Chevron Left
Вернуться к Машинное обучение

Отзывы учащихся о курсе Машинное обучение от партнера Стэнфордский университет

Оценки: 167,112
Рецензии: 42,785

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

24 янв. 2020 г.

Perfect foundational overview of the topic with challenging exercises, at least for someone who left university over 20 years ago and has since then not done much with his skills in Linear Algebra ;-)

16 мар. 2021 г.

I want to thank you very much for such a great course in any aspect especially from professor Ng . I just want to suggest that it would be great if there was a final project for the end of the course.

Фильтр по:

626–650 из 10,000 отзывов о курсе Машинное обучение

автор: Rohith R

17 июля 2020 г.

This course is definitely one of the best out there to take for a beginner in ML, especially since most of it is free. If you have prior knowledge of ML and how things work, this course is probably more of a refresher. However, if you are a beginner like myself, you will gain a significant amount of understanding of how various ML algorithms are implemented that you would not have otherwise. This course would have been AMAZING if it was taught using Python but it was still a great learning experience (although I can tell I'm not a fan of MATLAB). I am so happy I took this course and am confident to say I have come a long way from being a novice to being competent. A HUGE thanks to Prof. Andrew Ng for creating this course. I hope to take more of his courses in the future!! He just makes the hardest concepts sound a lot more simple.

автор: Vimal B

21 авг. 2021 г.

Hi, This is my first course on Coursera. I am from Mumbai, India. I am really impressed overall by this course in general and by Andrew Ng specifically. The very fact that you guys are giving the course for free is immense service to humanity. In the last video of the course, I was expecting Andrew Ng to push the audience to go for certification purchase. I thought he will say at least once like "having done all the hard work till now, it would be better if you go ahead and purchase the certificate". I was amazed beyond my belief that he never pushed for it. Hats off to you guys!! You are doing great! By the way, I have purchased the certification and I am proudly flaunting it. Also, I am looking forward to courses that would help me implement the algorithms in Java/Python for practical use. Please suggest if any. Thanks, again.

автор: Pranav S

1 июля 2020 г.

This course has to be one of the most magnificent course that I have ever taken. I spent sometime on other online courses on machine learning but did not complete them because the tutors didn't connect with me, the way Andrew did and that has been one of the primary reasons why I love this course and as a result of which the subject Machine Learning as well. Behind every successful student there lies a passionate teacher guiding him towards success and Andrew has had that influence on me. Thanks a ton for making our lives more exciting and for encouraging us to keep dreaming big. This is the best course and I highly recommend it to everyone who have prior programming experience and have interest in Machine Learning. Cheers! Thanks to Coursera too for providing Financial Aid which helped me pursue this course in the first place!!

автор: Fernando N

13 июня 2018 г.

Great fundamentals course. If you know your fair share of mathematics and optimization concepts you will definitely be more comfortable, but Andrew Ng makes great strides in providing conciseness for these complex topics and algorithms. I am an Industrial Engineer and so I have come in to the course with the mindset and understanding of these optimization topics, but was new to many of the applications within machine learning. I have taken a few other machine learning courses, and in retrospect I believe prospective students should start with this course. If you are not familiar with linear algebra, Andrew goes through a refresher, so even that is covered. Only difficulty in the program is the programming itself. I am a self taught programmer, so that didn't stall me, but that is the only thing I could see holding students back.

автор: Venkatesh C

4 авг. 2021 г.

I​ cannot thank Prof. Ng enough for simplifying such a complex topic into such an easy delivery style that one is highly motivated to get through the maths even as it gets more challenging with every passing week. I took this course not to become a data scientist but to get enough insights into finding applications for machine learning in my area of work and there could not have been a better course to do that with. The summary slides say it all - it was not just the techniques but really the insights into how one needs to manage a larger program, the kind of pitfalls to avoid, how to track progress, the metrics one could use to pivot from one idea to another - hugely invaluable. I just would like to conclude with a huge thank you to Prof. Ng and the support team that does a great job of responding to the questions and queries.

автор: Patrick B

27 дек. 2020 г.

The material might be a bit old, the video and audio quality not living up to today's standards, and Octave is a tool many won't consider as a starting point in machine learning. However, the material is presented in a way that it's easy to understand and motivating to continue working on the course. The way the graded programming exercises are implemented is just great; the system gives you a fast feedback and works flawlessly.

The single complaint I have is the presentation of the neural network algorithm. This is probably not only the hardest thing to understand, but also the hardest thing to teach, so I'm complaining at an extremely high level. But maybe the videos could be improved to get the main points a bit better across. However, with the tutorials and forums, it's possible to figure it out anyway. So five stars anyway!

автор: Dennis F

22 мая 2021 г.

This course exceeded my wildest expectations. It explained not only what machine learning is and how it is used but also how it works under the hood. Andrew Ng explains everything in simple-to-understand language that doesn't make you feel stupid. He is so self-effacing despite his stature in the ML community.

I had some problems with MATLAB Online on a MacBook Pro platform. It would routinely crash or run out of memory, requiring restart or even reboot multiple times over the course of a couple hours.

I also sometimes took longer than expected with the programming assignments due to confusion over terminology, especially the meaning of the various indices used in vectorized matrix operations. Back-propagation being the toughest one for me.

Overall, I learned a ton and it was a most satisfying experience that I highly recommend.

автор: Sauro S

1 сент. 2020 г.

Thank you Andrew Ng for this great course. I had a bit of research experience with regression analysis, neural networks and PCA, but this was my first "real" introduction to the fascinating world of machine learning algorithms, and I am greatly satisfied! I found the course to be really well structured. it begins with "simple" linear regression models, and progressively builds up to more complex / elaborate systems. The subsequent lectures not only present new models, but also gradually uses the accumulated knowledge presented previously, in addition to pointing towards important aspects to consider when designing / tweaking a real-world model. Again, thank you very much. I can't wait to learn more about machine learning techniques, and to apply them to my own research work in biomedical engineering and human motor control.

автор: Juan A L

11 июля 2017 г.

Great course with a lot of useful machine learning concepts. Good balance between theory and practice. Andrew Ng guides adequately each one of the lessons with good examples and fruitful suggestions either for the better comprehension or for the better application in a professional/practical concepts application. Some other fine machine learning algorithms could be presented here (decision trees, bayesian networks, hidden markov chains, genetics algorithms, etc), nevertheless it is understandable that the course has a specific scope either in a group of topics either in time, so no regrets about not finding more machine learning subjects here, it represents my new learning backlog for the future. Very satisfied with the material, the course structure, the exercises and the teacher. I will recommend it to my engineer friends.

автор: Daniel N

11 апр. 2020 г.

Excellent course. Very good introduction to numerous facets of ML. I supervise and generally work with a group of data scientists, data engineers, and ML engineers for one of the biggest companies in the world, but my background is more tailored to translating customer requirements, owning the vision for product development, filling in gaps, removing blockers, etc. - this was a huge leap forward for me in terms of speaking the language. Huge thank you to Professor Ng. Only complaint is the lack of emphasis on the actual iterator variables used in highly involved summation algorithms. At point, it was even stated that the iterators (i, j, k, etc.) and the total counts (n, m, etc.) were not that important. THEY ARE, pay super close attention to which one is which is Professor Ng walks you through it, and it will help a lot.

автор: Daniel G F

20 нояб. 2016 г.

Amazing course completely worth every second spent on it. I was enrolled in a similar subject in my University and I decided to unsubscribe from it and do some other stuff to get the credits as it involved so much time due to its really long practices (mainly due to documentation, dealing with Python peculiarities and collaborating with really junior or low performing students) that it was impossible for me to get the time to properly work on it, as I'm also working and doing some other subjects.

With this course here I have been able to learn the same concepts and work with them in practice too with much less overhead, focusing on the most important parts and concepts for each topic.

Most importantly, I this has served me as an introduction to the Self Driving Car Engineering nanodegree that I hope to join soon at Udacity!

автор: Michael L

12 июля 2021 г.

I found this course to be a good introduction to machine learning. The theory behind the algorithms is well explained and presented, even if you don't have a highly advanced background in mathematics and computer science. However, I do believe those that have a basic or weak background in either mathematics or computer programming may struggle a bit. As such, I encourage anyone thinking on considering this course to brush up on linear algebra and/or computer programming courses - if this is not something you do regularly - before considering this course if you want to fully embrace the concepts presented throughout. The only issue that I really had was that the assignment sheets for the programming exercises seemed outdated or not 100% consistent with what was expected in the code, so perhaps they should be revised.

автор: Alec W

17 янв. 2018 г.

Andrew Ng is a fantastic teacher. He preempts questions, and he doesn't shy away from important nuances just because they are difficult to teach. His course provides thorough knowledge of machine learning on a theoretical and conceptual basis. The course does not provide very thorough knowledge of actual implementation, mostly because the heavy lifting of the coding has already been done in the assignments. This is a course on Machine Learning, not on Python or Octave, so I'm glad he devoted the lecture time to the main topic. That said, the course will go much faster for those with some computer science knowledge and coding experience. If you're planning to take this class, stick with it through the end. The coolest applications are there, and the tough parts in the middle are necessary for them to be fully appreciated.

автор: Arpit

26 мар. 2020 г.

I think this course is really amazing. Dr. Andrew has really designed this course for a really broad audience. As someone working with numerical methods and algorithms on a daily basis, I found his use of simpler terminology very effective to help those without a mathematical background understand easily. Moreover, the examples he used to explain the algorithms were usually pretty relatable in the current world scenario.

The quizes were well-designed as a quick check of the knowledge learned.

Assignments were quite good to gain understanding of the implementation details.

The support from the moderators in the forums was great too. Although, I never had to post a query. Usually, a quick search too me to right thread.

I would highly recommend this course to any who wants to gain initial familiarity with Machine Learning.

автор: Mahak B

18 июля 2019 г.

Machine Learning by Andrew NG was luckily my first ever online course ever. Through this course, I learned various machine learning algorithms and got a chance to get hands-on experience on them as well. Andrew very greatly and simply explains some complex machine learning algorithms in this course and covers almost all the required points in the lectures itself. It is a must course to take if you want to develop an interest in this field or want to explore the same.

Kudos to Coursera for laying out the course in such a systematic manner. I really liked all the notes, lecture slides, graded quizzes, in lecture quizzes and all the programming exercises. Also, the active group of mentors really helped in learning.

Overall, I look forward to taking up more courses on Coursera in the near future for more such experiences.

автор: Jörg S S

23 мар. 2020 г.

General: The course can be done by very beginners. If you are familiar with statistics and calculus you might have a bit more fun.

Positive: • Every topic is explained in a very fashionable manner, therefore you'll progress fast. • A very important part of the course is the help in fixing errors, designing a mashine learning system and so on, that can safe you a ton of time in real life.

Negative: • Content wise the course lacks some topics like reinforcement learning. • The last 3 weeks or so, quality droped a little - i.e. no summary pages as in the beginning, uncorrected spelling errors in coding assignments etc.

Conclusion: Andrew Ng is a great and very humble teacher and it was a honor to learn from him. I feel prepared to apply what I learned in practice, which is obviously a good sign. Strong recommendation.

автор: Fernando O A

11 дек. 2018 г.

Excellent course! Andrew knows how to teach a subject that is not very trivial.

He uses a language that requires an abstraction of mathematical concepts, but without requiring a deep knowledge of formulas and calculations. He also manages to demand the least possible advanced knowledge, but it takes a little more dedication in programming and reasoning, achieving the goal of being understood through the preparation of well-elaborated exercises.

The Octave programming language is very simple and allows the dedicated effort in the exercises to really focus on understanding the algorithms and not on learning a new language.

Congratulations to Andrew, Coursera and others involved in the preparation of this course. I recommend everyone who wants to understand the basic concepts and algorithms related to Machine Learning.

автор: Oei L

9 мар. 2017 г.

Excellent! I'm amazed at how much I learned. If there's is an Academy award for online courses, this would win the "best picture" award (and I wish there is to help highlight well-developed courses). Lectures, tutorials, resources were great, clear and most importantly, effective in communicating concepts, algorithms and developing the necessary programming skills (and I'm saying this after trying many others and giving up mid way). I have no doubt that this course will continue to stay relevant and evolve as this field as well as online delivery format progresses. I'm very very thankful for having access to such wonderful training material, made possible by founders of coursera, which I understand to include Prof Andrew Ng. I'm also very inspired by how coursera democratizes access to courses from top universities.

автор: Siyabonga H

29 июля 2017 г.

I am deeply grateful to Professor Ng and all collaborators and contributors who have invested their resources into making this course a huge success. It has been very meaningful to me as a lover of learning new things and acquiring knowledge. I took the course to get my foot in the door of ML/AI. I one day hope to be an academic researcher in either this or another related field. I cannot thank the community and course faculty enough. The concepts presented are explained very clearly, pitched at an appropriate level, and the course is always engaging and thought-provoking. Thanks again.

As others have pointed out, it may be worthwhile to perhaps consider offering Python versions of the programming exercises alongside the Octave/MATLAB ones, given the ubiquity and industry preference for Python on ML implementations.

автор: Philip R K

3 апр. 2019 г.

The practice with applications in the programming assignments in this course was by far the most helpful aspect. If anything, I would have liked to have more programming assignments, and for some of them to be more challenging in terms of having the student build tools from the ground up (though I know most are available in Octave and Mathematica libraries). I also would have liked more mathematical derivations/proofs at times, but I recognize that those were arguably outside the scope of the course. Andrew did a great job explaining concepts clearly and the forum moderators apparently put in exhaustive effort to answer students questions and creative a very useful reference for other users. Thanks for putting in the time to create this great resource, especially writing out all the programming assignment content!

автор: Gerald A S M

21 апр. 2018 г.

Creo es el mejor curso con el que se puede comenzar en esta ciencia, 100% recomendado, no solo aprendes los conceptos, también los aplicas en octave/matlab, lo cual te da una idea de como comenzar a desarrollar en otros lenguajes, cuesta un poco adaptarse al ritmo del curso comparado con otros cursos en linea, pero vale la pena el esfuerzo, a las personas interesadas en el curso les recomiendo adelanten lo que puedan para que lleven bien el tiempo especialmente en la semana 9, la cual considero para mi fue la semana que mas tiempo me consumió, sin embargo el tema es bastante interesante para los que nos gusta tener una pequeña visión de como pueden funcionar algunas de las tecnologías de los gigantes en la red, de igual forma les recomiendo lleven sus propias anotaciones en una cuaderno de repaso siempre es útil.

автор: Juan F C C

11 дек. 2017 г.

Where to start? This course is one of the best I have ever taken in my life:

Andrew explains every subject clearly, I was surprised of his talent when teaching, a really admiring and uncommon thing. How come that most of my professors were not nearly close?!

He tackles every aspect of a subject you may wonder and also every aspect you may not but that is critical in practice. Indeed, the course gives a good deal of insight into the practical matters. The programming exercises are highly recommended, don't be shy.

I took this course for personal interest and got to feel so motivated that I felt joy when progressing, when rushing to meet deadlines and when completing it (I am sincerely sad it is over now). I am extremely satisfied with the experience this course was, I'm going to miss these past three months.

автор: Ryan D

3 мая 2017 г.

A very helpful and informative class! I don't know why it's listed as an advanced level course. Even with my limited Machine Learning knowledge and absence of experience with Matlab/Octave, everything was easy to grasp. Concepts were presented well. The summarized readings of the videos and lecture slides worked well as references. I would have hated having to go back and watch multiple times when I forgot something.

One thing I would have liked to see more of are the programming assignments. The automated submission system worked well and was helpful for making sure I had each step of the assignments coded correctly. I started doing the assignments before I took the quizzes, due to how well they helped me learn the material.

Would definitely recommend to anyone interested in learning more about Machine Learning!

автор: John R

31 авг. 2016 г.

A very good introduction to the subject that moves at a good pace but doesn't make such big jumps that it is difficult to follow. Andrew Ng presents the subject clearly and gives some good insights.

One of the most valuable aspects of the course are the assignments where actual code is developed and worked upon. The code provided gives a good starting point for people to move forward and develop their own applications as they progress further.

I would like to thank Professor Ng very much for producing this course and making it available so easily. Also to the people working with him to mentor those participating on the course.

The course has very much wet my appetite for machine learning and I am now keen to pursue the subject further both through developing my own applications and learning more about the subject

автор: Ricardo G

31 янв. 2021 г.

I've learned a lot in this course and I hope that I'll be able to apply this in my career. For those of you contemplating on taking this class, don't be worried about not knowing linear algebra or some other concepts that Andrew may mention, what you should know is that there are many resources out there (even the forums have some good material) that will help you move forward. Finally, I have to say, that after watching Andrew's last thank you video (I may or may not have shed a little year), I'm a bit bummed out because my journey in this class is over. However, rest assured that my learning journey in ML is not over and I hope to learn more in the coming years. All in all, I definitely recommend you do this course if you want to learn about ML and want to apply it to some real world problems. Thanks Andrew!