Machine Learning by Stanford

Overall the course is great and the instructor is awesome. Machine learning is fascinating and I now feel like I have a good foundation. A few minor comments: some of the projects had too much helper code where the student only needed to fill in a portion of the algorithm. I would have preferred to have worked through more of the code. Also, there were a few times when the slides didn't contain the complete equations so it was difficult to piece it all together when writing the code. Lastly, I wish that there was more coverage on vectorized solutions for the algorithms.

It would be better if it would have been done in Python

Excellent starting course on machine learning. Beats any of the so called programming books on ML. Highly recommend this as a starting point for anyone wishing to be a ML programmer or data scientist.

I've never expected much from an online course, but this one is just Great!Even if you feel like you have gaps in your calculus/linear algebra training don't be afraid to take it, because you'll be able to fill most of those right from the course material or at least figure out where to look.This course gives grand picture on how ML stuff works without focusing much on the specific components like programming language/libraries/environment which most of ML courses/articles suffer from.This leaves you with freedom to pick it yourself and apply gained knowledge however you want.Biggest takeaway for me as a person working on my own project is amount of attention professor Ng brings to methods of evaluating your ML methods efficiency and how this correlates with time/effort you should put into the specific system component. Because i feel like this is where most people slip up in practice.Great thanks for all of that!

This is an extremely basic course. Machine learning is built on mathematics, yet this course treats mathematics as a mysterious monster to be avoided at all costs, which unfortunately left this student feeling frustrated and patronized. So much time is wasted in the videos with arduous explanations of trivialities, and so little taken up with the imparting of meaningful knowledge, that in the end I abandoned the videos altogether. The quizes were basic (largely based on recall of, rather than application of knowledge), as were the programming assignments (nearly all of which were spoon-fed, with the tasks sometimes being simple as multiplying two matrices together).If you are serious about machine learning and comfortable with mathematics (e.g. elementary linear algebra and probability), do yourself a favour and take Geoff Hinton's Neural Networks course instead, which is far more interesting and doesn't shy away from serious explanations of the mathematics of the underlying models.

I am Vietnamese who weak in English. To learn this course I have to choose playback rate 0.75.But the teacher - Professor Andrew Ng talks clearly and the way he transfer knowledge is very simple, easy to understand. Myself is excited on every class and I think I am so lucky when I know coursera.This course provide a lot of basic knowledge for anyone who don't know machine learning still learn.Once again, I would like to say thank to Professor Andrew Ng and all Mentor.(I hope all of you understand my feeling because of my low level English, I cannot express it exactly)

Sub title should be corrected. Since I'm not that good in English but I know when there're mis-traslated or wrong sub title. If you fix this problems , I thin it helps many students a lot. Thanks!!!!!

This course has of course (pun intended) built a formidable reputation for itself since it was laucnhed. I took the course in 2019 when it had been around for a few years and so what I am saying here may resonate with a lot of people who have taken the course before me. "Concretely"(!), Prof Ng takes the student on a very well structured journey that covers the vast canvas of ML, explaining not just the theoretical aspects but also laying equal empahsis on the pratical aspets like debugging or choosing the right approach to solving a ML problem or deciding what to do first / next. At that level this course is highly recomended by me as the first course in ML that anyone should take. I do have a suggestion to make regarding how some of the portions could have been explained more lucidly. These are portions that pertain entirely to the mathematics and programming problems, where I struggled for days and (for back propogation) for months before realising that maybe the explanation given in the slide wasn't clear enough and at times i just needed to try really random ideas to get out of the programmin rut that I was stuck in. An advise for anyone doing the course would be to write down the matrices in full detail and do the transformations of cost fucntion and gradient descent or back prop using pen and paper and attempt to write the code for it only after once one is clear about the exact mathematical operation happening. Thank you, Prof Ng for gifting this course to the online learners community and I would also like to thank the mentors who have replied to the queries patiently while stadfastly enforcing the honour code.

It would be ideal course if instead of octave pyhon or r is used

You need to know, what do you want to get out of this course. It gives you a lot of information, but be prepared to work hard with linear algeabra and make efforts to compute things in Mathlab/Octave.

I just started week 3 , I have to admit that It is a good course explaining the ideas and hypnosis of machine learning . The instructor takes your hand step by step and explain the idea very very well.The thing is, there is no practical example and or how to apply the theory we just learned in real life.This course in to understand the theories , not to apply them.For someone like me ( far away from Algebra) it is really not for me. Despite i want to learn the applied ML

Very helpful and easy to learn. The quiz and programming assignments are well designed and very useful. Thank Prof. Andrew Ng and coursera and the ones who share their problems and ideas in the forum.