Very good overview of ML. The GraphLab api wasn't that bad, and also it was very wise of the instructors to allow the use of other ML packages. Overall i enjoyed it very much and also leaned very much
The course was well designed and delivered by all the trainers with the help of case study and great examples.\n\nThe forums and discussions were really useful and helpful while doing the assignments.
von Paulius J•
Wanted a course on ML. Could not find anything except this. Therefore decided to take it. However not so sure Turi Create/Graphlab is the best option (had installing issues as a Python beginer). Was it worth to use it instead of Scikit learn? Also I would expect closer connection between quiz tasks and study material.
von Salvador V M•
Good for start in machine learning concepts. Good because they use Jupyter Notebook an python (they use python 2, it would be better 3). But I don't like much the graphlab library for data frames. And also the quizzes are a bit difficult. You have no the whole information in the documentation to solve them.
von Romain R•
The content is really good, well explained=> 5 stars, nothing to add.
Why the 3 stars then ? Graphlab. If you use the pydata stack, as it is said to be possible in every assignments, you get stuck on the quizz due to variations on data and the algorithm used, so you can't really get quite the same answers.
von Vivian Y Q•
Videos were too short to go into details. Too much reliance on the package they development themselves, though I appreciated the simplicity, I don't get to learn about a lot of technical details. So you know how to run a image retrieval model without knowing what are the deep features, for example.
von Troy D•
Good course, learned a lot of basics. I think this course is rather old though and getting a lot of the required software up and running required a lot of work since there are much newer versions available now. I found that I had to do a little extra to get the older packages working in Jupiter.
von Aleksandar S•
The course content is great. It gives overview on what is going to be learned in details in the next courses. Considering that it is an introductory course and the fact that it utilizes the GraphLab library as tool, I believe it is overpriced compared to the other courses of the specialization.
von Yaniv S•
The whole eco-system is based on Graphlab create which is not very commonly used in the industry. The "Programming assignments" are very much like the exercise done in the videos - so no real thought and effort were needed. The Deep learning part is really bad thought and bad examined.
von Eric J•
The enthusiasm of the instructors was the best thing about this class. But I really wanted a more rigorous methodology - and didn't really get it here. But it was an alright introduction to machine learning but not enough if you want to know what makes the 'black box' work.
von Paulo S B d O F•
(1) Teachers know what they are talking.
(2) They are energetic and funny.
(1) The course uses proprietary and expensive tool.
(2) The course is too simplistic.
(3) The teachers, although they know what they are talking about, they aren't very good at teaching.
von Anirudh A•
Good with concepts. But would have been better if a standard library like scikit were used rather than SFrames, Turicreate and Graphlab for the sake of easing things out which actually is not very convenient for a lot of students. (atleast during the learning cycle)
von David K•
I think that the course is redundant, it is to general, trying to capture to much, and using a commercial program tool that's doing to much behind the scene.
The second course in the specialization is really great though and you wont miss anything if you skip ahead
von Varun J•
A lot of problems with software installations. But, the professors for this class seem to be very passionate about the course and they teach well. If not for a lot of problems faced during software installations(which is still not resolved), would have given 5 stars
von Michael C•
Really just an overview of the topics to be explained in detail afterwards.
Big plus for the use of python + notebooks but otherwise, if one is interested just in the overview and not in all the specialization, maybe the Andrew NG course is more detailed.
von Bernardo C•
El curso tiene mucho potencial, pero hay que afinarlo.
Pienso que los vídeos deben ser reeditados. Tienen errores y conceptos confusos. Deberían ser tan claros como para lograr tomar buenos apuntes y usarlos en las tareas. Las tareas son casi mecánicas.
von Rishi H•
Content and material is good and the trainers are good. Only issue i found is course assignments are heavily dependent on Sframes and graphlab which does not work most of the times.,they should go with panda libraries which is easily accessible.
von Aman S•
The worst thing about this course is graphlab. Trying to run it since last 10 days with the help of every available online resources, but in vain. There are many flaws in graphlab. I tried a hundred times to view images in graphlab, but in vain.
von Juarez B•
This course introduces the key topics of Machine Learning, but the math behind the algorithms is not explained and the programming exercises are too easy. Unfortunately, it also relies heavily on graphlab instead of using open source software.
von Mohit S S•
Course contet is ok. But, intructors really need to teach in a platform neutral way or some other popular library for which ample support is available. In my opinion, learning a tool which is nowhere used in te industry is not a good idea.
von Tarek M s•
the course is good for starter but according to its repetition I waited more .
one star down for many useless information in lectures about Amazon products and so on.
one star down for forcing using unpopular python library .
von Piyush K P•
thanks to prof and cousera for this wonderful course. I wish the programming part was taught separately from basic. I have taken the previous course which was case study approach with respect to which it was slightly tough.
von Jerome B•
The teachers are nice and the content is pretty interesting, but they keep talking about the Capstone that we actually won't do. That make me wonder if it's worth continuing, and wonder why they cancelled it eventually.
von Gregory T•
This was a valuable introductory survey course. For me, the challenge came from my unfamiliarity with Python not the material. I would rate this class as "entry level" for anybody with a college-level technical degree.
von Brandon P•
There were a lot of assumptions made about my math background. Terms and concepts were used that are foreign to most people and while the forums were helpful it was interesting to see that this is a common feeling.
von Mohammad A•
Course include great knowledge, but when coming to work on tools, they are using old method like we have python 3.7, but course is going through python 2.7 and also older version. That's creating confusion somehow
von Ivan P•
It's not a bad course, but it forces students to use GraphLab, a framework created by one the professors teaching the course, instead of using scikit-learn, a widely used framework for machine learning in Python.