Chevron Left
Retour à Apprentissage automatique

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

4.9
étoiles
140,851 évaluations
35,631 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

NN

Oct 15, 2016

It's a good introduction - not too complicated and covers a wide range of topics. The programming exercises are well put together and significantly help understanding. The free Matlab license is nice.

CC

Jun 20, 2018

good course; just 2 suggestions: improve the skew data part (week 6) and furnish the formula to evaluate the number of iteration in the window from image dimension, window dimension and step (week 11)

Filtrer par :

201 - 225 sur 10,000 Avis pour Apprentissage automatique

par Jaspinder S V

Aug 08, 2015

Awesome course for beginners.

par Mulat Y C

Feb 14, 2020

Machine Learning

Data Science

par 梁驰

Feb 08, 2020

喜欢吴恩达教授的课,讲的非常的好!教授很谦虚!赞赞赞!

par chandan k

Jun 06, 2019

Great course to study!

par Eugene M

Jan 04, 2019

Very useful course!

par Joy F Y

Aug 07, 2015

It's very useful

par Pavel K

Jun 06, 2019

A great course.

par Hacker O

Jun 17, 2019

very good!!

par Stephen M

Jun 05, 2019

Very useful

par ylfgd

Jun 06, 2019

very good

par THIERRY L

Jan 04, 2019

Excellent

par Saiful I A

Aug 07, 2015

Very Nice

par Vivek K

Dec 13, 2018

Awsome

par Lichen N

Aug 28, 2019

深入浅出

par Armen M

Apr 09, 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 Jerome T

Mar 06, 2019

I like the course very much. One point where it could be improved are the assignments: it is really nice to be guided and to have a big part of the programming prepared but the drawback is that many times I didn't feel in control of what was happening. For example, that was hard to know basic features of the implementation (is this data a row vector? a column vector?) since I didn't decide it. This leads me to spend quite some time on trying to fix simple problems. In short, I wish I had felt more "empowered" during the assignments.

par Saideep G

Apr 09, 2019

Very well made, well paced. Better than majority of college courses. Some errors do pop up midway through the course that should be addressed. It can be frustrating to push through these issues sometimes but they are the only thing keeping from 5 stars.

par MAHESH Y

Apr 09, 2019

it is one of the best course for beginners in machine learning, the only thing it lacks is its python implementation. If there is the python implementation of this course then no other course is better than this one

par Doreen B

Jun 09, 2019

Well explained, at the end of this course you will understand the subject and hold coherent conversations about it. Matlab implementation relatively simple, maybe too much so. Highly recommended course.

par Mohd F

Nov 08, 2018

There is a lot to say about you Andrew sir but in few words - "Thank you very much for teaching us the ML concepts in such a beautiful manner "

par Mehdi E F

Mar 19, 2019

Very instructive course.

Thank you.

It would have been great to get an OCR exercice at the end.

par Nils W

Mar 23, 2019

Great course, but the sound quality is quite bad.

par Sai V P

Aug 05, 2019

Better upgrade from matlab to Python

par Alexey M

Apr 10, 2020

Well, this course has at least 3 undeniable cons:

1. It exist;

2. It offers certificate for reasonable and affordable price;

3. It has "Stanford" in title.

Still, it could be improved in many ways.

First of all, it has poor video and audio quality, maybe worst I've personally seen in MOOC. Dear Stanford! Professor Ng is cool, give him room with windows, 1080p camera and microphone! Even less famous educational establishments can afford it.

Second, subtitles are also poor. English is not my native language but I dropped subs in my language after first try. English subtitles also have a lot of errors: many words are garbled with homonyms; I'm lucky to have some background in course theme and without it I would be completely lost trying to understand what's even going on.

Third, I think this and many other courses are suffering from past teaching system and experience. What is classical teaching system? There is lecturer narrating and writing on the board, sometimes showing something; there are students listening and taking notes. Well, still better than "watch your master working, nothing will be explained" method (still present in some cultures), but what century it is? XVII, XIX? We are learning "Machine Learning" via Internet, and watching materials being hand-written in process? Seriously? Even basic HTML skills in this days are enough to show formula, where you can get reminders of it's every part by simply moving cursor on it (Wikipedia is one example). After two weeks break in learning it will be very effective way to remember fast "what's going on, why this formula is so big and what the hell is that squiggle", and learning process will be improved greatly.

Little more HTML effort, and there will be way to live demonstrate curves, planes and how different parameters affect them; it will be possible to let students experiment while learning which is great improvement for learning, memorizing and understanding.

These are just examples, but hopefully my point is clear.

Quizes are too easy, solvable with "hey he just said that" method and some intuition, not require deep understanding.

Programming assignments are well prepared and explained, but programming materials amount is not enough for me.

Thank you professor Ng for your efforts!

par Eric S

Jun 06, 2018

This course needs to be severely updated and fixed. It is mostly kept alive by the amazing community of mentors, in particular, Tom Mosher. Without Tom, I would have gotten extremely frustrated with the weird quirks that come about during assignments. One important piece of advice: if you can do assignments in an Octave environment such as GNU Octave 4.0.3, I'd strongly recommend it (Althought it tends to crash ofter, so save, save, save!!!).