Nice One!!

Very Fun

nice

ok

I'm somewhat disappointed. I attend almost all other courses in this specialization (except of "data product") and this one is, on my opinion, the weakest one. A lot of links to useful information though. This is more reference guide rather than a real training course.

I can say even more, initially I start other courses of this specialization just because they were marked as strong prerequisite to this one. For now, I think all other courses of the specialization were much more valuable for me than this one.

I've also took Andrew Ng course on Machine Learning in the past, and my learning experience was much better. In lectures on some concepts (like regularization) I'm pretty sure I would not understand anything if I had not been familiar with the subject before..

This course does not have the depth it needs, but I do learn a few valuable things. I suggest breaking this course into 2 courses and give more lectures on using caret package and other packages as well. Another thing is I could not ever find the correct answers for the quizzes, and most of the time has to guess and take the quizzes 3 times to get things right.

I invested time and effort in doing the last project; but got a not so good grade due to peer review process. I got every requirement done and even have a direct link to my HTML final report but 2 out of my 4 my peer reviewers have limited knowledge of GitHub could not find my link to HTML file. That said with a higher level courses, peer review process has to be different.

The course gives a decent overview of the model building process and covers a good spread of machine learning methodologies. I found that the videos focused too much on some basic/immaterial concepts at times and tended to gloss over the more in-depth or complicated sections. It would have helped if difficult concepts were explained with more examples. This meant that a lot of self study outside the lecture notes had to be done. The way that the final assignment had to be submitted on Github resulted in me spending 8 times longer on learning how to post my results than actually building the model - some more guidance here would have helped a lot as the process was very frustrating.

I believe this course is critical and much needed given where the Industry is heading. Prof Leek, has tried his best to explain the concepts in a lucid manner, however the complexity of the content, may challenge most students.

A few more examples with R code would have been helpful as translating problem statement to R code may not be intuitive.

I would highly recommend that students should plan to study some advance statistics before attempting this course. Having said that, i think this is a wonderful starter course to get a glimpse of what Machine Learning is all about.

I have passed 5 courses of this specialization and I am not fully satisfied with this one. The course is a very brief introduction to practical machine learning, as the concepts are explained very fast and without a minimum level of detail. Then, most importantly, there are no swirl exercises, so it is quite difficult to put the acquired knowledge into practice. The other 4 courses I took, they all had swirl and that was great. Nevertheless, the course project is quite nice in order to face a real machine learning problem.

As as standalone course on machine learning, it's probably best to take Andrew Ng's class on Coursera. This course mostly teaches the basic usage of the caret package. It is too short to cover more fundamental topics in machine learning, like how to choose an algorithm based on the problem and the data.

I took this class just because I was engaged in the Data Science specialization. I wanted to clear the Capstone project and get the Data Science specialization certificate.

A key course everything has been building towards, some important concepts and modeling techniques are introduced. However Jeff rushes through a lot of material, and I think this would be better served as two courses with more case studies and exercises, especially as the capstone doesn't use much of this. But nevertheless a useful introduction to this topic, concepts of training vs. testing etc, different models to be used, along with the caret package in R.

This is such a cornerstone topic to the Data Science Specialization that I think it deserves a better designed and more polished curriculum. The subject is so extensive that it might be worthy to split the contents in two courses. Finally, I would like to suggest the authors of the course modeling the curriculum following the amazing treatment of the subject found in "Introduction to Statistical Learning" by Hastie, Tibshiriani et. al.

This is a good course for someone who has already done the previous courses in this specialization series.

It covers the most basic ideas in machine learning and expose you to work on real problems and learn by experience. if you are looking for more advanced in-depth courses, you need to take other courses as well.

Overall, lectures are in very fast pace and as a result they have several mistakes in them you should be careful about.

The course feels rushed. I understand teaching Machine Learning in 4 weeks is impossible, but then maybe the course needs to have a narrower yet deeper scope rather than throw at you many concepts without details. e.g. trees, random forests, bagging and boosting all in 10 minutes each? Impossible...

So, as opposed to creating machine learning intuition I feel the course became an R package code book.

Unfortunately, I didn't think this topic was as good as the other courses in the Specialisation. Quizzes often references aspect that haven't been discussed during the lessons, and the lessons itselves are often too high-level (although I reckon this is why the course is called "Practical", and we might need several courses to thorough fully understand how each algorithm works).

In my view the course was useful but not as good as the previus ones I followed in the specializacion (such as regression models and stat. inference).

The subject was too broad and there was no space to cover in detail all the algorithms. Also I think it's a bit out of date because there is no references to xgbboost which is now dominating many Kaggle contests

While the overview of the content seemed very reasonable both in scope and pacing, the lack of swirl exercises meant that the final project for the course was a bit jostling. Overall, I think this course still needs some development in the way of exercises to familiarize the student with the practical exercises associated with machine learning.

Lectures are too complicated. I understand that material is not easy and one should do a lot of research and reading to understand the essence of the taught algorithms but the lecturer is also not very helpful and assignments are everywhere on the internet which nobody needs to get tired of thinking a little to do the homework as their product.

Like all courses in the specialization, good introduction to statistical learning, although a bit rushed off.

The learner has to navigate through the arcanes of r packages, which is not always easy. I am also quite surprised that neural networks are not part of the course, it should be disclaimed in the course content.

The material is well choosem but poorly explained. This course among all would need swirl excercises, or just more excercises in any form. Instead the lecturer rushes through the material. So in the end you do have some overview about machine learning in R but not enough hands on experie

Breadth of content covered (different ML algos) is great but is very cursory. Would be interesting to dig deeper into diagnosing random forests.

Quizzes are poor as built against old versions of R so you have to waste time setting up the environment to get the expected results.

The quizes do not match a 100% with the lecture videos. There are some weird questions. My algorithms' outputs deviate from answers some times, which is due to different software versions. Quizes are not very educating this time. Courses by Brian Caffo were much better.

Class materials and videos are confusing and do not go into enough detail. Assignments require a lot of search of extra information outside course materials. Also, the length that is needed to complete the assignments vary widely week to week.

Weakest class in the Data Science Specialization so far. Don't expect to leave with a deep understanding of the machine learning techniques covered in this course. You will get practice using the caret package in R, which is very useful.

Although again very interesting, I found the lack of additional materials such as practical exercises, swirls and a book reduced the depth of the course knowledge for me. Maybe we have been spoiled by the previous courses :-)