Chevron Left
Retour à Apprentissage automatique

Avis et commentaires pour d'étudiants pour Apprentissage automatique par Université de Stanford

4.9
étoiles
161,922 évaluations
41,532 avis

À propos du cours

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....

Meilleurs avis

SS
16 mai 2019

This is course just awesome. You get everything you wanted from this course. It covers on all topics in detail, helps in getting confidence in learning all the techiques and ideas in machine learning.

AA
10 nov. 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.

Filtrer par :

51 - 75 sur 10,000 Avis pour Apprentissage automatique

par Rajdeep D

31 mars 2018

Perhaps the greatest instructor and the greatest course, I enjoyed it so much I had continued to do it in between my exams and looking forward fto start or deeplearning,ai specialization in a few days

par omri g

11 nov. 2015

Been asked to re-take all assignments *after* paying for a certificate! I wil never pay for a Coursera course again, and I would not recommend my friends to do so

par Tahereh P

26 juin 2020

This course is a very applicable. Professor Ng explains precisely each algorithm and even tries to give an intuition for mathematical and statistic concepts behind each algorithm. Thank you very much.

par Prabhu N

28 mai 2019

Course content was awesome, gave me lot of insights. If assignments were in Python, it would have helped a lot to improve my skills. Anyways I would recommend this course to a beginner who wants to understand the logic behind the machine learning process. Thank You AndrewNg Sir!!!

par Rune F

18 déc. 2016

Fairly good videos explaining the material, probably worth 4 starts. However, the written support material should be improved. IMHO the video should supplement the written material, i.e. it should be possible to learn the material only by reading. This is not the case, so frequent pausing of videos and making lots of notes is needed if one wants to commit this course to long-term memory.

par Anton D

24 avr. 2019

Overall, this is a great course and I learned an enormous amount of information. The biggest issue I had was the disconnect between the course and the assignments/quizzes. Although they had help sections, because you couldn't ask direct questions about the algorithms/quizzes, if you had a problem, you were basically on your own. (At least that is what it felt like.) For example, if you missed a quiz question and couldn't figure out the answer, there seemed little recourse to find the actual answer. In a couple cases, I decided to just take the 80% on a quiz simply because I had no idea what the answer was.

par Herman v d V

15 janv. 2019

My first open online course from Stanford University gave me a lot of energy. As my student years are far behind me (I am 76 years old) it was a discovery to become enthusiast in this new area. And building on my career in ICT, this is a surprising extension on the way systems can help us to develop a better life. Professor Ng is very good in offering in a controlled way many insights in the machine learning - now it is time for me to apply my new knowledge!

par Prateek J

21 janv. 2019

Exceptional. Best course to start learning Machine Learning! Only one grouse though, the exercises are in Matlab and not in python.

par Bayram K

17 févr. 2017

I would rename this course as Programming Octave with Application to Machine Learning rather that Machine Learning. Once you start the course you will have to focus on Octave rather than on ML topics if you want to do programming exercises. There is no degree of freedom in programming. You are provided with a lot of weird Octave codes which you will have to complete instead of writing yourself from scratch. More than 50% of my time was spent in order to learn Octave and understand (guess!!!!) Octave codes.

So, if you really want to learn ML and try it in practice this course is not for you. However, you could just watch the videos whose level is not more that elementary introduction to ML.

par Subham B

30 août 2019

This course is definitely not for beginners.

par zhang w

2 avr. 2018

Very nice course,. Give a fundamental knowledge of machine learning in a clear, logic and easy-to-understand way. Suitable for those who has relatively weak background of math and statistics to learn.

par Hou Z

4 mai 2019

Very good instruction for machine learning, and also very very good for new comers!!!

par Nikhil J

18 mai 2019

It was a great learning experience. All the lectures were in details.

par Aditya K

18 mai 2019

It was a very helpful course.

par MOHAN K K

17 mai 2019

Good Course

par Armen M

9 avr. 2020

THIS IS A REVIEW FOR BEGINNERS

ADVANTAGES OF THE COURSE

When I remember myself deciding whether or not I should take the course, the questions that concerned me the most were these ones.

1. Since I am a beginner in this field, will the course work for me?

2. Did this course get outdated? (For those who don't know, the professor uses Octave)

3. In the end, will I feel like I can do some Machine Learning projects all by myself?

For those who have the same questions, here are the answers for you )

1. Yes, the course will work for you even if you are an absolute beginner like I was at the time (I did not know any linear algebra), It does get annoying sometimes and you feel a lot of pressure at some point of the course, but a hard-working person can surely get through it. Mentors are active and very helpful if you get stuck on something.

2. This question is a big NO for me, here is why: When you are learning something from the very bottom it is super important to learn the hard way, which is the same as the old way. When you come across an easier path, you understand and grasp it way better. For Octave, many tasks require multiple lines of code, whereas in Python it is just one line. You have to do it at least once with Octave to understand how it works in Python.

3. No, you would not probably be able to start a project on your own, you would need some additional source. But, the point is that you now have a general understanding of what machine learning is, what are important algorithms and what are the key points you should consider when doing project. This is the base that every person should have.

DRAWBACKS OF THE COURSE

Although I loved the course, I could not give it 5 stars because it would have been unrealistic. The lectures of the course have an incredible amount of errors. You should be careful. Although all the errors are covered in the Errata section, it still was annoying to open the section every time when I started a new lecture. to check for errors I am about to see.

Another drawback was the programming assignments. They were not explained well and I almost always had to refer to extra Tutorials made by Mentors.

Special Thanks to Professor Ng and all the Mentors!

par Spencer R H

3 févr. 2019

It would be nice if it's taught in either python or R. So I do need to take extra effort to learn octave.

par Andrey

24 juil. 2019

This is a very basic course on Machine Learning. The main drawbacks are:

(1) the material is old and not updated to reflect new developments in this dynamic subject;

(2) the course is oversimplified and adapted for students who have never dealt with maths or programming;

(3) the assignments and quizes are, with rare exception, trivial and test students' common sense rather than the subject understanding; for example, you can pass the final quiz at 100% without reading or watching the lectures;

(4) the course is badly maintained: some mistakes in lectures and assignments have not been corrected for years, even though they have been pointed out in the discussion forum countless times.

While the Ng's ML course is arguably better than many other Coursera courses, it is very disappointing that Coursera and Stanford hardly made an attempt to improve it.

par Roman

12 févr. 2021

I would not recommend this course anymore in 2021 since it is almost 10 year old now and it really shows! While essentially a good starter for machine learning, this course spends way too much time elaborating simple and obvious concepts while completely skipping over most mathematical explanations or more in-depth explanations of the presented topics. Furthermore, this course contains a myriad of errors in the presented slides, complete reluctance for any consistency in variable indexing (even in the same equations), painfully obvious editing mistakes, and the English subtitles are utterly useless. Seriously, a machine learning class with a gibberish as subtitles that was probably auto-generated using machine learning is irony at its finest.

par Rui L

1 oct. 2018

I would not recommend taking this course any more. (2018)

This course is showing its age and lots of concepts simply doesn't apply any more, considering how fast this field is changing.

par Brian L

25 mai 2019

There's one saying in Chinese that says "一日為師,終身為師" which means once being someone's teacher, even just one day, you're the teacher for the rest of his life. Thank you for all your efforts and I really appreciate it. I'll keep working on Machine Learning and hopefully one day I can do the same contribution to the human society as you did.

par vinod

18 mai 2019

Explanation was very good and assignment helps us to understand the real picture. The way course is planned along with octave exercise, Graphs and visualization of data (X,Y) is very good. Very good course who is starting the Machine learning from scratch.

par Ali F

17 mars 2021

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.

par Maksym M

22 août 2018

So much like it. It gave me starting push in this interesting topic. And one important thing that after this course I figured out I need to continue dive into machine learning.

par Akyuu F

8 mai 2019

Excellent Machine Learning Lessons which need little advanced knowledge of mathematics.