Chevron Left
Вернуться к Машинное обучение

Отзывы учащихся о курсе Машинное обучение от партнера Стэнфордский университет

4.9
звезд
Оценки: 166,924
Рецензии: 42,733

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

MN
14 июня 2016 г.

Excellent starting course on machine learning. Beats any of the so called programming books on ML. Highly recommend this as a starting point for anyone wishing to be a ML programmer or data scientist.

ZL
6 дек. 2015 г.

The course is well organised, with cutting edge knowledge ready to use in our information era. And Andrew was really decent with clear illustration and explanations. I really enjoy taking this course!

Фильтр по:

651–675 из 10,000 отзывов о курсе Машинное обучение

автор: Rahul R

27 сент. 2016 г.

I enjoyed this course, its balanced, easy enough for a general software programmer to start off into this math world. One thing I would wish for is a lesson exclusively talking about all the available options for any production needs, and talking about the different jargon that is used out there in the ML world and how we can relate it back to the jargon used in this course.

For example, when I try to use R, I get to know that I need not code to start with and I can use off-the-shelf packages like 'caret' to quickly try different models and compare their performance. But the real trouble I felt is when I tried to analyse their results, as I see too many new words and representations that are used, like Kappa, Specificity, etc.,. I wished these kind of very generic things were also quickly covered in this course.

автор: Srikanth R

11 февр. 2018 г.

First of all, I am deeply indebted to and congratulate Prof. Andrew Ng and Coursera for providing such a valuable course for free of cost. The option of buying the course is also highly appreciated.

I felt that the exercises are designed in a manner that though mathematical operations/calculations required are few, still, they felt tough because they need understanding the problem which is similar to real life problem where a lot of time will be spent on properly understanding the scope and context of the problem apart from mathematical calculations. Thus they help the student prepare for real-life problems. The Quizzes are also of good quality.

The support of Mentors especially Tom Mosher is exceptional and community feedback is great.

Thanks for providing me this opportunity to learn Machine Learning.

автор: Florian R

28 дек. 2017 г.

I highly recommend this course as a starting point for every student found of data science, artificial intelligence and machine learning. Professor Ng is one of the best instructor you could find in a MOOC. He knows how to walk us through complex ideas in a simple manner and, through his own passion, arouses our interest for this enjoyable subject.

You don't need a mathematic background nor a solid programming experience to take this course; just motivation and commitment !

The team of mentors acting behind the scene are also very talented people who are very reactive to answer questions .

Thank you for making this machine learning course for beginners and let's enjoy this introduction to the vast field on AI, which is, according to Max Tegmark in his book 'Life 3.0', the most important conversation of our time.

автор: Rahul K

8 авг. 2017 г.

I learned a lot of concepts in an organized and structured manner in this course that I probably would have spent months trying to figure out on my own. Prof. Ng is one of the best teachers I have had, in spite of the fact that this was an online course. Thank you so much for providing these resources for the world to learn from. This is nothing short of a miracle. Suggestions for the course would be - updating lecture notes for the latter half of the course and maybe more mathematical rigor. If it is not possible to add more rigorous math to this course, links to material that cover the topics in more depth would be nice. Also, can we have a Machine Learning 2 course that would cover some of these topics in more detail plus some new topics? I'd take that course in a heart beat, as I am sure many others would.

автор: Haris M

20 июля 2017 г.

This was my first class in machine learning and in this class I have learnt a lot. Basically before this class I was wondering that there must be some magic behind the fact that machines can learn to do things and then can improve themselves too and after taking this course I now know that all that magic was just mathematics and some basic steps. This course is great and I highly recommend it to those who know nothing about machine learning. This should be your first course in my opinion. Also, do the assignments with full concentration and try to read the code of each and every function to get an in depth understanding of the algorithm. Andrew is really an amazing instructor. This course will make you capable of applying the machine learning concepts to build some cool systems of your own. Highly recommended!

автор: Ryan J

13 июля 2016 г.

Loved this course! It was nice to get a real world comparison of the runtime of perfect mathematical solutions to problems like optimization vs. algorithmic solutions. In my experience, math classes tend to favor solving for variables algebraically, when the calculation of such a solution in many cases apparently takes much longer than the very accurate approximation obtained by gradient descent, for example! Also, I must admit I got a rush from implementing my first neural network, even though it was a lot simpler than I assumed it would be. I thought it was so cool to have built an autonomous program that can read numbers from a pixel array! Finally, I've always found the topic of data compression to be fascinating, so having algorithms and analysis tools for compression is pretty helpful. Thanks, Dr. Ng! :D

автор: Ayesha N

17 мая 2021 г.

Excellent beginner-level course for Machine Learning. Before starting the course, I read some reviews that said the math is too hard and some that said the math isn't in-depth enough. Now that I have completed it, I realize that it's very subjective. To me, the math was mostly non-existent which was fine since I was looking to get an understanding of the concepts before diving deep into the math. There are a lot of equations of course but it isn't math-heavy because you won't know where that equation originated from and how it was derived in most cases. I can see why the course skips derivations and proofs to cater to beginners that do not have the math background to understand Calculus/Linear Algebra. Perfect course for my current needs though. Thanks to the team! The discussion groups are immensely helpful.

автор: Vinay P d L R

5 сент. 2017 г.

Very well explained, and the subject is extremely interesting and contemporary. Made for people with almost no experience. But, it's also great for people who already have more in depth statistical/computational knowledge, as you can simply skip videos whose contents you already know. The programming assignments are also really good at testing your knowledge, and they are very satisfying to complete. They don't require many lines of code, but you really have to understand what you're supposed to do when you write the few lines code that are actually required. I'd like it to be longer and perhaps go a little deeper, but I guess that can be done through other courses (Like Dr. Ng's recently released Deep Learning Course), so this course is complete, as far as it's main purpose is concerned. Pretty much perfect.

автор: Samir S S

11 окт. 2016 г.

I really like this course, specially the way Prof. Andrew Ng explains mathematical intuitions behind algorithms and concepts. I have done many courses in maths including linear algebra, statistical analysis ,signal processing etc, but never seen any professor explaining mathematical aspect behind algorithms, concepts in simpler way. I really like to thank Prof. Andrew for teaching this course so that people like me understands some of the concepts which were confusing to understand in past. After finishing this course, I feel confident in not only in applying algorithm in application but also to improve algorithm performance. Once again, I really like to thank people who made this course possible.

Thanks for you very much Prof Andrew for devoting your precious time to teach this course to students like us.

автор: Stéphane S

10 мая 2019 г.

Machine Learning by prof. Andrew Ng is excellent! In my opinion, it is among the very best courses on Coursera. It is thorough, well taught, and provides extensive learning materials, and lecture notes. Each lesson comes with graded programming assignments, and has detailed instructions on how to apply the knowledge easily.

This is an entry-level to intermediate course, which is very accessible as an introduction to machine learning, and provides a solid foundation in the underlying mathematics. As such, it does not cover hard ML issues. The knowledge covered is greatly useful, and can be readily applied to learn complex models for a wide range of applications.

Those looking for more advanced concepts should consider following up with deeplearning.ai's Deep Learning Specialization (also by prof. Andrew Ng).

автор: Rajeev Y

5 сент. 2020 г.

I listened about this course from one of my friends during my graduation days and Since then I always wanted to complete it, I tried once earlier and couldn't complete the deadlines, but this time I completed well before the course end date, I am glad to overcome my mistakes. This course has formed my basis of ML and its concepts along with practical implementations has helped me in my job. Quizzes require good insight about the algorithms and thus encourages to follow course material carefully, following course material is enough to complete quizzes and practical assignments. I would like to thank course Instructor and all mentors for all resources and help provided through the course. Special thanks to Coursera for making this course as an open course to help all students learn ML and its applications.

автор: Alexandre B

19 мар. 2020 г.

It was an honor to complete this course by Andrew Ng. The scope of the course is well defined and the professor respects it by not spending more time than needed on some maths concepts such as calculus. Being someone who is familiar with calculus I was pleased to see that the course focuses on machine learning and does not waste valuable time teaching calculus. That is not to say that there is no maths in the course because there is but the level is fairly accessible even if you don't know what calculus is. I would have appreciated a little bit more hands-on exercices between assignments but that is a subjective opinion. The course has a lot of theory but every week you get an assignment to validate the theory. I would recommend this course to anybody who wishes to get started with machine learning.

автор: Christopher P

22 июля 2018 г.

Excellent overview of Machine Learning. The goal of this course is to explain the main ML algorithms from a practical, intuitive perspective. This is accomplished using real-world examples, and the key ideas and techniques are reinforced by Matlab/Octave exercises. [No prior Matlab/Octave experience is assumed, and in fact, this course allows one to pick up the basics easily, if needed.] The key mathematical results that underlie the algorithms are presented, but there are no rigorous derivations or proofs. Some differential calculus and linear algebra background would be helpful, but it really isn't necessary to do well in the course, and to apply the various algorithms successfully. Finally, I found the notation consistent and clear throughout the course, and this helped to tie things together.

автор: Karan R

21 июня 2016 г.

The best course I've taken on Coursera so far. This was the first ever course offered on Coursera, by the founder himself, Andrew Ng. He's a great instructor, covering topics right from the ground to the sky. I'd say the implementation is in OCTAVE instead of popular languages like R/Python, which could have improved upon a lot for learners. But since Andrew has focussed this course upon beginners, I think OCTAVE is apt.

The assignments were relatively easy as most of the implementation (ground work) was done, only the main functions were to be implemented. But yes I learnt a lot from the way the assignments are designed. You create a digit recogniser just by being through this course.

I would recommend it to all learners who are beginning with Machine Learning or Data Sciences to take up this course.

автор: Denis O

16 февр. 2019 г.

Great introduction to Machine Learning.

It gave me exactly what I was hoping for: at the end of the course, I feel like I can look at a typical machine-learning / AI / neural network program and understand how it might work (of course, a specific program mightn#t work that way, but I#d know one way that it could work, and the type of results, predictions and flaws to expect.

The programming exercises were very helpful because they forces us to think and to refresh our knowledge of linear algebra. I would probably have made them a little bit harder - not that they were easy for me at all !!! - in the sense of ensuring that we had to always program the critical code for the key topic of a given lesson. But maybe that#s not realistic.

The lecturer is phenomenal - very clear, very precise, very engaging.

автор: Abdullah S

25 окт. 2017 г.

Just Excellent, everything about this course is just fantastic, beginning with Prof.Andrew, passing with his passion for the subject and his motivation to really make you understand everyword he says, he is keen on delivering all this expertise and this alone is a fine quality, the course is well organized and the quizzes and programing assignements are to the point and are a very good exercise, I just felt the course needed 2 small videos one addresssing the differences between linear regression, logistic regression, SVMs and Neural Networks and another video exciting people by a small example of machine learning on self-driving cars (very small programming assignments to help excite people and give them an-overall idea)

again Thanks to Prof.Andrew and all who helped me find my hobby and passion :D

автор: Xiang L

10 июля 2017 г.

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. It was so great and very helpful of implementation.

автор: Lokesh N

15 июня 2020 г.

Immensely helped me to start off with Machine Learning. Every concept is deliberated beautifully by the instructor. He has great expertise in the field and understands especially on how to teach or guide the novices and think from their perspective. In this regard he delivers what is concretely required. This course bridges the gap between applicability of the algorithms and mathematics behind it without deeply diving into the latter. If someone isn't well versed with Linear Algebra,Calculus and Statistics they might find themselves impatient for superficial explanation in this regard. This course would have been ideal if it's worked out with the current language in demand and bit more practical. Overall, In my opinion I would definitely recommend this course for all the beginners.

Heartfelt thanks!

автор: Divakaran K

21 окт. 2017 г.

Andrew Ng's teaching methods go a long way in imprinting the concepts very clearly in our minds and makes us understand each and every concept perfectly before moving on to the next. Perhaps he is THE best instructor out there in the field of machine learning. The exercises have been designed in an absolutely error-free way that helps us to quickly learn from them without any hassle. That, combined with the small small instances where Andrew talks about his practical experiences makes us more confident in our course progress.

Just a small suggestion : It would be great if Andrew took these classes with python too. Maybe you can add it as additional(optional) exercises in the lectures. It will go a long way in making everyone feel that they are actually coding industry-level stuff with this course.

автор: Mohamed H

22 авг. 2019 г.

Very well taught class by Prof. Andrew Ng, he explains everything in a really cool way by showing the benefits and applications of a concept first before diving deep into the formulas. I read some reviews mentioning the high focus on math but I experienced it differently. Coming from a Computer Science background it was easy to follow the mathematical part even if you're not very strong in math like myself. You just need a little linear algebra to follow and understand everything, as the hard proofs aren't presented. One last thing, maybe this course should be in python now, however, Matlab was very easy to start and it gives you more of the theoretical understanding compared with python. This is due to the intuitive mathematical syntax of Matlab which is very similar to the mathematical formulas.

автор: Paul L

16 апр. 2020 г.

I am a student in engineering and i had a lot of notion of Machine Learning already. I learned in class and myself so i already knew the majority of the concepts. But i have to say, i am glad to have taken this class because i realised that some algorithms i thought i knew were way better explained and that finally, i didn't know them well. Also, after having done several Machine Learning projects for my school, i ended up using libraries without knowing exactly what the algorithm did. Now I know.

Only "negative" point: maybe the using Matlab in the course is not such a good way to practice nowadays. Everybody use Python or R today, so i think it would be good to adapt this class by letting the student choosing the language (even if i realise it demands a lot of work to rewrite all the exercices).

автор: Alex K

27 февр. 2019 г.

Brilliant introduction to machine learning. Shows the student that there is *so* much more to the field than just the fancy, hot topic things like neural networks and self driving cars. There really is a simpler and fundamental grounding to these things and it turns out that we can achieve amazing results with just a bit of clever matrix algebra and calculus.

Very good pace - not too fast, but can be sped up using the video controls. Well structured - Earlier topics are referred back to later in the course so that you're continuously reinforcing knowledge you've already gained. The programming exercises made me think, but weren't so challenging that I got frustrated or stuck.

Thanks Andrew hopefully when I'm further ahead in the field I'll be telling people this is what really got me started!

-Alex

автор: Anas

19 окт. 2018 г.

What's great about this course is that it not only teaches about the theoretical aspects of Machine Learning, but it also gives you a chance to get your hands dirty and apply what you learn on real life applications. The course provides programming exercises which are a great way to demonstrate some of the cool stuff you could build with the knowledge that you gain throughout the course. What's more, the way the material is provided makes it possible for inexperienced people who have no background in Machine Learning or Mathematics to get a pretty good understanding of the way the algorithms work without delving too deeply into their most intimate details. I thoroughly enjoyed every part of this course, and I would definitely recommend it to those who are just starting out with Machine Learning.

автор: Brandon B

10 сент. 2017 г.

What I loved about this course is that Andrew jumps right into the details without a lot of fluff that other lecturers use to fill the time. The mini-quizzes that pop up during the lecture videos help to solidify the material being learned. The graded quizzes are just challenging enough to make sure you did actually comprehend the lectures. The programming assignments were fun, challenging, although I did notice that there was quite a bit of hand-holding when it came to setting up the algorithms and executing them. A lot of the heavy lifting was already done, but it was just enough to get the point across by allowing the student to think about how to implement the main algorithm being studied. Overall, I do recommend this course to anyone interested in getting started with machine learning!

автор: Swagata C P

7 янв. 2019 г.

Really good course.... Enjoyed learning this although Machine learning being a alien topic to me. Understood every chapter, lessons and all the topic. It helped me to realise that machine learning is something in which I can do my career. As it is just the start of my career this realisation was important for me.....Only one thing that I didn't understood from the course is that how to make our own features for any image input or so, but I am sure that it has cleared my other topics so much that I can get the information from other sources as well and will be able to understand it quickly from the point of view that any one should have for a particular problem, which I learned from this course.... Thankyou for the course and for making such knowledge available to us just at the click of a mouse