" of the algorithm and found that a few items were glossed over. Overall, I found this course to be beneficial (especially with the aided programming assignments) and it has given me motivation to continue to learn about machine learning in the future.

автор: simachew M

•27 нояб. 2018 г.

Great Lectures (presentation)! Great course organisation.

I will not talk much on the positive aspects, but rather focus on some of the points that I think could be improved: -- I think one of the videos at the beginning has some visual noise and was hard to watch. -- At the starting weeks, I found it not loud enough to hear it (perhaps it is just for me) and believed it could be enhanced. -- No question about the great demonstrative coding exercises; however, a lot more of the part had to be left for us. -- The last two weeks should have demonstrative assignments as well. They are rich in terms of content to prepare similar exercises as the earlier ones. Probably, you could implement such kind of improvements, to make it even greater.

My great thanks to Andrew and fellow tutors.

автор: Senya S

•17 июня 2017 г.

Thank you so much to everyone who put their hand to this beautiful course, especially prof. Andrew Ng whose voice is now associated for me with machine learning like maybe forever, and all the mentors who patiently helped all us newbies on the forum. Starting from Week 2 I could not resist the urge to write down everything Andrew says and writes so now I have a perfect clear notes about main topics of machine learning, using which I believe I can explain the main concepts to almost any person. The course is in fact so good, even being somewhere in the middle of it, I was able to talk and keep up the conversation with professionals from the industry without feeling any lack of theoretical knowledge.

So thanks you guys again, it's been a great pleasure to be a student of this class!

автор: Sachin B U

•11 июня 2020 г.

It is a well structured wonderful course for people who are new to concepts of Machine Learning.

The course covers concepts of Machine learning under classification of Supervised and Unsupervised learning.

And also guide you on how to evaluate the performance of the algorithm.

One gets insight into advance topics which are being worked in the field.

The instructed assignments which cover above topics, push one to work on codes and relate the working of algorithm with theory.

one need not worry too much about writing too many code lines as coding needs to be done only where the key concepts from class are applicable.

It has helped me to get a good view about fundamentals of how AI system work the way it does.

Thanks a lot to Andrew and team for setting up such a cool course.

автор: Curtis G

•20 июня 2017 г.

An excellent overview of some of the most popular machine learning algorithms in use today. I particularly enjoyed the mathematical treatment of the subject matter, rather than simply plug-and-play algorithms, as are available in many software packages and libraries today. Additionally, the use of Octave / Matlab is a welcome change from many courses on data science / machine learning, most of which use Python and/or R. The use of Octave allows for the more mathematically mature discussion / implementation of each algorithm. I found it very rewarding to understand WHY these algorithms behave as they do, and what is actually going on "under the hood." Thanks to Andrew Ng and all of the TAs who worked so hard to make this course possible and maintain it for learners of the future.

автор: Hendryk T W

•16 окт. 2019 г.

The course has been a great overview about machine learning problems and algorithms. It also covers further details like advantages/disadvantages of certain techniques or ways to handle performance analysis and optimisations. Most explanations can be understood easily. Both videos (with visualisations) and texts are given to present the content (in the end there are less summaries).

The programming exercises are very helpful, as one can see the algorithms work and really needs to understand all the ideas to implement them correctly. There are also lots of little tests which ensure one does pay attention to the lectures.

Unfortunately there are some minor mistakes in the materials, which may be confusing until one looks for the issue on the forum (there are lists with the errata).

автор: Mijael M

•12 мар. 2018 г.

Awesome course! Some people might say it is a little outdated, but in reality, I've found it covers more material than the more updated version undersigned by Prof. Ng (DeepLearning.ai). Both courses complement each other and fill the gaps of each other.

Regarding the use of Octave, since it is based on Matlab, the language is more consistent and robust than the commonly used Python. The latter is strong on its 3rd-party libraries, but as a language leaves things to be desired. Not with Matlab/Octave. Also, I believe it is very valuable to have access to the multiple tools for signal processing, automatic control, etc.

Great course overal, and thank you to Prof. Andrew Ng. It is awesome what you did and the quality of the materials you put out there, for the world to learn them.

автор: victoria m

•18 мар. 2020 г.

It has been a real pleasure to take this class and learn, without complicated math proofs, the basics of machine learning algorithms and techniques. This material will help me out to apply it at work. The quizzes and specially the programming exercises have been of great help. The “Test cases resources” have been extremely useful to check my implementations and debug my code. The week lecture notes are very useful because it has all the lecture notes without the need to go through all the video presentations. The course contains so much information that I had gone over the material twice and still think I need more time to really get a grasp of all the material. Thank you very much for making this material available to all the people interested in learning about this material.

автор: Hongwei L

•13 сент. 2019 г.

i basically don't write reviews in my life. But i am willing to write very positive review for this course. because it is so special and it brings me through the door of machine learning world.

Compare with may other machine learning courses which most focus on how to use the existing formulas, tools, libraries, apis, etc, this course actually helps me understand the fundamental theory and its relationship to the math formulas that a specific problem use. that's the most powerful thing makes the course stand out in crowds.

when you struggle at most of the fancy concepts you see or hear in other places but don't understand what they really mean, then this course will provide the keys to let you understand them better, and open your mind.

thank you so much professor Andrew Ng.

автор: Michael K

•23 мая 2017 г.

Professor Ng is not only one of the premier authorities in the field of machine learning. It turns out he is also one of the best educators I've ever experienced. I truly admire the easy with which he can explain complicated concepts. He chose the right pace to move through the material, and liked his enthusiasm which reverberated through each movie. I want to congratulate Professor Ng to this highly successful class. I've enjoyed every minute of this. I was new to machine learning, and I'm glad that Prof. Ng was the first who introduced me to to. He has given me a base knowledge to which I feel I can always come back when things get more complicated.

It's been a real pleasure to have been taught by you, Prof. Ng. Well done. I wished the world would be full of people like you.

автор: Chamoda N N

•29 мая 2018 г.

It was a great privilege to take part in this course. I had little to no knowledge in Machine Learning before taking this course. But I hope I have a sound understanding in this field. I have to thank all the mentors who had supported with solving the content related problems I had. Having questions in the video lectures was a good idea as it keeps our attention to the videos. The Review questions also tested my skills and understanding very well. Programming assignments were time consuming a bit , but worth a lot. Flexibility with submission deadlines also helped me as I was busy during some weeks. Also this course helped me to solve an industry level problem to a certain extent.Lectures would be more understandable for anyone with little knowledge in mathematics too.

автор: Rajnil G

•1 янв. 2018 г.

This course was simply amazing. I got to know what happens under the hood in different machine learning algorithms. Prof. Ng was wonderful as the instructor for this course, and he presented these complex ML concepts in such simple ways. Also the mentors were great and I got response from them regarding my various doubts in the discussion forums. Lastly I would like to talk about the assignments. The quizes tested your theoretical concepts while the programming assignments were there to test how well you can convert your understanding to code. The problems like digit recognition, email classification, image compression to name a few gave us a lot of inside into the problems of ML in real life. In one word this course was exceptional and had a wonderful learning experience.

автор: Zhi S

•24 июля 2017 г.

This courses has introduced many interesting machine learning subjects, with a... ahem... learning curve that is just right for me. There are a lot of aha moments when you see the powerful effect of these algorithms on learning pictures, building a recommender system, creating clusters, etc. . The programing assignment is the most time consuming but it's not really difficult because students are only asked to fill in certain parts of certain functions. It does help to have a good foundation of linear algebra, but Prof Ng has simplified the maths to a great extent and provided tons of examples to make the algorithm as intuitive as possible. Great course! (The fact that I have finished it without missing a week is a testament of how interesting this class is at least to me.)

автор: Simon N

•19 апр. 2016 г.

The true value of this course lies in the excellent programming assignments. From identifying hand-written digits in postal codes to providing plausible movie recommendations for users of a streaming service, you can be sure that the problems are non-trivial, applicable, and elucidating.

As other users have pointed out, it is true that this is not a very mathematical introduction to the subject. Ng's concern is clearly with pedagogy and implementation over theorem-proof. However, given the abundance of rigorous (freely available) material on the subject online, this can hardly be classified as a serious shortcoming. Rather, each video lecture can be viewed as an appetiser which teaches you "just enough" to start coding, while opening the door for further independent study.

автор: Ahmy Y

•6 дек. 2015 г.

I believe this is the most enjoyable nine weeks course that I ever had. Prof. Andrew has his way explaining a complex mathematical concept in an easy and non-intimidating way. I used to be afraid & dislike when it comes to statistics, machine learning related field. After following this course, I've gained a bit more courage to learn more complex and exciting field. The Quiz and programming works are challenging but enjoyable to do. It gives me more understanding about the topic while having fun applying the concept to real problems in my field of work.

The course itself is really interesting and relevant if you are in the software engineering field. There are a lot of concepts that you can apply to your work. I highly recommended to follow the course and do the assignment.

автор: Varun T

•19 сент. 2020 г.

Quite and interesting course, and it has been very insightful.

The course content, I feel, is just optimal, and easy enough to understand the basics of the machine learning, for a beginner like me.

The assignments were really good, and the pdf handouts were very useful to navigate through the problem statements very well. I strongly feel, for everyone who has opted the course, one needs to be aware that the programming assignments are just the beginning and more emphasis needs to be on the application of the concepts of machine learning even after completing the course, to have strong command/understanding on how the algorithms work.

Overall a very good course when it comes to basics of machine learning and its applications.

Thank you Andrew for your well structured course.

- 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