I love the material! The lectures are good, but this course has some serious problems. There are bugs in the slides and the quizzes, causing formulas to show up as things like "Undefined control sequence \dfrac" or " Misplaced \", making you guess at the part of the formula that's missing.
Despite having a decent background in computational learning theory and a bit of background in ML, I found myself having to crack open a book to be able to do a lot of the quizzes. The material for many questions is only covered tangentially in lecture, if at all. I can only imagine how hard it would be with no background (the course material pointedly did not list ML background as being required). If you go to the coursera forums, you can see multiple highly upvoted threads complaining that the lectures simply don't cover the material needed for the quizzes. The staff have responded by saying they're thankful for the feedback, and will try to make things better next time; here's one exact quote: "Thanks for the feedback everyone (including everyone who votes for feedback threads). We're working out the right balance as we go, and I think we'll have it down better next time we run the course. I agree that there've been some real problems."
It's great that they're acknowledging the problems and will try to fix them, but that doesn't help anyone currently taking the course.
To summarize, the lectures are great, except for some bugs in the slides, and the overall course would be good for someone with a decent ML background. However, it's billed as a course for people that don't have that background; they say they'll try to make it better next time, but this run of the course has some problems.