Вернуться к Машинное обучение

звезд

Оценки: 159,029

•

Рецензии: 40,720

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....

AD

21 апр. 2017 г.

Very good coverage of different supervised and unsupervised algorithms, and lots of practical insights around implementation. All the explanations provided helped to understand the concepts very well.

RC

18 июля 2019 г.

Amazing course. It gets deep into the content and now I feel I know at least the basics of Machine Learning. This is definitely going to help me on my job! Thanks Andrew and the mentors of the course!

Фильтр по:

автор: Krishnan I

•22 июня 2020 г.

Very good course on machine learning. Prof. Andrew is a very good teacher and I look forward to taking more advanced / specialisation courses in machine learning taught by him.

Most of the concepts and algorithms are explained very well. Programming exercises are simple as approx. 75% of the code (except the core algorithm) is pre-written in all exercises. I think if some more optional and real-life problems are added towards the end of the course, to be completed offline, would help understand and remember the concepts that were learnt. This would give more practice to the students on applying the various algorithms and help reinforce the concepts while not increasing the overall course time.

Also, I think it would be better if the prerequisites are mentioned in the FAQ / About section or even better would be to explicitly create a section named "Prerequisites for the course" with some pointers to what specific topics would help understand the course better. I had to search thru the discussion forum to get this info.

автор: Rahul B N

•23 нояб. 2020 г.

Thank you Andrew Ng for making this such a wonderful course , Looking forward to your next Deep learning.ai specialization. With lots if respect thank you sir!

I also want to thank coursera for offering this course to me and I'm in high debt to this platform! thank you coursera.

It was hard really hard, To complete each programing exercise need you to understand the depth of the topic what you just learned. This course make you feel like "Yeah, I should drop this Today!". I'm From a non-maths background which made me even harder to focus on but I didn't quit instead I learned maths from the imperial college london "Mathematics for Machine Learning Specialization" , Through coursera and I came back to this course!

This course is highly informative you will get to the depth which you never imagined off, gives a super solid foundation to build anything beautiful above this. If you ever find this hard just believe me I too felt the same, but as wise man said "If I can do it you can do it".

All the very best, Gold Luck!

автор: Jon C

•15 сент. 2019 г.

Great introduction to the principles of machine leaning and its core algorithms. Do NOT let the Octave/Matlab dissuade you - while I'll likely never use it for real problems I think this was a good choice for teaching and playing with a new language was kinda fun in itself. I would've liked to see Decision Trees in the curriculum, and sometimes I felt the videos ran long on easy concepts and went through important points too quickly, but I also recognize everyone has different priorities and backgrounds. This course strikes a good balance on those issues.

One tip: You can get away with filling in the blank functions of the coding assignments and learn little except transcribing equations into matrix operations in Matlab. Don't do that. Read all the code, play with parameters and see what happens, google things that make you curious, etc. This is important to get the most out of those. Fundamentally, despite the awesome materials, these are not "hand holding" courses and are best used as vehicles for self-study.

автор: Antonino I

•30 янв. 2019 г.

Excellent class to gain a broad overview of the field of machine learning. I was already quite familiar with data analysis and linear algebra. The teacher is great at breaking down complex topics and give progressive step-by step understanding. The math notation is very lightweight and I would have liked a more expanded linear algebra context. However, it was quite easy to connect the course material to a more formal linear algebra approach and I enjoined doing so as a side during the course.

The number of topics and the depth of each topic strikes a pretty good balance between the need of deep understanding of each technique and the need to have abroad enough awareness of different methods. I particularly like all the elements related to "debugging" machine learning that are introduced throughout the course. These include model evaluation and crucial decision like whether to work on improving the model or collecting more data, which component of the pipeline to will give the most gain if perfected and so on.

автор: Olivier D

•13 мар. 2019 г.

I completed my undergraduate degree in economics. As much as I love the mathematical rigour of economic models and and theory of economics I found econometrics much more engaging, practical and able to deliver more value for others. I studied advanced econometrics like binary models, truncated models, EV and so on and having found machine learning & data science I feel that this is a natural extension for me to pursue a big interest of mine.

With that in mind, the introductory course was reasonably challenging, in the sense that the theory naturally built on econometric maths. The programming was something we touched on in university so a steeper learning curve. Linear algebra was also something I had to actively think about but again manageable.

As they say, the more you know the more you realise you don't know. I am finishing week 10 currently and hoping that there are suggestions as to where I should head next on my journey in order to learn more rather than re-capping what was covered in this course.

автор: Hasnain L

•15 февр. 2020 г.

Andrew Ng is a boss when it comes to teaching. Throughout the course, he has simplified the machine learning concepts to a point where they can't be simplified any further without losing their mathematical basis.

The programming assignments in the course are really fun, however, I would have preferred if the assignment packages did not include so many hints on how to program a particular algorithm. With the exception of the programming exercise on implementing back-propagation, I mostly avoided looking at the pdfs that came with every assignment and only followed the guidelines in the starter code to implement the algorithms. I felt that this allowed me to gain a deeper understanding of the architectures of different algorithms.

The course is super dense, beautifully structured, and covers most of the topics in surprisingly great detail. If you want to start building a career in machine learning, this course is simply a MUST!

My sincere thanks to professor Ng for putting together such an awesome course!

автор: Felipe A C d O

•12 мая 2017 г.

Outstanding course! Andrew is an exceptional teacher, making difficult and complex topics easy to understand. The course is very well structured in a way that there are no questions left unanswered and you can have a really in-depth understanding of the topics by just watching the videos and paying close attention. I have a degree in electrical engineering, so it was quite easy to follow the course. But I believe that even people with no programming/engineering/mathematical background would benefit from this course, because Andrew makes it easy to understand the concepts and the algorithms formulations. The programming assignments really provides a good practical approach for all the theory given in the video lectures, and the code templates are very well structured to enable even someone with no background in programming to complete the tasks. The functions used and implemented can then be adapted for implementing your own machine learning problems. Overall, great course, I am very satisfied with it!

автор: Arun K K

•10 янв. 2016 г.

Hi Coursera,

Thanks for providing a course like this. I have had experience with a lot of MOOC but nothing can come closer to the simple explanation with technical depth from Andrew Ng.

I feel really confident having done this Machine Learning Course. It has become very easy for me to interpret any Machine Learning problem and attempt to solve them.

Please convey my deep sense of gratitude to Andrew Ng. Without him the coursera and the accessibility of courses like this would have become impossible for people like me who are from developing country.

I have few suggestions regarding Machine Learning Course :

1. If possible can we have a Machine Learning Part 2 course which is more advanced w.r.t content (math oriented), data munging, some more algos and with more focus on industry applications.

I have few suggestions in general :

1. Few relevant courses are shown as archived (Eg. Neural Networks) for past few years. Can you unlock them and make them a recurring course like 'Machine Learning'.

Thanks,

Arun

автор: Ilya L

•5 сент. 2017 г.

I found this class easy and fairly interesting. I do have some math/programming/Matlab background, perhaps that's why I found the class easy. I didn't have any machine learning experience before taking the class (except perhaps knowing what a linear regression is), so it's a bit hard for me to judge the quality of the content.

I wish the class had more reading material (for about the first half of the class the videos are paralleled with reading pieces, and I think it would be great if this coverage gets extended to the rest of the course).

I do not know how much feedback is provided by the automatic grader for the programming assignments (I was lucky to have all my programming assignments accepted at first submission). If for each failed submission the grader provides the input data and the expected output, that's really great. If not, that's something that can definitely be improved (the grader can use random input and the corresponding output from a reference implementation at each submission).

автор: Devendra C

•8 июля 2018 г.

Excellent course for any ML started. I like the hand-holding approach to programming which doesn't scare one off who has little knowledge of programming. Basics are cleared in efficient way. To borrow from Quora "I believe Ng’s course is especially to-the-point and exceptionally efficient, so it is an extraordinary acquaintance for somebody needing with getting into ML. I am astounded when individuals disclose to me the course is “excessively fundamental” or “excessively shallow”. On the off chance that they reveal to me that I request that they clarify the contrast between Logistic Regression and Linear Kernel SVM, PCA versus Matrix Factorization, regularization, or gradient descent. I have talked with hopefuls who asserted years of ML encounter that did not know the response to these inquiries. They are for the most part plainly clarified in Ng’s course. There are numerous other online courses you can take after this one but now you are for the most part prepared to go to the following stage."

автор: Janis K

•5 февр. 2018 г.

Course "Machine Learning" cover all main topics of macine learning and describe algorithms very clearly. After the course you will feel that you are AI and machine learning expert. However, this is introductinary course and I believe seperate course can be created for every topic, algorithm and method covered here.

Course gives opportunity to solve real world problems. Octave was discovery for me and I find it much easier than R.

It was easier to follow the course because I had background in mathematics. You will need to use and understand matrices and vectors that are important to complete programming assignments. However course starts with mathematics and explain all the basics that will be used in this course.

Course was quite difficult for me, it was quite difficult to complete assignments in deadlines, I had no time to think more carefully about covered topics. I will do it now after a course.

All in all I strongly recomend this course if you are interested in machine learning and AI.

Thank you!

автор: Atul S

•24 нояб. 2017 г.

Excellent course, was very interesting and helpful. As with any course, I have a few suggestions:

-- Why not develop the math in vector notation from the start? It would be easier for students to take a few minutes to understand basic matrix algebra, and then the cleaner vector formulation. All those summations, subscripts, superscripts, etc. are much more confusing to tease apart!

-- It would be helpful to have Andrew (or a tutor, for that matter) to write up the notes as a text. I, for one, would have happily paid (say) $10 for a PDF with a bibliography at the end!

-- As part of my "textbook" suggestion above, or as a standalone, it would help to have a small list with explanations of Octave functions used. That is, some of the built-ins, and also some of the more complicated ones (like fmcxxx). As an extra-credit exercise, you could also advise at the end of each assignment what to do to generalize our Octave code to make it even more useful (apart from vectorization), things to avoid, etc.

автор: Laimonas S

•5 февр. 2017 г.

This was my second course in ML. I took it with the aim of gaining a deeper insight into some of the fundamental topics and I was not disappointed. The professor Andrew Ng teaches the concepts in a way that is easy to understand and reason about. I loved the pace and the way the material is structured. Quizes and programming exercises completed the lectures very well to give a more complete picture of the topic at hand. Actually some of the quizes and specifically programming exercises are quite challenging. This is actually a good thing as the lectures alone would make the course a bit boring and without any practical application examples.

I wish the videos were a bit better in terms of video / audio quality, so be prepared to ignore that aspect and just take the incredible knowledge that is given to you.

If programming exercises are too hard, do struggle through them and use the forums to solve them. It really helps you deepen the understanding of the concepts that are taught in the class.

автор: Julian C

•26 дек. 2015 г.

This class was a great introduction to machine learning ideas and implementation. Prof. Ng does a really good job of not only showing you how to code up machine learning examples in MATLAB/Octave, but explaining the rationale behind them. If machine learning is as much an art as a science, then this is the "artistic" part, which is hard to find in a textbook.

However, I do kind of wish we had covered fewer topics, but in more detail. Mind you, I'm biased because I was a math major and want to see proofs for everything, but I would have really liked to see more of the details behind support vector machines and neural networks. If you're looking for that kind of thing, then it's probably best to do additional reading on your own.

Anyway, I still gave this class five stars because I have been searching for an introduction to machine learning that could give me a broad perspective (and share some wisdom of expertise) for a while now. I found it in Andrew Ng's machine learning class on Coursera.

автор: Philipp H S

•6 окт. 2020 г.

Thank you very much to Andrew Ng and his Team for this very interesting course. It is clearly a great way to get a good background on Machine Learning.

Although I already finished my university degree in physics I learned many new things. Especially the discussions on applications and the best practice examples for improving machine learning systems are very insightfull.

The mathematics is on a level which allows to understand the basic principles of the algorithms well. The review quizes are generally well designed, only occasionally there are some problems with unclear formulations ("Is X a large value?", compared to what?)

It is a bit sad that the programming excercises are in matlab, python with numpy would be closer to industry aplications and there would be no need to always write "remeber that index 0 is index 1 in matlab". However this is only a minor point. In the general the excercises are very helpfull and were clearly designed with a lot of care.

In total, a really great course!

автор: Antonio C

•1 апр. 2021 г.

I am currently a software engineer and just finished up this course. Going into this course, I only had a high level understanding of machine learning systems. I saw a review on here that said that Professor Yang did not go in depth as he maybe should have in regards to the math behind the algorithms. I would argue that if he would have gotten into the theoretical side of things, then this course would not be what it is today. Frankly, it comes down to your expectation for the course. I did not come into this course expecting to come out a machine learning expert. Rather, I went into this course with the sole purpose of getting exposure to such a technology and this course did a great job with that. With that said, I now have a deeper understanding of the capabilities of machine learning systems. I hope to apply this knowledge both in my personal ambitions and those of my employers. If you are on the fence about taking the course, do yourself a favor and go for it. Best of luck.

автор: Jason W

•15 дек. 2016 г.

Professor Ng has been working with machine learning R&D for more than 10 years now and have seen the significant phase of evolution of this field before it gain its popularity. Undoubtedly, AI and ML is going to be ubiquitous and impactful in many creative forms in the coming decades and I'm very fortunate to not only gain such an in-depth intuition and understanding of the fundamentals of machine learning, but also to gain the confidence needed to articulate these concepts and theories with Prof. Ng's guidance. The difficulty of this course is average. Quizzes and programming exercises require solid understanding of the concepts and also a lot of patience (just because you don't understand a particular concept, doesn't mean you're dumb. Give it some time and perseverance and you will pull through). Thank you Prof Ng and Coursera for this course. I would recommend this course to be the first stepping stone if you're going to venture your life in to the world of Artificial Intelligence!

автор: Nimrod B

•12 мая 2020 г.

I found the course very interesting and informative. I wanted to learn for a long time about Machine Learning, Neural Networks, Artificial intelligence etc. so the course in Coursera came in a good time during the COVID-19 quarantine. The videos are explained in a very good way by Dr. Ng. Slides are extremely useful. The question/quiz is helpful to digest the information and the programming exercises are done in a very good way in order to implement the acquired knowledge. I will probably spend more of my out-of-work time in Coursera in order to learn more about implementation of Artificial Intelligence and Deep Learning which are the next two subjects of interest. A final note: since I am using MatLab in my daily work as a researcher in academics I found no problem in implementing the exercises also in somewhat more advanced vectorized way from the earlier exercises. Many thanks for the excellent course and a nice interface for remote courses such as Coursera. Dr. Nimi (Nimrod) Bachar

автор: Ivan M

•8 окт. 2019 г.

Andrew Ng is such a great person and teacher! This course is just pure gold and this is my first MOOC.

Andrew smoothly guides you through the most important concepts of machine learning, doing so, that you really understand things very well. He eaxplains pretty difficult things in easy way, generalize ideas very well, so, that you don't need to remember lots of things, but actually just understand principles.

Also, with his great experience in the area, he gives you super valuable advice on application of ML and prioritization of work. He knows what are the most important things to know, so you can trust him!

I was happy to learn everything and work on assignments thoroughly, which are of such a great quality!

Tests in each video and at the end of the topic are also great and help to check your understanding!

My life never would be the same :)

Andrew, thank you with all of my heart! Due to your work new generation of AI engineers is appearing!

Now, I will learn Deep Learning Specialization!

автор: Yemao

•21 мая 2019 г.

This is the best course for machine learning beginners. The best. Andrew explained many fundamentals very well and it is not just one algorithm that he focused on but he wanted the students to understand how to debug and how to improve and optimise. These "strategic" stuff are probably more important than the hardcore "tactic" algorithm stuff because students will have a better understand about what they are learning and why they are learning this, more importantly what they shall be learning in the future. I would like to thank all the efforts from Andrew and other mentors on course for developing this fantastic course. If you really want to pick some bones from an egg i would say that probably provide a python version of this course would be brilliant. For the same course assignment, in matlab the codes should be this and the codes in python could be this...i know this will put so much much more work on the course developers but you know just a small suggestion. Thank you Andrew!!

автор: Siddhartha S M

•2 апр. 2020 г.

Profession Andrew NG has a quite indepth knowledge in the Field of Machine Learning and he covered almost all the topics in very great detail with the approach of creating basic building block of the Machine Learning of any individual. Although, sometimes I felt that professor deep dive into too much derivatives and mathematics but after completion of the course, I realized that all those stuff were necessary for creating a foundation of the subject.

The course content covers quite mathematics and consumes a lot of time but I felt it worth investing. I took more than the video time to complete the course because sometimes I had to google the terms and understand the basics first and then returned back to the course again to continue. This may be because I was novice for the field at the time of starting the course.

Thank you very much Professor Andrew NG for devoting your time and energy with full of compassion to share the knowledge and helping us building the basic understanding.

автор: Winson L

•2 окт. 2018 г.

I graduated at UCL in London, my PhD was in Electronics Engineering, far from maths and computer science. Machine learning is a very interesting topic that I have always loved to explore. By coincidence I became a data scientist working in London where machine learning was needed. 2 years after I first come across Andrew Ng's coursera video lectures, I decided to finally go through all the modules and get the certificate. Not native to Octave, but I am glad that I have learned it for the assignments and now feel very comfortable on applying it. Today, I have finally completed this course, after spending many evenings late after work staying in my work office's meeting room to study. Many thanks to Andrew and all the examiners in this course. A special message to Andrew: I have recognised your appearances on TV and blog posts documenting artificial intelligence, I wish you every success, and I secretly wish that one day we would cross paths with each other.

All the best. Winson Lam

автор: Humberto F F

•17 авг. 2015 г.

This course is an opportunity to get acquainted with several machine learning techniques, including linear regression, logistic regression, Support Vector Machines (SVM), anomaly detection, non-supervised learning (clustering, K-means, etc), recommendation systems and very interesting discussions about batch/mini-batch versus stochastic learning and large-scale learning systems. It does not require a deep knowledge in algebra and calculus (although a solid background in mathematics surely helps a lot) and progresses in a logical manner from easy, standard techniques to advanced ones.

If you are new in this realm, this course is comprehensive enough to make you confident to design your own customized algorithms. If you have some experience, you can consolidate your knowledge and benefit from the tips the instructor gives throughout the course. I've been dealing with adaptive filtering for some years and I can say I've enjoyed this course so much. I definitely recommend it!

автор: Wahyu G

•15 дек. 2017 г.

This course is really really really amazing for me! Andrew Ng is a great lecturer. There are 2 main parts here, the maths and the intuition. Most of the time, the class talks about the intuition and the reasoning, i love it. The reason behind that is you can take a more advanced course about machine learning or deep learning afterwards with a good intuition about the algorithm. But, the math is not so little, too.

There is also the programming assignment which really really helps. See your code works is one of the best feelings, even you dont build it from the 'really scratch'. The hardest part in this course i think is in the Neural Network and SVM part, but once you've past through that, trust me, you'll pass along and enjoy the class.

100% will recommend it to my friends. Speak about myself, I am not a cs student but i think i have a little bit of confidence now.

In the last video, i'm so touched. Thank you Andrew and team, definitely going to take Deep Learning specialization.

автор: P S R

•16 авг. 2017 г.

Fundamentals well explained, solid programming exercises complement the theory giving us an opportunity to see the theory in live implementation. Contemporary solutions like recommendation systems, e-mail spam, image recognition and long standing regression/classification techniques are well balanced. Advice on practical implementation of ML applications is the highlight. Over all it is well designed and delivered. However, it approaches more from mathematical/engineering stand point, whereas in business world it is approached more from statistical analysis perspective using co-relation, R-square, p-values, error function following normal distribution etc. Some linkages between the two approaches may help us become more productive at real life work. Almost entire course focused on classification problems, except the first exercise that deals with house price forecasting. May be few examples of regression with the same algorithms also can help matching the needs of enterprises.

- 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

- 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