Вернуться к Машинное обучение

4.9

звезд

Оценки: 154,002

•

Рецензии: 39,295

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....

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!

RS

12 авг. 2019 г.

Andrew Ng is a great teacher.\n\nHe inspired me to begin this new chapter in my life. I couldn't have done it without you\n\nand also He made me a better and more thoughtful person.\n\nThank You! Sir.

Фильтр по:

автор: Adam P

•1 февр. 2019 г.

I found this class to be excellent. Professor Ng presents the materials in an approachable way that goes into the mathematical intuitions of the topics. As always further mathematical study (in this case specifically linear algebra) would be helpful, but for the length and scope of the course there is an excellent balance of mathematics with practical usage. I also found myself agreeing with the notion that Matlab was useful as a prototyping tool (a view I didn't initially hold), and I use it for that on my own now when the situation warrants it. I personally would've liked an overview of the tools for these types of algorithms in any of a number of programming languages, but I can see how that is not really the focus of the course, and with the fundamentals gained from this course transitioning to other tools should just be a matter of familiarity with the tools, rather than the algorithms they implement.

автор: Barnaby R

•4 нояб. 2015 г.

This is a great course ! The pacing is just right. Andrew covers each topic in very easily digestible bits and is very careful to not overwhelm beginners. I find this technique incredibly refreshing and open and welcoming. It is all too easy for professors to act like elites in their ivory towers and make you feel foolish for not knowing enough but Andrew is the opposite of that and actively encourages you to push through difficult topics by focusing on the high level details first and leaving it up to you to research the details on your own.

The programming exercises are set up so that all the distracting details are all coded already and it's up to you to fill in only the parts that are directly relevant to the topic you are learning. There's only one exercise that is slightly confusing but it's easy to get help on it in the forums if there's a helpful moderator like Tom Mosher around !

Highly recommended.

автор: Johan H

•3 нояб. 2020 г.

Excellent primer. Would recommend.

Touches a wide spectrum of topic, but because of that breadth it can't get into the depth of things. Have often heard Andrew tell that the underlying mathematics falls outside the scope of the course.

The course doesn't use Python. Instead it uses MatLab - or Octave - for the assignments. Whereas I was more familiar with Python, I actually rather enjoyed this excursion and felt challenged in removing all iterations and for loops insofar possible.

On the other hand, when you talk in terms of its applicability, it would've made more sense to have the course run Python. If you as a student stop when finishing this course, there's still quite a threshold between your run-of-the-mill Python/numpy environment and the course - with its MatLab/Octave environment. Would be a shame if that should stop people from experimenting further and putting the lessons learnt into practice.

автор: Arnaud L

•10 февр. 2016 г.

Excellent course, perfectly paced and detailed. The professor Andrew Ng succeeds in creating a comfortable atmosphere and is easy to follow.

As a beginner in machine learning, I appreciated the fact that the contents cover the most important aspects of machine learning, without diving in too fast in the underlying mathematics and computational details. I think I need go deeper in these aspects now, but these lessons are rich of practical and methodological tips that i'm sure even advanced engineers would need.

Last but not least, the Octave/Matlab hands-on exercises permit a deeper understanding of the algorithms, and to realize what remained misunderstood after the lectures.

I am happy that I decided to start (and to end) this course. This was my first on Coursera : there will be others. Many thanks to Mr Ng, to the mentors that helped us on the discussion boards, and to the coursera team in general.

Arnaud.

автор: Norbertin N E

•8 окт. 2020 г.

This course has definitely provided me with the necessary theoretical knowledge of the concept of Machine Learning. It is not difficult at all if one has a good grasp of linear algebra, statistics, probability, with some experience in MATLAB/Octave programming. I always find it more useful to set the foundations right with first principles, before setting off to using more advanced tools and libraries that tend to operate as black boxes.

However good the course content, my next step in this journey of Data Science and ML is to explore with more advanced courses that cover the tools used in industry, and experiment with practical applications in order to gain some solid skills in ML. But, this course definitely served its purpose, as far as I'm concerned, and I shall GREATLY THANK COURSERA, Prof. Andrew Ng, and all those who were involved with it and helped facilitate the learning experience for students.

автор: Marnie L

•21 мар. 2019 г.

Professor Andrew Ng's Machine Learning course was an excellent learning experience. The course was well organized and pedagogically sophisticated. The combination of hands on exercises, quizzes, and lectures made the course enjoyable, engaging, and easy to learn and retain. I believe that Professor Seymour Papert would approve of the methods in this course. The exercises provided the students with the opportunity to interact with the material. By providing a framework of well designed code, with the task of writing the core concepts on our own, students could focus on the important things and simultaneously learn from the expert and optimized code provided. We were expected to use vectorized implementations, which enabled us to both think about the problem in a mathematical way and write code that is efficient and scalable. This course is a Machine Learning classic. Thank you Professor Ng and tutors!!

автор: Gaetan P

•8 мая 2020 г.

Many thanks to the professor Andrew Ng for his time and effort to make these videos.

This course is perfect for beginners to understand the key concepts behind ML. It is quite reasonably easy in terms of mathematical and programming skills required (standard linear algebra knowledge is sufficient). The videos won't mention inessential mathematics, because the point of this course is to focus on the practical implementation of several algorithms in real-life examples.

In practice, start with this course to get all the main principles, and then learn to use more pratical engineering tools (like TensorFlow, Spark MLib, or Matlab machine learning apps)

I highly recommend the 'useful resources' section, to learn more advanced notions, and apply what you learned to other programming languages (python, C++)

One suggestion: the audio recordings have not optimal quality, they could benefit from a cleaning process.

автор: SAROJ S

•19 сент. 2019 г.

First let me thank Professor Ang for all the effort he had put in. My over reaching objective was to get

knowledge about Machine Learning which I read about all the time. I was very happy that I could put to use all the knowledge I had learned years back in linear algebra and statistics . I find that I am motivated to learn more and use it in my business consultancy ventures and build data products for our clients and I will make my younger staff to learn areas of Machine Learning, Neural Networks, Deep Learning and Data Analytics and build their futures accordingly.

Though this course is a one of the first in this field and many newer have been created in the recent past it allowed me to understand the basics rather than using “pre build” libraries and the functions given in them without really knowing the reasoning.

Thanks again to all the mentors who spend their valuable time helping the students.

автор: Dan N

•14 авг. 2015 г.

A fantastic hands-on introduction to machine learning. A very good balance of theory and math with the hands-on aspect. The math, when it goes into calculus, is there for the interested student but is optional.

This course is only introductory and should not be expected to provide anything approaching mastery in machine learning. Such mastery presupposes much deeper math skills than those covered here, along with much greater mastery of whatever language/tool is being used, and deeper knowledge and understanding of many other topics that are either merely touched upon here or skipped entirely. But you have to start somewhere, and this is a very good place to start.

A few of the later modules have some very distressing errors in the material that can cause enormous confusion. Otherwise the material is very solid and well-vetted.

The instructor is engaging and lively and his enthusiasm is infectious.

автор: Abdur R K

•15 нояб. 2017 г.

Incredible course, introduces so many machine learning concepts flawlessly and leaves you excited for more, Andrew Ng is an amazing teacher and it's been said before, but I will say it again, he definitely has a knack for explaining complicated concepts in an easy to digest way. I completed the course in about six weeks (if anybody's wondering, because I know I was), in those six weeks it was about 26 full days of work with assignments and everything (yes I kept track), but realistically you should spread out the information and absorb it over time so that it sticks long term. I already have an engineering background (electrical engineering to be specific) and had taken courses on Linear Algebra, Statistics and Probability Theory so the math he points out seemed familiar, but if you're looking for an introduction to machine learning and the various terms associated with it, this course is for you!

автор: Selvaprakash

•25 июня 2020 г.

Before starting this course, I know only a few concepts in Machine learning but after finishing this course, I know how to apply the most advanced machine learning algorithms to problems such as anti-spam, image recognition, clustering, building recommender systems, and many other problems.

The biggest takeaway for me is that I learned, the amount of attention needed to evaluate the Machine Learning algorithm's efficiency and also how it correlates with the time and effort I should put into the specific system component.

Basic Linear Algebra is a pre-requisite for this course and you will be working in Matlab/Octave. If you know Linear algebra, which is essential for ML and little experience in Matlab/Octave you can finish this course with flying colors. I would recommend this course to get to know the concepts of Machine Learning, as always you should practice a lot to master all the concepts. :)

автор: Deepak S

•30 мая 2020 г.

This was one of the most interesting course I ever took. It was long time pending, I started it but in initial days I was discouraged as I was not able to match the mathematical understanding even I after having engineering background and took sometime to brush those concepts, but after some time and some reading I was able to understand. I was putting hard efforts and after 3rd week it was more difficult in doing programming assignments, which again took some time to learn and the cross this difficulty level. Overall it was great experience and great learning. I can't believe this that I reached till end. The course was ending but my interest and curiosity was increasing everyday. Even sometime I was dreaming the problems I was trying to solve and overcoming those challenges. It was amazing and throughout I enjoyed this course. It is totally mind blowing and addictive one. Thanks Mr. Andrew Ng.

автор: Juan L B C

•14 апр. 2020 г.

Acabo de terminar el curso fue un viaje fantástico en algo que en verdad no conocía, pues no tenía conocimientos de programación (a decir cero), en el primer ejercicio de programación dije hoo!, y comencé a buscar tutoriales de Octave en internet, demore 3 semanas en entregar el primer ejercicio, mientras avanzaba en el curso me instruía más en Octave, hasta lograr nivelar las semana y hoy terminar el curso.

El profesor Ng Anderw, un excelente tutor, y los tutoriales de los trabajos de programación excelentes, Tom en los tutoriales presenta herramientas muy entendibles para realizar los ejercicios de programación, excelente todo, gracias a los mentores por su apoyo, los moleste bastante, felicidades por este gran curso.

PD: Soy graduado de ingeniero industrial hace 32 años, tengo 57 años, y lo que había visto de programación fue, basic, cobol, pascal, fortran cuando estudiaba en la universidad.

автор: David N Y L

•18 сент. 2017 г.

The course provided me a very good concept of Machine Learning. The practice exercise are very good intellectual training for the understanding of the course materials. However, one must put some effort into it in order to get in-depth understanding of the materials, searching on the web for extra info for help to clarify the concept is necessary. Dr. Andrew Ng is good lecturer but a bit shy. However, learning with him is a pleasant experience. Because after this course, I found other similar ML course only repeat the very very basic concept with no details of how is done like that (just use the formula etc.). But this course is only focus on machine learning other that that; like cleaning data, remove unnecessary parameter, deal with missing value etc. are not the purpose of this course. I sincerely recommend this course for those who would like to know the "WHY" to participate in this course.

автор: BAPPADITYA D

•6 сент. 2017 г.

This is the course through which I started my journey with machine learning. I am really grateful to the Machine Learning community and specially Prof. Ng for making this course and the curricular available to so many students including me. I learned a lot from this course and beside this course helps me to think and dive into the deep of ML. Though I completed this course and got my certificate but no doubt I am surely going to miss this course. But I already started my journey with Prof. Ng once again with his deep learning course. Once again, I am thankful to the Coursera community, the Machine Learning community, the discussion forum members and last but not the least Prof. Ng for their tremendous effort, support and providing us the platform to learn and implement the crux of Machine Learning. A recommended course for researcher, self-learning student, industry personnel related with AI.

автор: C S

•29 авг. 2017 г.

This is an exceptionally good course where I learnt the fundamentals of machine learning in detail. The coding assignments "concretely" helped me commit these concepts to memory, give one a hands on feel for problem solving and it's just awesome to see your own work. The course is a little rough at the start. Once the coding assignments become more image based though it becomes easier to understand and visualise things.

The course in my opinion requires some linera algebra background. It is very time consuming, not only is 12 weeks long but coding assignments rarely take 3 hours as stipulated.

The course can be refered back to when looking for information about machine learning as it is well organised and contains high level problem solving info. I feel that I have a better understanding of what coursera was built for and where online learnings place is in the world after completing this course.

автор: Glen D

•17 сент. 2018 г.

Dr. Ng is an incredible instructor! The lectures meticulously lay out the math required and the instructor provides encouraging comments along the way. I was not looking forward to the math in this course but ultimately is was not only straightforward, but addicting! I started working a little ahead, then farther and farther ahead. I actually started wanting to spend all my free time on this, doing all the optional work, and taking the example code and expanding upon it for my own experiments. And now I have finished the course in about a month, and I am genuinely sad it is over. Why couldn't I have been this motivated about my classes when I was a university student years ago? Probably because Dr. Ng wasn't there! Great course. Excellent instructor. Lots of resource materials when you need them. Ex4 is a bit difficult and time-consuming but all the rest were very fast to complete.

автор: Sumit K

•18 авг. 2019 г.

I will never be able to thank Sir Andrew Ng and team Coursera enough for this opportunity. Sir Andrew Ng is truly a genius. I have learned a lot here not just technical skills but also way of thinking and approaching problems in general. I feel like growing up as a person here, and that's how machine learning also works. Isn't it? I'm a bioinformatics student, so I needed this skill. I've already started thinking of on how I can apply these algorithms on biological data to solve problems in genetics. Lastly, I'm convinced by others that this is the best course on machine learning. I'm not in a state or position to review all the efforts you guys have put to make such complicated looking course so simple. For those who are new to machine learning and thinking of doing this course, please do it without any hesitation. Blessings to all of you, and I wish you all luck for your future projects.

автор: DL

•16 июня 2019 г.

Excellent introductory course on Machine Learning, even for people who don't know a whole lot of linear algebra. One can do this course in two ways: First is to look through all the pre-existing code in the test exercises and really understand how all it works and the second is to only focus on the portions that the course expects you to finish. Just finishing this course would not make you an "expert", but this is a very well structured course to get basic concepts firmly rooted in-place. Since this way my first foray, and I am not a good programmer, I was looking to focus on concepts, which this course truly enabled.

Finally, any good course is as good as the teacher makes it to be. Andrew has done an excellent job in taking the most important aspects and simplifying them into bite size pieces. My gratitude to him for the excellent work he has done for the benefit of learners at large.

автор: Yichi Z

•11 окт. 2020 г.

My graduate ml-introduction course professor actually recommend this course. I only focus understanding the exam math and concept at the time. This course gave me a solid refresh and a better general explanation on some of the doubt I can't help to clear before. For the programming assignment, I saw people who give 1 star review complaining that it doesn't teach you how to do it end-to-end. For me, the simplicity and moderate depth actually help me to unveil the mysterious mask of ml, which is a pretty big deal for me. This programming assignment itself essentially just ask you doing one thing, that is vectorize calculation. But that doesn't mean it only teach you that alone. I skip most of the peripheral code. And I think for a start of implementing end-to-end, those peripheral actually give you a good sense of direction what else you will need to go in depth and implement yourself.

автор: Marcel D S

•29 янв. 2019 г.

Absolutely fantastic course. Professor Ng's approach to teaching is a bit more top-down, so you'll get a lot of useful theory and intuition about how the different Machien Learning algorithms presented in this course actually work. Do not expect to be terribly fluent in implementing these algorithms after completing this course, though. I found that the programming exercises really show their age and although I recognize that Matlab/Octave is a nice programming language to implement matrix operations, I still feel that having to use this language is the weakest part of this course. But there is no single course that will teach you everything you need to know about Machine Learning. Considering the huge amount of intuition I've gained, I feel like this "11 week" long journey (it certainly took me longer than that!) was one of the most elevating educational experiences I've had to date.

автор: Mark A S

•8 июня 2018 г.

This class is a basic course in Machine Learning - "basic" as in foundational, not as in "too simple": "basic" as Linear algebra and partial differentiation are "basic"; however deep knowledge of these aren't required for the course. Dr Ng is a superb teacher, and provides everything needed for even novice programmers to acquire a ML foundation. Before taking this, I started watching his older Stanford CS229 videos (still available) and they too are excellent - covering some topics more in-depth, but they did not come with graded tests or programming exercises. Half way through I started a Hinton Coursera course in parallel and quickly exited; I found this course much clearer & more accessible, and the programming work I found to be both rewarding and reusable. After each week I had an intense desire to actually find a relevant real-world problem and apply the current lesson to it.

автор: Alexander W

•16 июня 2020 г.

I give my highest recommendation for this course. Among my other courses within mathematics, statistics and computer science this will be my number one course before all others. Since I grew up, I have admire the universities in USA and this course is a prove by that. Thanks to Professor Andrew Ng and the mentors, I have managed to complete the course within Machine Learning and gain more insight of computer science. After this 11 weeks, I believe, I will mainly remember the course moments of Neural networks, the applications of Logistic regression and all hard work for vectorized implementation in Octave to complete the programming assignments. Besides this and that the course was given online, I will also associate that this course was given during the time of World Pandemic. Once again, Thank you for all advices and the excellent course.

Sincerely

Alexander - Sweden

автор: Jon I

•15 мая 2017 г.

This was a very enjoyable introduction to and overview of machine learning, from the perspective of someone who doesn't want all of the detailed mathematical justification for the machine learning algorithms, but does want to see the nuts and bolts of how they are implemented. For example, we don't prove that we have the partial derivatives of the cost functions (or, even, really justify what partial derivatives *are*), but we do see how they are used as the input to gradient descent routines which let us optimise systems such as linear regression. It is an ideal course to use as a springboard for different aspects of machine learning, such as the Neural Networks course which is also on Coursera.

The main lecturer is clear, and does a very good job of explaining some of the practical aspects of machine learning, and when you might choose the different optimisation techniques.

автор: Dr. H d l H G

•1 июля 2020 г.

I am impressed by the tender and empathic way that Andrew uses to explain the material. It is a pleasure to listen to him and learn with him! In addition I am very thankful to the people that put continuous effort to improve the programming exercises and answer the questions of the students, so that we can walk through the exercises focusing on the main concepts of the course - you all made a wonderful job!

The only thing I would suggest is that you find a way to offer lower prices to students in low-income families. 80 dollars may be perfectly affordable for many Europeans like myself but it would be a lot of money for very capable students in other situations in the world.

Apart from that it is almost unbelievable that these algorithms (videos and code) are offered for free to the whole world over the internet - I feel very lucky that someone recommended this course to me!

- 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