Chevron Left
Retour à Apprentissage automatique

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

166,972 évaluations
42,747 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

18 juil. 2019

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!

15 août 2021

My first and the most beautiful course on Machine learning. To all those thinking of getting in ML, Start you learning with the must-have course. Thanks Andrew Ng and Coursera for this amazing course.

Filtrer par :

426 - 450 sur 10,000 Avis pour Apprentissage automatique

par Subramaniam S

21 juil. 2017

Wow! What I can say! Thoroughly enjoyed a computer science subject with plenty of Mathematics. And, that is at the age of 51. I enjoyed going through each of the Video and the subsequent notes and quizzes. The quizzes took lot of time and needed reviewing the materials again, for most quizzes. I initially struggled with programming exercises. The speed and my familiarity with matrix multiplication increased exponentially and finally finished the last few programming exercises in no time.

For an average Joe, I will recommend this course to take at a leisurely pace, referring to several materials outside. I too was reading couple of books while going through this course. The books really emphasized the learning. A couple of books most suitable to read along with this course are, Machine Learning by Tom Mitchell and Introduction to Machine Learning by Ethem Alpaydin.

This course improved my confidence tremendously as I was not programming hands-on for the past several years. I have not even used any IDE as most my programming experience was on Unix machines using vi editor. This course made a swift change in my thinking and imbibed confidence that I can code complex systems.

par Jian X L

31 mai 2021

The course on Machine Learning given by Andrew Ng has been a nice learning experience and a huge professional step toward my career objectives. I have appreciated the didactic and detailed description of the different concepts and insightful examples. Without going too deep into the mathematical development, Andrew ensured that the lectures are easy to understand.

However, if I had to assign one bad mark, it would be related to the programming exercises. Actually, I have had the feeling that there are too many hints and indications; e.g., the instructions in the pdf file say which formulas must be implemented in a given part of the code, all the pieces of code for plotting, optimizing, etc. were given already.

In practice, I expect that I will have to code a machine learning algorithm (for a given application or problem) from scratch. Yet, as I am not a professional developer, all the clues helped me to get through the exercise quite fast, which was also appreciated.

Finally, the course was time-consuming. Yet, as said by Andrew in his videos, time is a valuable resource that we should dedicate to something that worth it. And Machine Learning is a thing that deserves our time. :)

par Aashirwad

21 oct. 2017

An amazing course! The lecture videos and slides are well-prepared and the concepts are explained by prof. Andrew in a clear and concise way, using neat graphs and plots when necessary. A lot of effort has gone into making the course largely self-contained. There's more focus on the application and practical implementations of machine learning algorithms than their mathematical and theoretical details (although not at all necessary, a fair exposure to advanced Linear Algebra - derivatives of multivariate functions, matrix decomposition, projections, etc. - can help in understanding some of the algorithms better). Lots of tips and tricks are given to help troubleshoot problems that often occur in practice.

The programming exercises are designed so that the student can focus on understanding the essential topics instead of getting bogged down in too many details (nevertheless, it's a good idea to briefly go through the functions and files already written by the staff). The quizzes are also well-designed and help the student recognize important nuances in the subjects.

There's a lot to be learned by taking this course! Thank you, Professor Andrew Ng and Coursera staff!

par Matthew J

2 mai 2017

A really excellent course.

This is the first online course I've taken, so I cannot compare it to others, either on Coursera or other MOOC platforms, but I can say that it was perfect for my needs and I learnt a lot from it. The math content - of which, obviously, there must be a lot of - is very well-explained, and Andrew takes care to require little more than a high-school level expertise to understand.

The programming exercises were slightly challenging, but not overly so, and helped solidify understanding - and hey, there's always that little thrill of excitement when you see your program begin to give you real answers, and you realise that you've just written a program to recognise letters when given just a bunch of pixels.

I didn't use the forums much during the course myself, but they appeared to be very well-supported by knowledgeable and helpful mentors. (Tom Mosher, in particular, seemed to be on-hand all day, every day!)

As to Andrew Ng, the lecturer, he clearly has a deep and extensive knowledge of his subject matter, but his presentation is always kind, enthusiastic and helpful, so I'd like to pass on my thanks to him for making and presenting this course.

par Simran K

9 févr. 2019

For the past few years, all I've been hearing is the word "Machine Learning" being thrown around. In my head, it was built up to be something really difficult that I had no idea about. I wanted to change that, I wanted to be a part of the conversation. This course has truly helped me do that, even as I go through more professional forums about machine learning, I understand the concepts a lot better. It's no longer technical jargon out of my reach.

Andrew Ng really breaks down the course to simpler elements. He brings up layer on layer of abstraction while keeping the students interested with real world application. The presentation, documentation and course assignments are planned perfectly. It's so simple to follow everything, and yet, you still gain more understanding as you move forward.

The community and discussion forums are a great help as well. I'd recommend this course to everyone looking forward to know more about Machine Learning! Don't let the math scare you, it's for your understanding, it's okay if you don't completely follow it. I'd suggest going through an intermediate maths course to relate to it better, but it's okay even if you go without.

par Matteo L

27 avr. 2020

An absolutely fantastic experience from start to finish. A great approach to teaching this material and making the student feel like part of the class right away. The contents were incredibly interesting and the structure of the course was absolutely perfect in my opinion. Andrew Ng. is a fantastic teacher and you can clearly see how passionate he is about this field from the get-go.

I think it's also important to mention you can see the hard work put into constructing the exercises and providing structured information in the resources tab and the discussion forums thanks to the mentors.

The only (small) negatives I'd mention maybe are the fact that random forest (or similar) algorithms were not discussed (maybe there is a reason that I am not aware of) and possibly the exercises tended to get a little bit less challenging towards the end. I think an exercise on optimization using the stochastic gradient descend and the mini-batch gradient descent could have been a nice add to the list of exercises as well.

Once again, overall this course really should be considered a reference in terms of teaching and course structure for MOOCs and courses in general.

par Aaron S

8 mai 2021

I think this course is fantastic for anyone who wants to explore Machine Learning. However, it is not perfect. Professor Ng focuses completely on the Algorithms and avoids going too deep into the mathematical aspect of those algorithms. What does that mean for you? For Mathematicians and Computer Scientists, you are left wanting more. All the technical concepts that Professor skips seem deeply familiar and yet a bit too complex to delve into by yourself. For people with no experience in Maths or Programming, this means A TON OF MEMORIZATION. Being familiar with Linear Algebra and programming is key to completing this course smoothly. If you are not familiar or not experienced enough, then you would have to grind all those basic mathematical concepts in your head as you go along with this course, just to keep up with the deadlines. However, I will say this - if you complete this course successfully with flying colors, then you would have gained skills and knowledge that not even some formal University courses can provide you. Hence, I recommend this course 100/100, but I would rate it ~4.7/5 just because of how it sort of flies over everything.

par Federico L B

9 août 2020

This course was absolutely phenomenal. The main teacher Andrew NG made all the videos and classes so fast and seamless to watch with very interesting examples of real life, as well with important theoretical explanations. The topics, additional contents, extensions and real life cases were delightful to learn. The reviews at the end of each video made for a very fun and interactive way of demonstrating what you just learned in a video class. The reviews at the end of each sections were difficult at times but fair and rewarding when passed. The exercises were very difficult at times but the amount of resources, help from the mentors and the community and the general support to the students was more than enough to help me obtain a 100/100 score on each one of them. The only issue I would have is that the last few exercises were very difficult to understand. This meant that the code did almost everything and I felt like I did very little and that I myself could have not done what the code was showing me. But maybe it is tuned as close to perfection as it is. I can only say thank you and I really hope this helps me find a job as a Data Scientist.

par Kunind S

31 juil. 2020

A really amazing course by Prof. Andrew Ng. He covered all the majorly used Supervised and Unsupervised Learning Algorithms. Now these things are covered by many other courses too, so what's so good about this course? The answer is Prof. Ng's lucid ad easy to follow explanations so much so that, you don't really need to be a wizard or even have a knowledge of College level Linear Algebra or Vector Calculus. Also what additional information we gain from this course is not just the Theory behind ML algorithms BUT also the practical implications! These things are crucial since most of us aspire to be ML Engineers in the applied space. He teaches us ways to debug our algorithms, practices which are industry relevant also how to improve performance of our algorithm, what to devote more time and energy resources to, etc. Just be committed to this course, you'll start loving ML and getting a hang of it in no time! Well it would have been "another" cherry on the cake if Prof. Ng had included other algorithms such as KNN, Naive Bayes, Decision Trees, Random Forests and a much deeper implementation of SVMs, but overall, I'll rate the course a 5/5!

par Dr. M B P

25 juil. 2019

An excellent course. Very well structured and well paced. The quizzes and problems in every week have been extremely well thought of and provide a very good insight into the concepts explained in that week. The barrier of 80% for clearing each quiz and each week's problems is very good and important.

Andrew NG is a very likable person and obviously comes with fantastic experience in the area of AI/DL/ML. There is one suggestion though. It is important for everyone taking this course to have a good understanding of linear algebra. So while Andrew does explain the mathematical concepts of each of the algorithms quite well, I believe he should not underplay the need for understanding that math even though some concepts are advanced. It is certainly important that everyone who takes the course, realizes that it is not just using an algorithm, but that the mathematical foundations underpinning the algorithm are equally important.

All in all I thoroughly enjoyed the course and will be taking up the Deep Learning and AI courses eventually, which Andrew has already developed.

Hats off to Andrew and team for a wonderful learning experience.

par Debangshu M

9 juin 2017

I am only 4 weeks in this course now. I am loving it!!

I must say, this course if very informative. I like the content, which is very precise yet easy to grasp. The course gives enough fundamentals, yet leave some of the finishing work, which is necessary to solve a particular problem, to be done by the students. For example I enjoyed thoroughly determining vectorized representation of the algorithms. Coming from High Level programming languages (I am a .NET developer), I had to unlearn easy way of implementing (For loops) and learn the new (and fun!) way of vectorized solution of Cost Function, Gradient Decent, Logistic Regression etc. Also I had to brush up some knowledge on calculus and matrix algebra from college days. Those are necessary to truly understand the beauty of these algorithm and working out an elegant vectorized solution.

Last but not the least, this is my 3rd Coursera course. This course provides me familiar experience, ease of using the platform, with all the great new knowledge in a concise format. I would like to express my gratitude to the trainer for a great learning experience and such an outstanding course.

par Piyush B

23 avr. 2020

The best thing about this course is that it takes you step by step into the world of machine learning without overwhelming you. The initiation is simple and the complexity builds with each day and week passing by. So when you look at the content you feel intimidated but once you get down to take a day/week at a time it actually unfolds pretty well.

One more thing which makes this course great is the practical wisdom which Andrew provides. Given his vast experience in this area, he is able to explain the pitfalls, the thumb rules, the way to move ahead without getting lost. He is able to connect the dots, provide real life examples and also explains what lies beyond.

The other great thing was assignments which have been designed very well with starter code. You really need to do only the core algorithm implementation but running the completed code almost gave the feeling of implementing a mini project instead of just writing some code snippets. This helped in seeing the code execute from end to end with data visualization, predictions to measuring the efficiency of the algorithm.

Thank you for this course. I thoroughly enjoyed it.

par Peter L

2 avr. 2019

This course is perfect if you are a beginner in Machine Learning and would like to get some gentle yet thorough exposure to the field.

Professor Ng is an enthusiastic teacher who presents the material in a very accessible fashion. He doesn't get too deep into mathematics but teaches you enough to get a sense for what exactly a learning algorithm is doing under the hood.

Some minor criticisms: The programming exercises each require you to complete some predefined functions with a couple of lines of code which, given the extensive instructions, is often trivial - here I would have wished for a steeper learning curve. Furthermore, I would have liked to hear about additional topics such as Decision Trees, Ensemble Learning and perhaps more about the different types of neural networks.

Nevertheless, I warmly recommend this course to anyone interested in Machine Learning. You'll walk away with a deep understanding of several key algorithms, some experience in how to implement them, some knowledge about real-world ML applications as well as a number of very useful guidelines for data preparation, model selection and error analysis.

par Alan J R

21 mars 2020

If machine learning is interesting to you then I would surely recommend this course. Professor Andrew Ng really makes it understandable and easy to grasp, honestly. I come from an economics and finance background, so I had some prior knowledge on linear and logistic regression, but I could easily see myself still understanding these topics and the whole course if I had not studied economics and finance previously.

Also, I learned how to use MATLAB which I consider a very valuable skill. At first I was overwhelmed by the software and how to use it and I tried to run into it head first. However, I recommend taking it slowly at the beginning and really relying on the discussion forums, because everything is there and it is a super active environment. Here I would like to thank Tom Mosher as well, because his contribution to answering questions on the discussion forum resulted in me not having to ask any questions. This course is quite old, but it is also ripe, because so many people have done it before and you can find answers to almost all of your questions. Again, really big thank you to professor Andrew Ng and Tom Mosher.

par Methus P

28 juin 2020

This course is one of the best courses I've ever taken, both online and in real life. This course requires no prior knowledge, meaning that anyone who has an interest in computer science, or particular, Artificial intelligence, can finish this course. I love how the programming assignment was designed and how such great so-called classmates have helped each other along the way. The mentors are very supportive. Before I started this course, I have no idea what machine learning is all about and what it can do. Then prof. Andrew Ng just made it looked so simple that I wanted to write the whole program by myself! The contents of this course are well-selected, not too easy, not too difficult, and of most importance, useful for everyone. I'm currently studying Medicine (I'm interested in BOTH Computer Science and Medicine, but I thought CS could be studied online) and found many potentials in improving the world's healthcare. I never regret spending my time finishing this course.

Conclusion: Highly recommended. You don't need to major in Computer Science to learn this course. It definitely will be useful in any field.

par Jose A G

3 janv. 2018

Awesome class. I took it while also taking Data science and Machine learning at my school. I felt like it was very informative and actually explained a-lot of material better than my school teachers. I like how Ng went above and beyond to not only explain what are the different types of machine learning algorithms available, but also tips and tricks on how to properly use them and also explain industry insight into these problems. The difficulty for me was not too hard, there are many hints sprinkled around some of the assignments, and I like how clear and easy Ng explains the material, and he makes the effort to explain things from the ground up and sets up reminders, which i think is very important. I recommend taking this class as a basis for machine learning, however more study is required to learn about more advance topics in machine learning such as Deep Learning algorithms: LSTM, Generative adversarial neural nets, convolutional neural nets, etc. Take a look at this course's syllabus for a list of topics that are covered and plan your courses towards the complete set of what you want to learn.

par Rick T

2 juin 2018

This is the best college course I have ever taken! I have a MA in Psychology with emphasis on Statistics and Research Methodology and ABD (All But Dissertation) for a doctoral degree, and this class was better than any class I have ever taken. The lecture videos were organized, always on subject and extremely well done. I used to nearly fall asleep in some of my graduate seminars, but had no such problems watching Andrew's lectures. I especially appreciated the karaoke-like presentation of the videos + transcription. I have always done better when having textbooks to go to and take notes. With this approach, I was able to better process the information presented to me. The programming assignments were challenging but not impossible, and the tutorials for each assignments always seemed to provide the necessary clues to find the solution. And on completing the class, I feel that I have gained a significant amount of knowledge of Machine Learning, which provides me a bridge into a new knowledge domain. I highly recommend this class to anyone wishing to learn the basics of Machine Learning.

par Sarang D

17 oct. 2020

An excellent starter course if you want to start building your own ML systems and have a background in math. The course covers the high-level agenda and issues of developing and deploying ML systems in real life, while disbursing an engaging learning experience with a good amount of math and algorithms involved. The programming exercises are very well setup, helping you focus on the core learning for the segment. (Of course, setting up the problems is also a key part of the ML workflow, and you should try to spend time trying to do it yourself.) Centred around GNU Octave or Matlab, the course doesn't cover the applied aspects of real-time ML systems and deployments for server-grade operations, but it does touch upon the logic behind the MapReduce programming model for big data computing. Overall, the course was an excellent experience - challenging at times (rightly so), but fun throughout. Take this course in its entirety if you are looking to develop ML models as an engineer, and especially if you're looking to get up to speed with ML development as a part of product/portfolio management.

par Vincent D

27 nov. 2016

Great class. Much better than most I have attended in person. Excellent instruction, excellent resources, excellent programming exercises, excellent support in the forums, especially by Tom Mosher. Video is a much better medium than live lectures because of the flexibility, shorter segments, ability to stop and study something before going on, and ability to repeat when necessary. Great practice in vectorization. Excellent introductions to the necessary elements of ancillary topics. Bought the certificate. We live in a golden age for learning. Getting this kind of instruction would not have been possible for someone in my situation 30 years ago. I am grateful and looking forward to whatever I learn next.

Took this course to develop skills to work on artificial intelligence and other projects. One previous project described in article at

Very satisfied. I have not been able to stop talking about how good this class is since I began taking it, and will continue to recommend it as the first step for anyone serious about the topic.

par Martin v B

3 mai 2020

The course is well taught with clear examples and a good practicum. It certainly is worth your time looking into if you are (relatively) new to machine learning as it provides a strong basis. The practicum system submission and grading system works very well.

Some words on improvement: * Some of the video and audio quality feels dated as it is recorded around 2011. * When finishing a course I felt left an addition video about what changed in the last decade. * In the practum I sometimes had the feeling that key components were left out, such as creating the hypothese in the SVM. Imho it would be better if the practum scope had a wider scope on the core of the algorithms presented later in the core. * Being a mathematician, I enjoyed some of the backgrounds. However, sometimes I felt a bit left-out because some proofs were missing that aren't not that hard to grasp (such as why the backprop works or why the inner product does what it's suppsed to do while spanning a basis). A couple of extra (optional) video's on the mathematical background of these key ideas would have been appreciated.

par Daniel W P

15 oct. 2015

This course was very nicely done. Dr Ng's videos and narrative were excellent. They were long enough to convey the material properly and short enough not to loose my attention. Assignments were very good as they left you just enough room to fail, learn and ultimately succeed. The quizzes were thought provoking. On the questions that stated "choose all that apply," I would suggest that some form of feedback be provided so that the test taker could know which ones were incorrectly selected/not selected. Perhaps partial credit would be good instead of 0/20 with one wrong selection. Feedback, perhaps an explanation, would be appropriate on all questions incorrectly answered.

I would also suggest a pdf document that showed how to do the various matrix operations in octave with an example or two. This would include basic and advanced operations. I know linear algebra, I just didn't know the syntax in octave and this cost me 3-5 hours over the whole course.

Now off to do some simple applications here at work like spam filter and anomaly detection to start. Thanks for an excellent course.

par Harsh B

2 oct. 2017

This was a very introductory course to Machine Learning, very well taught by a very experienced Prof. Andrew. I will recommend people to take this course to understand the working of various machine learning algorithms conceptually. Although, various proves like Back-propagation, PCA, etc. are not explained in this course, you will never feel like being not able to grasp any of the contents of the videos. I personally watched the videos at 1.25x and it just went as good as it would have been at 1.0x, except for saving the time and completing the course in 6 weeks rather than 11.

Videos are very well organised and the instructor elaborates every section with as ease as any other. In short, I have become a fan of Prof. Andrew.

The only short-coming of this course is that it doesn't have any section dedicated to Bayesian Learning, Knowledge Discovery and few of the other basic topics related to Machine Learning. I will, therefore, request Prof. Andrew and Coursera team to give sometime developing one of the courses containing all the modules that have not been covered within this one.

par Suhas B

7 juin 2020

A truly remarkable course. Andrew is a great teacher and the course brought back memories of my University days.

Now, about the course:

1. Being my very first foray into machine learning, I was not sure as to what to expect in terms of both the content and my takeaway. I would gladly say that the knowledge gain has been very positive.

2. Even if it was recorded more than 7-10 years back, it is still valuable learning. Andrew points in all the right directions and sets up a good foundation. Yes, it does not have every bookish derivation but it sets up the broad spectrum so that consuming additional information from other sources won't be difficult.

3. The programming assignments were fun and insightful. It may be straightforward for a person with prior experience in the field but for beginners, it's a challenge.

4. Finally, the software being used in the course is Octave. For some this may be a downside but I was actually surprised by its very similar approach in both syntax and structure with Python. It will be great learning to self-code all the exercises in Python.


par Ame

7 juin 2020

I want to deeply thank Professor Ng for everything he had taught me in this course. For me, in the beginning, I always knew that the only way to realize the dream of one day pioneering the AI industries and perhaps even help building the world of tomorrow of a Technology Utopia is through actually putting in the work into learning everything from the ground up. As a high student myself, though, these high-level, math intensive college computer science and AI courses like Machine Learning have always been intimidating to step into. Were it not for Coursera's platform and Professor Ng's genuine, intimate, and definitely extraordinary lectures and personality, I could not see myself smoothy entering the field this early and only have my passion ignited hotter than ever. Thank you, Professor Ng, I promise you I will continue down the path I chose, and regardless of difficulties and obstacles, I will push through, step by step, and just perhaps, one day, I will be able to attain that dream I still cling onto. When that day has come, I will remember my first course in ML and you.

par Rene L

7 avr. 2016

Un cours excellent qui traite les principaux aspects du Machine Learning avec une ligne directrice sur la gestion de l'erreur et les différentes techniques qui visent à réduire cette erreur. NG présente les problèmes de réduction de cette erreur avec la gestion du Gradient et les différentes options pour éviter les minima locaux. Ensuite on comprend mieux l'impact des paramètres de régularisation pour la régression logistique ainsi que les spécificités des architectures neuronales. Le cours nécessite un investissement certain en temps pour comprendre le contenu et préparer les exercices sous Matlab mais on apprend beaucoup dans ce cours même sur des sujets plus complexes comme les SVM et les Kernels. Ensuite pour ceux qui veulent mieux comprendre les traitements de l'image quelques exemples (ce n'est pas mon domaine). A la fin NB aborde le Big Data avec Hadoop et la parallélisation des traitements (initiation). Il ne manque que les approches autour des techniques d'Arbres (absence totale) et les réseaux bayésiens ou algorithmes génétiques. Mais c'est un très bon cours