As PhD in physics I found lecture super-boring (too much theory and derivation) and irrelevant to the practical assignment. On the other hand, most of practical assignments are explained very pedagogical manner (except week 5!). As for the first course - I would recommend more code-related lectures.

Excellent material! I got new very useful knowledge. I really like the final project. Although course design is not perfect. It would be great to have additional content (links or documents), lectures are not enough to pass the tests. Also some assigments have issues (code and grader errors).

Good course. But some suggestions: topic about variational inference or variational EM in theory is quite tough, better to have equivalent level of assignment for better practical understanding. Personally, I feel VAE is a very simplified application case.

The materials of this lecture are awesome. Very useful! However, the introduction of project assignments are very confusing, especially the final project. It took me hours to understand what the task is really about, and what should we really do.

The content+course structure was phenomenal. The assignment environment setup was a bit cumbersome at times, but the level of difficulty in the assignments really solidified the understanding of the course material.

a very important material is covered in a clear manner.

some of the labs could have been more effective (e.g. avoid unnecessary mixing between tensorflow and Keras)

Strongly recommended course ! great curriculum !

It probably offers the most comprehensive overview of Bayesian methods online. However, it would be nice these methods translate into practical data science problems found in the industry.

The course covers a lot of very advanced material and is a great starting point for Bayesian Methods, but it would greatly benefit from having additional reading materials.

Great class. Well presented material. Sometimes the path from introduction to advanced material could use a few steps in between.

We may need more help for homework format or quiz answer format. It took me lots time for solving it.

Amazing course, an absolute must! Only some programming assignments were having minor issues.

Good course but a bit difficult and the peer review is helpless

Good course.

Too much theory, not enough practice

The first exercises are sessions are fun and very good.

However, the last exercise is a catastrophy. Conflicting instructions. Once I should upload a HTML version but nobody says who. Then suddenly the rules are changed and it is supposed to upload it some google cloud. This platform is qute annoying. Either I cannot edit my work any more or suddenly it just disappears. The editor is also very bad. This is just unfair. Really the technical problems in the final project are too extreme.

Not very well prepared. Contents are dry and not well illustrated. Failed to explain points that are made in the videos. The lecturers are reading from scripts and look very nervous.

Not so good as I thought. Some times is too complicated and dry. Need more balance. I hope, that guys can better. But I want to say thanks to authors. You did a great job! Good luck.

Explanations are very technical and do not develop any intuition as to what the methods are supposed to accomplish.

The trainer's English is not very good, and the explanations provided are insufficient.

As the description suggests this course is very advanced and math heavy.

给三星是因为所选的 TOPICS 很好， 真的很好。但是，说到老师的讲解，就真的不敢恭维了。从逻辑性到流畅性都让人捏把汗啊。希望改进。

ㅁㄴㄹ

It is a great idea for a course -- very important in today's ML environment.

However, I felt the instructors did not give much of the "big picture" reasons for why they were teaching each individual technical detail. As a result, I know some more math, but not much about how to apply it to ML. I'm going to have to go online and independently read materials available on the subject so I can better internalize this and figure out how to use it for my purposes in ML.

Although I admire the instructors for giving the class in what is obviously not their first language, it was still quite difficult to follow sometimes when words were mumbled or mispronounced. This could be improved if someone technical could review the lecture transcripts and fill in all the errors and [INAUDIBLE] notices.

The programming assignments were OK, but mostly struggling with syntax rather than concepts. The python package GPyOpt that we used has awful documentation, so we were in effect blindly applying some process optimization code to our homework, without any idea of what it was doing to it and how we could adjust the parameters to better suit our particular application.

The instructions are hard to follow. Most of the material presented as purely mathematical derivation exercises that do not have stated goal.

On the plus side the topics covered in the course are very interesting. Personally, I ended up using this course as a guide and looked for explanations elsewhere.

I felt the explanations too mechanical and in between they skipped a lot of concepts and explanations.

Not structured well