RG
Jul 12, 2017
Prof. Koller did a great job communicating difficult material in an accessible manner. Thanks to her for starting Coursera and offering this advanced course so that we can all learn...Kudos!!
CM
Oct 22, 2017
The course was deep, and well-taught. This is not a spoon-feeding course like some others. The only downside were some "mechanical" problems (e.g. code submission didn't work for me).
By Nairouz M
•Feb 13, 2017
Very helpful.
By brotherzhao
•Feb 15, 2020
nice course!
By Utkarsh A
•Dec 30, 2018
maza aa gaya
By Musalula S
•Aug 2, 2018
Great course
By Yuri F
•May 15, 2017
great course
By 赵紫川
•Nov 27, 2016
Nice course.
By Pedro R
•Nov 9, 2016
great course
By Frank
•Dec 14, 2017
老师太天马行空了。。。
By HOLLY W
•May 24, 2019
课程特别好,资料丰富
By Siyeong L
•Jan 21, 2017
Awesome!!!
By Alireza N
•Jan 12, 2017
Excellent!
By dingjingtao
•Jan 7, 2017
excellent!
By Phan T B
•Dec 2, 2016
very good!
By Jax
•Jan 8, 2017
very nice
By Jose A A S
•Nov 25, 2016
Wonderful
By Mohammed O E A
•Oct 18, 2016
Fantastic
By zhou
•Oct 13, 2016
very good
By 张浩悦
•Nov 22, 2018
funny!!
By Alexander A S G
•Feb 9, 2017
Thanks
By oilover
•Dec 2, 2016
老师很棒!!
By 刘仕琪
•Oct 30, 2016
不错的一门课
By Accenture X
•Oct 12, 2016
Great
By Ludovic P
•Oct 29, 2017
I wish I could give 4 and a half star to this course.
On the positive side : there is a lot of value in this course. Professor Koller succeeds in introducing us to PGM representations in a few weeks. IMHO, one should really do all the exercices "for a mention". Without them, this course lacks "hands on" sessions, and is much less interesting. Most programming exercises are great, and the companion quiz are really a plus.
When I followed Professor Ng programming exercises, I was both delighted and frustrated. Delighted because I learned a lot of things. Frustrated because it was sometimes really too easy.
This is not the case for most exercices there. I find them so well prepared, so crafted that I often learned a lot of my first wrong submissions of quiz of programming exercices.
On the negative side : the quality of the sound recordings is sometimes not really good. That is especially true in the first videos. That should not stop you from following this great course ! Some programming exercices were a bit frustrating because their difficulty is more in knowing octave tips and tricks than in PGM. In addition, and this is more embarassing, some exercices do not work, like in Markov Network for OCR https://www.coursera.org/learn/probabilistic-graphical-models/programming/dZmtj/markov-networks-for-ocr I had, as other students, to disable some features and to blindly submit my ansmwers.
Also, some exercises were difficult for me because of very precise English. I guess it might be difficult for native speakers to handle that, but as this course seems to have an international audience, it would be great.
I feel that raising this great course from 4 stars to 5 stars would not require much efforts. Prepare better recordings of the few videos that have really bad sound. Correct those small bugs in exercises. Simplify some English wordings.
I, however, advise this course to all persons interested in this field. And I intend to follow the next course, on inference.
By Jonathan H
•Jun 25, 2017
Excellent course. The video lectures are challenging (had to keep my finger on the pause key) even if you're familiar with the math, since the instructor encapsulates concepts in an amazingly concise manner. This pays off with a lot of "Aha!" moments as strong concepts are combined to create insights, especially starting around week 3. I'm already in love with this subject after 1 part
It would have been nice to have more worked homework problems, since this is a math course. But, this is not necessary to pass the class or understand the concepts. I've purchased Prof Koller's text on PGM and hope to solidify some of the intuitions I'm missing shortly.
Taking off a star because the test cases and grading software for the honors homework assessments were clearly low effort and sometimes incorrect. There were a lot of cases where functions passed all the provided and automatic test cases despite major flaws (e.g. not working for any cases besides n=1), which made it difficult to tell if things worked since the programming style is unique. The homework itself was super interesting and valuable, but I probably spent over 50% of the time fighting the grader instead of learning stuff. Given that I'm a professional programmer and completed most of the homework in 25-50% of the estimated time, I'm guessing that the average student wasted even more time with issues that are ultimately unrelated to our understanding of PGM.
By Hunter J
•Jan 12, 2017
Before I took this course I took the Stanford Machine Learning course, which I greatly enjoyed. That course allows for the learning of difficult concepts in a way that I found less painful than working through a textbook. In this course there is a lot less video content, and the coding assignments are less interesting. Expect to spend a lot of time understanding the nuances of the code that the instructional team has developed, and be prepared to really pore over the gritty aspects of Octave or MATLAB. If you're serious about this course I suggest buying the accompanying book. The slides are not easy to understand without the audio narration, which makes them difficult to review, and unlike the case in the ML course, there are not a lot of readily available open introductions written on the topics.