学生对 斯坦福大学 提供的 Probabilistic Graphical Models 1: Representation 的评价和反馈
课程概述
热门审阅
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!!
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).
176 - Probabilistic Graphical Models 1: Representation 的 200 个评论（共 297 个）
创建者 Yang P
•Great course.
创建者 Nairouz M
•Very helpful.
创建者 brotherzhao
•nice course!
创建者 Utkarsh A
•maza aa gaya
创建者 Musalula S
•Great course
创建者 Yuri F
•great course
创建者 赵紫川
•Nice course.
创建者 Pedro R
•great course
创建者 Frank
•老师太天马行空了。。。
创建者 HOLLY W
•课程特别好，资料丰富
创建者 Siyeong L
•Awesome!!!
创建者 Alireza N
•Excellent!
创建者 dingjingtao
•excellent!
创建者 Phan T B
•very good!
创建者 Jax
•very nice
创建者 Jose A A S
•Wonderful
创建者 mohammed o
•Fantastic
创建者 zhou
•very good
创建者 张浩悦
•funny！！
创建者 Alexander A S G
•Thanks
创建者 oilover
•老师很棒！！
创建者 刘仕琪
•不错的一门课
创建者 Accenture X
•Great
创建者 Ludovic P
•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.
创建者 Jonathan H
•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.
Coursera Footer
