Chevron Left
Вернуться к Машинное обучение

Отзывы учащихся о курсе Машинное обучение от партнера Стэнфордский университет

Оценки: 149,457
Рецензии: 38,079

О курсе

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....

Лучшие рецензии


Nov 11, 2017

Great teaching style , Presentation is lucid, Assignments are at right difficulty level for the beginners to get an under the hood understanding without getting bogged down by the superfluous details.


Aug 19, 2017

Very helpful and easy to learn. The quiz and programming assignments are well designed and very useful. Thank Prof. Andrew Ng and coursera and the ones who share their problems and ideas in the forum.

Фильтр по:

401–425 из 10,000 отзывов о курсе Машинное обучение

автор: Winson L

Oct 02, 2018

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

Aug 18, 2015

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

Dec 15, 2017

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

Aug 16, 2017

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.

автор: Iain M

Sep 06, 2015

Andrew Ng's passion for the subject of Machine Learning is obvious and infuses every lesson. His wide experience in the field allows him to enhance the video lectures with tips and examples that help him to explain what are often quite complex concepts.

The lectures are very well organized, clearly presented and, although they cover some very advanced techniques, are obviously aimed at those new to Machine Learning. The programming asignments include clear and detailed instructions. In fact, if I have one criticism of the course it is that those instructions may actually be a little too detailed - occasionally involving little more than copying and pasting code from the instructions into Octave rather than writing our own scripts.

I really enjoyed this course. If you are a beginner, then I think you'll find this is an excellent introduction to Machine Learning. If you have a little more background knowledge then this course will help you consolidate and build on that knowledge.

автор: Marco C

Jan 04, 2017

A fantastic opportunity to get a global overview of one the most exciting topics of data science.

Lectures by Mr Andrew Ng are well structured, perfectly declined in both illustrating the need behind each development and in rigorously explaining its logic. He drives you through a step by step path and always helps in understanding the overall context with clear examples. Each video is stopped now and by a not graded quiz aimed to check you are perfectly in line with the concepts. Grades are obtained through the questionnaires (five questions each time, you need to get no less than four correct answers out of them) and a programming exercise in Octave/Matlab. Especially in order to well deal the programming exercises, the discussion forum and the kind availability of the course mentors are a great resource!

In conclusion a seriously challenging course, that will take lot of your time but it's definitely worth! Many thanks Coursera and really thanks and congratulations Mr Ng.

автор: Xinguo W

Oct 08, 2016

Just completed the course myself and I have to say this is a great course for anyone who wants to get a comprehensive understanding of Machine Learning. First of all, the content of the course is very well structured. It covers a lot of machine learning algorithms and also includes a lot of practical applications. Professor Ng is very gifted in teaching and he can explain some difficult topics in very simple terms. I also found he is very engaging and the quick questions inserted in the middle of the videos are very helpful to keep the students focused on the lecture. The programming assignments are at the right level of difficulty, and I found the instruction for each assignment works like a great summary of the corresponding materials. Didn't use their discussion forum much, but for a couple times I used, the mentor was able to respond in a very timely manner. Overall, this is a great course and I am so happy to be able to take it myself. Thank you, Professor Ng!

автор: Nikhil G

May 30, 2020

I came in with no background in linear algebra/octave/MatLab, and machine learning always seemed like this black box to me. This course had some challenging sections, but is totally doable for someone with a limited background, if you're willing to put in the work. The lectures simplify the concepts into little, manageable pieces, and the programming exercises reinforce the concepts learned from lectures (these exercises also have detailed tutorials to help those out that aren't familiar with the programming languages used in the course). Dr. Ng has an amazing ability to teach without jargon, and being overly technical. His final video, and mannerisms throughout the course, make it clear that he is a compassionate instructor that really wants to inspire his students to learn these concepts. Some of the ideas behind machine learning are now much more clear to me and I look forward to learning more, and using more current implementations of machine learning e.g. w/ python.

автор: shockwave2000

Jan 10, 2020

Very helpful course that taught me the basic principles behind the field of machine learning and its various applications in the world. Mister Andrew did a great job teaching, and his love for the topic made the whole experience even more exciting for the student. The videos were short and straight to the point with various questions and quizzes that constantly held the attention of the student and helped him keep his focus, while the programming assignments gave a very good intuition about the practical use of machine learning principles in real world problems and helped the student gain a first- hand knowledge about machine learning application programing. The tutorials were very useful and the mentors replied to my questions very fast, giving me the help I required while working on an assignment. I thank Andrew and the mentors for helping me embark on a journey towards the world of artificial intelligence, machine learning, robots and technology. A great course indeed.

автор: Zoltan K

Jan 26, 2018

A practical and engineering minded introductory/overview course to machine learning. It has set the scope of the subjects right, it was wide and deep enough to be able to understand the basic ideas, how to attack the problems, the type of thinking needed for solving problems with machine learning, how to plan the work, where to spend more time/energy, how to implement efficiently, how to measure performance and progress etc. The choice of Octave for the programming assignments proved to be excellent. It was fast to grasp its concepts and very efficient both at writing the programs and running them. The videos are transcripted, the slides were well explained, they are available for download, the resources section contained the summary of the lessons etc. All in all there's been a lot of progress from the first Coursera courses many years ago. The Coursera app (Android) was surprisingly good and useful, I preferred using that for watching and I used a browser for the exams.

автор: Digvijay D

Apr 30, 2020

I've been utilizing my free time to learn the concepts of machine learning and their applications and successfully completed the Machine Learning course offered by Stanford on Coursera.Professor Andrew Ng is a great teacher and this course is both challenging and satisfying. The course is of 11 weeks and some weeks have two sets of lectures. So there is a little more effort required in this course than any other ML courses but is great value for the time spent.This course gives a grand picture on how ML works by focusing more on the basic concepts as opposed to focusing on specific components like programming language/libraries which most of the ML courses available on the internet suffer from.What I loved the most about this course is how the instructor(Andrew Ng) always mentions the correct way of doing things and how things are done by a few people in industry. Overall this is a very good course which gives a solid foundation in the basic concepts of Machine Learning.

автор: Guilherme C d A S

Jun 14, 2020

Fiz o curso em 2020. Sou estudante de Economia (já tinha uma base boa de estatística), tinha um conhecimento básico de programação e conhecia um pouco de Machine Learning. Na minha opinião, Andrew Ng tem uma boa didática e é muito bacana aprender com alguém de renome na área. O curso serviu para dar boas noções de ML, tornou o assunto muito mais tangível e deu um panorama interessante. As tarefas de programação me tomaram um bom tempo e tive algumas dificuldades mas consegui completar tudo com alguma ajuda. O programa utilizado é o Octave (ou Matlab). Não foi difícil me adaptar a esse ambiente. No entanto, me parece que a escolha de software pode ter ficado um pouco ultrapassada, talvez seria mais interessante em Python. Não sei dizer o quão difícil é adaptar o código e as bibliotecas. De qualquer forma, isso não afeta a explicação dos modelos de ML ou mesmo os conselhos e boas práticas apresentados. Não tenho base para comparar com outros cursos de ML disponíveis.

автор: Kevin S

Jan 11, 2019

The positives of the course are: Material presented was clear, and concise, not a lot of fluff and thus very efficient. The pace was just right for absorbing the material and to write some notes. Besides the excellent delivery of the material, what really stands out about this course for me and why it is so awesome is that there was strong coverage of methods to use to avoid possible pitfalls (underfitting, overfitting, types of problems that each learning method is suited for, how to decide on spending extra effort gathering data or not, finding which component in a pipeline is worth trying to improve and avoiding wasting effort on components that don't improve overall results). Other courses will often present a range of different methods but have little or no guidance on how to use them correctly and avoid pitfalls. Anyone can use a tool but often it can make a big difference in efforts and results if it's used correctly.

The negatives of this course are: none :)

автор: Himanshu G

Apr 25, 2020

Thank You Very Much, Andrew Sir. I feel the scarcity of words to express my gratitude and thank you to you, Sir and the Coursera. The course is very well designed and enables a novice like me who has little prior exposure to the field of computer science to understand the concepts of Machine Learning, pass the review exercises and programming exercises. I think a little improvement could be if more videos related to Mathematical concepts (for example something relevant to Support Vector Machine) relevant for this course are included in the course or authentic links or (esp. Mathematical) resources are provided which students can refer to sharpen their mathematical concepts which are relevant for this course. Thank You very Much, Coursera for providing me financial assistance. I guess without the financial assistance, it would have been hard for me to enrol to this course because I earn very modest from my current job. Thank You Very Much Coursera and Andrew Sir.

автор: Josh F

Nov 25, 2017

Excellent course. I have no background in math (save for a good understanding of linear regression) but professor NG's teaching is so good I was able to follow along quite well. I knew I would eventually be working in python, so I personally elected to forego the assignments in matlab/octave and found a resource online that had all of the finished assignments in python which I simply studied and commented until I understood them. I would recommend this approach if you are simply interested in getting up an running quickly and know you will be using python. I would also recommend watching the videos at 2x speed to save time.

The only criticism that would be possible to levy would be that he did not go deep enough into the math in some areas but on the other hand, I may have been lost if he had. I was really appreciative that he was encouraging enough to say "it's ok if you don't fully understand the math, it will work regardless". Solid course, absolutely amazing,

автор: Tianhong Y

Nov 24, 2016

Prof. Ng is such a good teacher that he explains things in a proper way to make you understand.

He has a profound understanding of the details and derivations behind the knowledge and conclusions. If you have a relative background, you would have a chance to think about the knowledge in a deep way. If not, you can still get the main idea and be able to use it, and you know what is lack and where to learn it.

Overall the lecture notes and videos, the quiz and assignments are all good, full of thought about how to make students follow the course and understand better, as well as exercising with real applications.

I didn't realize that the machine learning course was the first one on Coursera and Prof. Ng is the founder of this wonderful platform, until toward the end of the course. No wonder the quality of this course is so good. I learned a lot and would recommend it to anyone with a good math or physics background and want to learn Machine Learning seriously.

автор: Daniel A R

May 01, 2017

As this course is rated, and according to the lots of opinions written about this course, I can only add a new congratulations remark to their creators. Andrew Ng is not only a genius who masters all the contents, he is also really didactic and teaching. Andrew is able to boil the more complex concepts (e.g.: neural networks) in simple explanations with very illustrative material and an updated approach to real examples and use cases like (autonomous drive or Photo OCR and text recognition).

I would like to thank you the great support provided by Tom Mosher in the Discussion Forum (this is one of best forums I've checked in the different MOOCs and the main reason is the fantastic work done by Tom who gives quick and intelligent answers focused on making you think and learn about the questions or doubts you ask).

I think this course is a must for all those who are into data engineering, data processing and especially Machine learning or Artificial intelligence.

автор: Bob H

Nov 09, 2018

Excellent course, Professor Ng teaching approach works very well for complicated but fascinating subject. I always found his lectures to be clear and concise regardless of the difficulty of the material. I also found the programming assignments to be a valuable tool to enhance understanding of the material.

At the conclusion of the course I feel I have an excellent grasp of the topics that were presented in this course. I have found additional materials on the internet (e.g. course syllabus from CS 229 that Professor Ng teaches) such as papers and books covering aspects of Machine Learning. I am now equipped to continue my learning using more advanced material. I am now rereading the Master Algorithm by Professor Domingos and I find that I now have a improved comprehension of the material presented in the book.

The only thing I could wish for is additional material and assignments for other learning approaches, e.g. Markov Chains, Naïve Bayes etc.

Thank you!

автор: Soumen S

Oct 23, 2019

I learned a lot from this course. I recommend any beginner (like me) or a professional in this field may try this course, because

1. I have learned types of mathematical learning

2. I have learned how to prepare myself to proceed step by step to solve an ML problem in future, instead of just jump into the problem and try to solve

3. Not less not heavy but Andrew has shown me the actual mathetics behind the algorithms.

4. I have learned to find a bug in a model and how to approach it to debug the same. Those parts are the best parts of this course I have enjoyed.

6. I learned how to decide the hypothesis, how decide the polynomials, how to decide parameters, how to decide threshold value (instead of guessing[Classification Problems]), how to choose and/or synthesis features and many more.

5. The last thing I should mention, Andrew taught me how to evaluate an algorithm with a simple number(real number) whether it is working fine or not.

Thank you Mr. Andrew Ng

автор: Jason J D

Jun 25, 2019

This is probably the best Machine Learning course out there. The course covers up everything in Machine Learning, right from the basics to the complex parts. Even though I had studied some Machine Learning at college, this course helped me learn many new concepts that I was previously unaware of. The instructor Prof. Andrew Ng is very good. His explanations and examples are simple, yet cover up all the details. The course structure is very good and the assignments are well prepared. The course also gives a tutorial on Octave / Matlab basics and helps develop your logic and coding skills in the same, through programming assignments. The course material like the Lecture Slides are very useful as well. This course not only helps you learn Machine Learning, but it also helps you develop the intricate details used to implement Machine Learning in daily as well as industrial applications. I would recommend this course to anyone interested in Machine Learning.

автор: Keiji H

Aug 18, 2017

You can learn everything about machine learning from the very basic things to the now omnipresent product recommenders and spam removers such as Amazon's and Gmail's. The course consists of lots of short, 0-15 minutes, lecture videos and programming assignments, so you can see them at your intermediate times though you will need a certain amount of time to complete each assignment, which would greatly help you understand how they work and make you feel like you could make your own algorithms yourself. Don’t worry about the programming environment. You can see how to install it on your computer, either Mac or PC, in the course. In my case, I’ve completed all using Online Octave, in which you can run your program without installing anything on your machine because it runs online though the computing power you can use is limited. Anyway, I truly appreciate Andrew Ng, the creator of this course and the co-founder of Coursera, to give this great opportunity.

автор: Tan M

Oct 30, 2016

It has been a great learning experience taking this Course. I am currently taking an advance version of Machine Learning in my school, and this course on Cousera has definitely provided me the basic and essential knowledge in tackling more advance machine learning problems in school.

To the mentors, thank you for answering my questions that i have posted in the forum. Just a little feedback, i hope that there will be different mentors tackling on different weeks' problems (Spreading the workload ..maybe). In this way, answers to some of the questions can be more detailed.

And i also hope that some days the errata in videos can be corrected even though these are minor that students do not need to refer so much to the errata page while watching the video lectures.

Overall, the course is great and i will definitely recommend this to my friends! I hope that one day Coursera will have an advanced version of the class! (etc. Machine Learning II)

автор: Brian T S

Feb 13, 2018

Professor Ng provides an extremely accessible overview of AI techniques. The math does seem a bit imposing, but anyone with a background in pre-calculus or higher should be able to "get it" if they sit down and work it out. I took a similar course at the University of Texas in the 90s and this was presented in a much more understandable manner. It might have been beneficial to work on a complete AI programming assignment at some point, or at least accomplish more of the coding, as most of the assignments required completion of the more trivial aspects of the technique. Also, I was a little surprised that search (tree traversal) was not addressed. Maybe that's too old hat, or covered in a graph course. There were some frustrations with Coursera not working correctly (unable to submit assignments due to broken URL forwarding, broken Latex rendering which is still not 100% working), but I really like the site when it works. High marks for Professor Ng!.

автор: Tom M

Jan 31, 2018

I reviewed many courses before taking this one and I'm sure that I made the right choice. This course covers the underlying mathematics of how the various learning algorithms work. Understanding at that level is essential to designing and debugging machine learning systems rather than just applying rote techniques or blindly calling library functions in an ML framework.

I found parts of the course challenging as I'm not a great mathematician but I'm very glad I persevered. The pace and structure of the course were just right. I've just got one tiny gripe. I suffer from multiple hearing problems so at times I needed to turn on the captioning. The problem with automatically generated captions is that they struggle (i.e. get wrong) precisely the same words that I am struggling with, so for me at least, the captions were useless.

Overall, I would describe this as the defininitive 'must-do' course for anyone looking to get involved with ML applications.

автор: Joseph M

Feb 08, 2016

Fantastic. Andrew Ng is a naturally charismatic teacher with a knack for anticipating issues which his students may encounter and assuaging them before they become sticking points for later understanding. By their nature, online courses cannot benefit from students asking questions of their instructors so it is doubly important that instructors be aware of areas which may confuse students and take anticipatory action to avoid this- this is only one of Ng's strengths. Beyond this, Ng is simply an enthusiastic instructor whose passion for his subject is contagious. He also conveys a genuine sense of understanding the student's process of coming to grips with more difficult portions, often explaining what has confused him before (though, given his expertise, one may wonder just how much these areas actually give him difficulty). All things considered, the biggest disappointment is that there are not more courses available with Ng as the instructor.