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.
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.
por Mulat Y C•
por Mewada A J•
best experience of learning
por chandan k•
Great course to study!
por Eugene M•
Very useful course!
por Joy F Y•
It's very useful
por Pavel K•
A great course.
por Hacker O•
por Stephen M•
por Thierry L•
por Saiful A•
por Vivek K•
por Nazir A Z•
por Lichen N•
por Sam C•
I'm not crazy about online learning. There are certain aspects of classroom learning that online learning can't give. But as far as online learning goes, this course is probably about as good as it ever gets.
Prof. Ng gives very clear expositions of the fundamentals of machine learning. Anyone taking this class and completing the assignments will be ready to apply machine learning to at least some simpler real world problems and should be in a position to quickly pick up more advanced techniques for more complex problems.
The exams are fair (although I think some more work could have been done to make many of the questions less ambiguous). The programming assignments can be a time sink, but I don't think they could have been any shorter and still give valuable practice in using the techniques outlined in the lectures.
Students who already have a background in linear algebra or the basics of data analysis might find the pace of the class in the early units, where Prof. Ng deals with linear regression, to be rather slow. But if you can get through those early units, you will definitely find yourself dealing with new material (and occasionally appreciating the initial slow pace).
Octave/Matlab is the only language in which the assignments are accepted. I personally would have voted for python. But Prof. Ng spends a few lectures telling you all you need to know about Octave/Matlab, for the purposes of the course. (To save time, I would advise that you spend a day or two learning the language on your own before starting this course. That will allow you to stay that much more ahead of the due dates. But maybe that's just me.)
One word of warning is that, as a friend of mine said after taking a machine learning class in a traditional university classroom, this material makes machine learning accessible, but also takes the "magic" out of it. If you are impressed at how Netflix can be so good at recommending new movies for you to watch, well, after taking this class, you won't be impressed anymore. You'll probably be figuring that, yeah, they probably have some tricks I don't know about, but I could do 90% of what they're doing myself! Which actually means it's a good class!
One thing I definitely would have added are some words at the end of the course about what the "hot topics" are in machine learning, and suggestions about where to go from here, what topics would reward further study, and what books, websites etc. are available for studying them. For example, some words on where to study how and when machine learning turns into full blown artificial intelligence would be appreciated.
The only real gripe I have is that the assignment due dates really didn't give appropriate regard to how busy real life can get during the winter holidays. After all, the big selling point of online learning is flexibility! Right?
In summary: I figure this class is about as good as online learning will get. The instructor is very clear; the assignments are fair and useful. I would have done a few things differently, but nothing is ever perfect. This is a good class for anyone wanting to know the basics of machine learning. Four stars.
por Saideep G•
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.
por Doreen B•
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.
por Moto G•
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 "
por Mehdi E F•
Very instructive course.
It would have been great to get an OCR exercice at the end.
por Nils W•
Great course, but the sound quality is quite bad.
por Sai V P•
Better upgrade from matlab to Python
por Eric S•
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!!!).
por Daman A•
The course needs a platform where people can actually apply all techniques independently and learn by way of being graded on their accuracies in prediction. Otherwise the assignments just become a mere copy-paste mechanism of the formulae provided in the pdfs.
por Shitai Z•
Too easy for people with background in machine learning. But would be a good introductory one if you have zero understanding in machine learning and want to change your career track.