Chevron Left
Retour à Apprentissage automatique

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

165,581 évaluations
42,411 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

11 juil. 2021

I've learned a lot from this machine learning course. A huge thanks to prof. Andrew for guiding me throughout this course, and also Coursera for providing me with such a platform to learn this course.

30 oct. 2017

Great overview, enough details to have a good understanding of why the techniques work well. Especially appreciated the practical advice regarding debugging, algorithm evaluation and ceiling analysis.

Filtrer par :

326 - 350 sur 10,000 Avis pour Apprentissage automatique

par pat

15 févr. 2021

I'm glad I didn't pay for this one. The answers in the quizzes are not correct. I checked them. Also, they don't tell you until week 2 that you will not be able to use any strings in your files in Matlab and Octave, everything has to be a number. I'm not sure this is useful to anyone. Bec the answers are wrong in the tests you won't be able to pass any of the quizzes, I got 60% on them. I retook each of them 6 times. I even checked the answers on Octave. Whoever wrote the quizzes did a poor job. I also did not understand any of the homework labs. I tried doing them and there were no instructions and the scripts did not work. Unfortunately, I can't recommend this class. It looks like the person who did the videos spent a long time on them, but whoever wrote the quizzes and homework did not check anything. Really sad. They could have made some money off of this one. Just sloppy.

par D M

14 juil. 2021

Has a lot of content, but just like you would experience in a university, the delivery comes in the form of:

1. Instructor talks at you for many hours

2. Now go take a test and see how much of what the instructor said stuck.

The course does very little to encourage understanding and comprehension of the material, so if you actually want to walk away with the ability to apply the material that has been presented, you are going to have to look for resources outside this course to complete your understanding.

A​lso, the homework problems frequently feel like they are from an entirely different course. Referring back to the videos for help offers little to no help in understanding what is desired in the homework.

par Richard L

5 oct. 2021

​I have tried three times to purchase this course unsuccessfully. My credit card is valid and It works for other purchases. Coursera customer support is totally unhelpful. Coursera should treat its paying customers better. I am a subscriber to Coursera Plus and before that I paid for a number of courses. Up to this point, I had been reasonably pleased with Coursera.

par Sabahat

13 févr. 2021

In the beginning there are notes to explain each video. In the last few videos, there are no notes and it becomes impossible to keep pace with what the instructor is saying as the slides also don't mention the key points that one is interrogated upon in the quiz. The assignments are also extremely tedious and I at least did not learn much from them.

par Maarten d s

7 janv. 2020

the quizzes were very good but the programming tests were badly made and not well enough explained.

some problems can come from having Dutch as first language others from the continuous task of just translating the formula given into a formula for the programming. or just plain old copy paste from the instructions of the file itself

par James L

6 févr. 2021

I sleep every single time when I am watching the webinar only for 5-10mins.

Need more visual aids and examples. Also the voice is so calm, nothing exciting to learn.

If you want to fall sleep fast, I recommend you watch the videos.


par Miguel C C

6 juil. 2020

Lioso y muy mal organizado. Las preguntas de los test hacen referencia a otros temas y la puntuación es injusta. En general, muy decepcionado y voy a pedir la devolución del dinero.

par Gosforth

10 juil. 2019

My feeling is that the author of this course has no idea what is "Machine learning" - I have the impression that he repeats slogans which he does not understand.

par Lorenzo V

23 mai 2019

No math, purely intuition and drive through formulas not demonstrated. You can't improve after this course because you don't really know why you did what you did

par Golam R

24 juil. 2021

​The course is designed based on Matlab/Octave. But Python is more intuitive language for this field. So i lost interest on this course.

par Abdullah D K

18 févr. 2021

This is not a course, more like listening to the people who talks about machine learning and then writing your feelings about them.

par Romie C M

8 juin 2020

A good set of questions contain only one best answer and that is in measurement and evaluation.

par Uri Z

9 sept. 2016

Very basic and superficial course. Apologies each time derivatives need to be used.

par Ruslan Z

23 oct. 2020

theory is intuitive and ok but rated program assignments are just waste of time.

par Rishi A

4 déc. 2019

Locked assignments are really frustrating.Why to wait till a specific date?

par Siddharth K

1 avr. 2020

Python should have been great language for this course.

par Vivek P

4 oct. 2021

Course not updated in ages.

par Aly E

10 juin 2021

I have to say Andrew did a pretty wonderful job in this course. I was a person with a very nice software development experience but never had to deal with machine learning. The last time I had to deal with calculus, algebra or mathematics in general was about 7 years ago (in Arabic, and having to deal with that in English is another story), thus I had approximately zero mathematics knowledge. Before this course, I attempted different approaches into this field but throughout them, I would either fall in a valley of philosophy or I would have to stop every few minutes and check the mathematics behind what's just happened.

The way Andrew approached the content in this course makes perfect sense to me (and I assume, to anyone with similar background). He's not the kind of teacher who'd plot complicated things onto the board and tells you that you should use it, instead, he would build the components of everything bit by bit until it makes perfect sense. He also has a good estimate of how hard/complicated something might be/seem to new comers and thus he instructs you throughout the course to be gentle on yourself if you don't get it at first.

Also, the vast majority of quizzes and programming assignments in this course put you in situations where you have to deal with tricky confusions in order to work things out and thus try to make sure that you have a deep understanding of what's going on.

I also like the quality of the content provided in this course. Andrew didn't just tell you "hey, here're the algorithms and that's how you use them, go use them", instead, he dedicated a decent amount of effort trying to explain how to choose which algorithm and when and why, and how to "not depend on gut feeling" but instead diagnose and debug different situations you might find yourself in.

Judging by earlier approaches I attempted before this course, I believe that it might've taken me a very long time to obtain the knowledge provided in this course.

One minor draw-back of this course is that unlike the first half, the last few weeks don't have reading recap after each video session. Another one might be the fact that the weight of this course (in terms of time and effort needed to complete something) is not equally distributed across the weeks (one programming assignment took me almost two weeks to complete, and two weeks in the course took me one day to complete).

par Augustin L K

22 sept. 2021

(1) I​ think the lecture material has to be revised: My suggestion is this: to make the lecture clear use 3 by 4 matrices to describe or explain each steps ( this will ensure that the student can solve the problem manual and therefore use any language to code). The summation over i, j, k with the training example m ; makes less pratical. there are many repetition which can be removed as well ;

=​> Based on my coding experience, it is very good to keep the mathematical generality aside for clarity purposes; making the lecture very easy ; Really there is a total disconnection between the developped theory ( equations) and their coding ; it makes it hadrer ;

I​f one can solve or translate the mathematical equation manually then the programming assignment will be easier

(​2) you start each topic in a wonderful way by providing sweet examples ; however , in this case, there is not a general formulation of the example that will help easily the student decided about the next example different from what you gave: In order words : when you talked about aircraft engine on anomalous algo; you did not clearly (in words) say what are the characteristics of a problem which will be identical to the aircraft exaple

(​3) About the assignment, there is a huge dark side : the student has to complete only whatever it is asked to; however in practice the student will have to developped more than what he is asked as assignment, It is therefore important to present fistly important to tell the student if there are some libraries developped in the current language used in the lecture ( in this case Matlab) : in other words:

l​et say , the in the << exercise>>, the main code is ex3 where there are lines of cod ( which the student will have to write in practical scenario as well : This ex3 is not concern by the assignment, which is good BUT at least say a word about this: Let the student know if in practice he will have the task to write this main file ( ex3), will be better

T​hanks , your lecture is good in the sense that it connect two main sides upon which the ML is made : mathematical side ( by this I mean the useful resulting equation to be used ) and the pratical formulation and application of this in an algorithm


par Malcolm N

11 janv. 2016

My CS friend recommended me to take this course to learn more about how to use data in business, after he heard that I wanted to program an app for food. he warned me about the great deal of math involved (mainly linear algebra). me being a physics/engineering major I naturally got even more excited (it turned out that he was right, and it would also be a huge plus to know multivariate calculus, and I can see myself struggle with the concepts had I not studied both these topics to bits in school). incidentally, this was my first online coursera experience. I can tell you it will be life changing experience. No longer do I have to physically travel somewhere to listen to lectures or hand in assignments, nor download lecture notes off of the school server. This is a 24/7 always on always available service, with the best TA's to answer your questions if you get stuck on homework assignments and quizzes. Everything in the coding assignments tests your knowledge of the course lectures and is designed such that you can complete it in the shortest possible amount of time while reaping the maximum amount of benefit. It is "easy" sense does not require you to grind through mundane things like looking for your own training set data or writing code to plot and visualise the data, but it is "hard" in the sense that very often it takes an hour (or more) of studying the lectures and thinking to figure out how to solve the problem in the most efficient way as possible which often involves writing a single line of vectored matlab/octave code. It is more of an overview of the most important topics in machine learning, but will be a great springboard to go in depth into each aspect of it. Lastly, Andrew often offers wonderful insights into the day to day of machine learning professionals in his lecture videos, so I would advise watching every single minute of them to get the most out of the course instead of aiming to race over the finish line (which can be tempting at times when the deadline approaches)

par Daniel D

10 juil. 2018

This course is vital. People can do machine learning using out-of-the-box tools like keras,, theano, tensorflow, and do amazing things. But to understand what's going on internally, to understand what it takes to get things to converge fast and to perform accurately and to be as useful as possible, to understand various types of networks and new discoveries later on, it really takes a good, healthy, rigorous foundation at least in very simple calculus, matrix algebra, back-prop, stochastic gradient descent, linear and logical regression, and such. If you try to forge ahead and get stuck or cannot come up with a way to build a proper model later on, you may find yourself giving up or returning to the material provided in this course. Andrew Ng did an excellent job teaching this. Even so, I heartily recommend watching views from others to get unstuck or to reinforce what you have learned--to make it more concrete. And do all the assignments aiming for 100% on every one.I found myself viewing youtube videos from many experts and found most of them extremely interesting and exciting. By getting several people's perspective, I feel I was able to learn the material better and more easily. Of course, it helps to have a math background, too, and I received my BA in math long ago from Fresno State with an Applied Math option and a Physics minor. It was a joy to return to my old math stomping grounds.If it takes time to get through, that's OK. Sometimes it helps to let the material marinate or let your brain marinate in the material. Then if you're like me, you might come to the place where you start to get on a roll and decide you need to put everything else aside and focus on finishing *this* course to perfection. And it can open the door not only to interesting work but to other interesting and worthwhile certifications.

par Tejas R

26 mai 2020

I found the Machine Learning course has a good structure, excellent teaching instruction and a perfect pace for working professionals. It covers a wide variety of topics/techniques in Supervised and Unsupervised Learning.

Professor NG has an excellent way of teaching any given topic. He covers all the fundamentals or building blocks to a particular topic quite well before putting it all together to demonstrate how a learning algorithm can be built. Each week has some quizzes and programming assignments you need to complete. For someone who is new to this entire topic, I found the quizzes and programming assignments sufficiently challenging. The quizzes test the basics covered in each topic, whereas the programming assignments give a hands on experience in how to write parts of Machine Learning algorithms.

I was also impressed with the course resources. There are numerous resource links available if you are interested in reading more into any topic. And the course forums are quite helpful in case you are stuck on any particular problem. Just going through the forums’ FAQ is bound to help you gain further insights into the course topics.

I am a working professional from whom it is difficult to dedicate sufficient time to enroll in a proper university course. I found the pace of this course well suited for the amount of time I was able to spend in a week.

This course does not cover any one particular topic in too much depth. It is structured to introduce you to a wide range of topics in Machine Learning and can set you up with the proper introduction and background if you wish to pursue any of those topic into further depth.

Overall, this course was very fulfilling and I would highly recommend it to someone who is looking for a course which introduces you to a wide variety of topics in this domain.

par Pat L

30 nov. 2019

This course is an essential tool. I am beginning on a long journey of machine learning I hope will end at my ultimate goal of securing employment in the field of natural language processing and deep reinforcement learning. Starting completely from scratch, I began this journey by getting text books on the topics and attempting to follow along. Many of the basic learning algorithms, which seemed so daunting at first, were explained to me in a way that allowed me to fully embrace and understand the topics on an intuitive level. This course is the essential entry point to anyone wanting to truly understand the mechanics of machine learning. The mathematical concepts are broken down in a way that is truly intuitive and easy to follow. Additionally, Andrew Ng is a world class instructor. His manner, presentation, and encouragement from, at the time of this review, 8 years ago is evergreen and invaluable. He sincerely believes anyone who puts the time into learning this material can accomplish great things in the world. This course was inspiring. I was so engrossed with the material that I completed all 11 weeks of course work within 5 weeks. My only issue is the use of MATLAB/Octave in this course. All the materials I have read state that these languages and applications are widely not used in the field anymore though at the time of the course development, I understand the inclusion. Perhaps an update to the course that allows for the programming to be done in Python or R would be beneficial, but once you get the hang of MATLAB the programming exercises become easier as the course moves on. My sincerest and most heartfelt recommendation goes to this course for anyone who has an interest in opening the door to their own journey into this field.

par Alistair W

6 janv. 2019

I worked for a start-up specialising in AI and rules based software that aims to learn how attorneys review contracts to extract key data points (e.g. clauses, parties, names, dates, numbers and text classification). Although I worked in sales / presales and as a domain expert for legal (being an attorney), I always wanted to know more about the technical side of what we were trying to achieve. This course provided my first proper and thorough introduction to machine learning, not only the coding concepts but also the underlying maths. It's been really tough going through the course, but that's down to my rusty maths (I have a maths A-level (i.e. pre-University maths to American readers)) and hadn't practised maths in around 12 years before completing this course. Similarly my coding skills had become rather rusty. All that said, the quality of teaching, forum support and coverage of this course has been great. I've had to read around quite a bit, mostly where certain topics were introduced without first zooming out to explain what the overall algorithm is trying to achieve. However, these issues were easily overcome given the course is well supported on the forums and similar topics are covered elsewhere on the internet given their prevalence today. I thoroughly recommend this course to anyone interested in AI and machine learning. I am looking forward to completing the Deep Learning specialization course as a result of this course, and will also be completing FastAi in tandem to get both a bottom up understanding (as was the case with this course, and will be the case with the deep learning specialization) and a top-down understanding (as will be the case with FastAI). Thanks to the team at Coursera, the forums and Andrew Ng!