good

C

This course has interesting contents about the regression algorithms but sometimes it goes into too many mathematical details and it is easy to get lost. I'm not sure that much detail is necessary to understand what algorithms do, something else is missing to explain them intuitively. On the otThis course has interesting contents about regression algorithms but sometimes it goes into too many mathematical details and it is easy to get lost. I'm not sure that so much detail is necessary to understand what these algorithms do; more intuitive explanations are missing. On the other hand, as in the previous course, the material has not been updated to reflect that the last courses of the specialty have been canceled.This course has interesting contents about the regression algorithms but sometimes it goes into too many mathematical details and it is easy to get lost. I'm not sure that much detail is necessary to understand what algorithms do, something else is missing to explain them intuitively. On the other hand, as in the previous academic year, the material has not been updated to reflect that the last courses of the specialty have been canceled.her hand, as in the previous academic year, the material has not been updated to reflect that the last courses of the specialty have been canceled.This course has interesting contents about the regression algorithms but sometimes it goes into too many mathematical details and it is easy to get lost. I'm not sure that much detail is necessary to understand what algorithms do, something else is missing to explain them intuitively. On the other hand, as in the previous academic year, the material has not been updated to reflect that the last courses of the specialty have been canceled.

This course offers great background instruction on Machine Learning and I would give it 5 stars except for the following:

First, there doesn't seem to be any moderation of the session discussions except for help from other students. This was worth a -2 star penalty. This and the lack of any review of linear algebra and vectorized solutions, I think, is giving some students the impression that they should be coding loops in their functions to build and solve ML models.

Next, I am auditing the course, and this is the first course where I was not able to submit quizzes. Therefore, I can only guess at my solutions. This was worth a -1 star penalty.

UPDATE: not being able to submit quizzes is a "feature" of the new Coursera platform. I never did get an answer from the discussion forums, but I see the same problem in other Coursera courses I am taking.

However, I still think the course is worth taking, so I added back a star. This is the second ML course I have taken. The first was from Stanford ML course which was very specific to implementation in the Octave language. I got a lot more background information from this course, and I think it is well taught. Just wish there were more moderators that were actively watching the discussion list.

Good topics and well enough explained, I really did learn a bit. But getting through the course is torture if you are using Sklearn (rather than using their tool TuriCreate). The Programming Assignments use different data sets (sometimes?) and are troublesome to download. From a purely UX viewpoint, the assignments are wordy/difficult to follow along with at some points (even when the content is not so difficult)

The instructors have put a lot of effort into this course and I really appreciate that but unfortunately, I was hoping that the assignments were more interactive like in the deep learning specialization and the tool used is not required at all in any job I searched for also It's not required to use it. I learned a lot out of this course but please update the tools used in this course

The program assignment's description was written badly and hard to follow

For example: in week 6's assignment, the description doesn't indicate features list but ask students to compute distance between two houses. I could only find out the feature list in provided ipython notebook template for graphlab which I apparently didn't use.

There are parts of the course which I got very very stuck on.. thankfully the forums have people's previous frustrations / questions on there. Reading these helped. Other than that, this course is the most comprehensive look at regression techniques I've taken yet, and I'm thankful that this course is provided.

Assignments instructions are not very clear. Formulas used in assignments are structured differently then formulas in lectures. Too much emphasis on using turicreate. Not practical- companies do not ask for knowledge of turicreate. Companies ask for knowledge of scikit learn, pandas and numpy.

The material is well presented. Two of the exercises were worded a bit obtusely, and I had to really parse through the questions carefully to understand why I was submitting answers that were graded as incorrect. Once I understood the ask it was easy to provide correct answer.

The content is good but completing assignments is a real pain because they choose to deploy a unstable proprietary python library, which gives hard time installing and running (as of Q1 2019). The entire learning experience is marred by this Graphlab python library.

Passing mark is 100%, it is tough for me and demotivating to persuade further. And the course becomes too extra factors and complexity on later classes, it made me to lose the interest on the algorithm and course.

I cannot complete it because of these two factors

The reading sections in module 4 had incorrect assumptions because of which I could not clear exams for months. Also the queries we posted in the forums are hardly responded. I just hope coursera takes support systems as actively as the contents

Nice explanation and nice tasks but the course is designed for graphlab. If you want to use something else the tasks are often badly described or it is impossible to pass the

The material is excelente, But I would like you to promote a little more the community. Due to, sometime is difficult to advance when you don't understand a subject.

Great indeed, but you have to rely on the Graphlab to realize those functions. You need to figure out whether you will use Graphlab in your future studies or work.

Rather elementary and slow-moving for my taste. But the material is competently presented and covers the material it is advertised to cover.

Missing in-lesson quiz, with all the homeworks being at the end of the week: this make following the pace quite tough

Good course content but it can be very difficult to get help if you are stuck on something.

Course materials are well organized. It could be improved by adding more description.

Please show examples of codes in lectures just like the previous course

Course should contain a project related to real life.

very interesting environment to learn the subject.

Too much math...

I'm a statistician, not a programmer. There is so much detail and explanation about the statistics and concepts behind how it works, but there is hardly ever an actual lesson on the code used or needed to implement the algorithms. When trying to fumble my way through the code, I found, on several occasions, the code in the self-directed lessons to be incomplete (I'm referring to pieces of code that were obviously meant to be there, but were missing), causing hours and hours of anguish and turmoil. I feel like there should be a lot more time spent on the actual coding and learning how to implement it within the code (similar to the 1st course), rather than spending an exuberant amount of time going through derivations and no time on actual coding and how to implement it within the programming language.

If you are a software designer/engineer or programmer, then you should be fine as long as you pay attention to the very long lessons and derivations and can fix the broken code that you are given. There are other mistakes within the quizzes as well, which make them near impossible to pass. For example, it is unclear which model you need to use to calculate in order to get the correct square foot. On other occasions, the question actually specifies to use the model from (3), whereas it actually wants you to use the model from (4) instead to get the correct answer. This course needs to have better quality checks to ensure needlessly lost time is minimized.