It's a little bit difficult to understand some concepts, even thought with examples. So it would be nice if there are some programming in the course. That will help to understand the process.

Andrew Ng was great. Mu only complaint for this course is was it was a bit slow paced as per my liking and could have more hands on practice for that part. Otherwise, This course was Awesome

Great class. Homeworks don't encourage independent thought. It would be nice if the material would spell out the problems that need to be solved more clearly, before describing the solution.

That is a good course that teaches you many useful tricks in machine learning. However, some mistakes in quiz make me feel puzzled. In general, it is a good course that you should not miss.

Very good course with important topics. The Quiz 2 should be reviewed because has some inconsistencyies has mentioned in the forums. Some more pratical assignment would be also appreciated.

I was a little disappointed that this course didn't have any programming exercises. That being said, I really like how the quizzes make you think of a real world application. Great stuff!

Very good advice that is hard to find anywhere else. The quizes however have some ambiguous cases which are borderline wrong. At least they should be explained better after the completion

Interesting opinions on what strategy to take to drive ML projects forward. Here and there you must weigh in with some "numbers" that suit you/your team but it's informative, nonetheless.

The course appears to be in development and could be strengthened with programming assignments that take you through an actual mock project. Otherwise, the current content is enjoyable.

Not so much different with the materials in the Machine Learning course from Prof. Andrew Ng itself. If you don't have the time to finish the ML course, then you should take this one.

So thanks for your well-designed course. I would say that if you provide much examples or programming assignments for this course, it would definitely be more helpful for the students.

A good approach to ML strategy. However, having a programming assignment to better explore results from tweaking models based on the strategies discussed in the course would be great.

Developing intuition on how to structure projects in deep learning is essential to becoming effective and productive. This course is a good start for gaining that experience quickly.

Valuable information that is well-organized and clearly delivered. Would benefit from a larger number of shorter exercises each week to cement learning after each group of lectures.

This is a great course with excellent contents and guidelines !

Point for improvement:

Please add a programming assignment in python and the questions appearing during the lecture....

This course provided an empirical approach in tackling hurdles in solving most common issues faced by data scientist in solving Machine learning problem in a very simplified manner.

I really appreciate learning about the high level strategies for designing machine learning projects. I only wish there were some programming exercises to put it into practice.

Based on my own experience and comments on the discussion forums, I get the impression that the quizzes have a couple of errors in them that makes it impossible to achieve 100%.

This course is less pratical and theoretical. I don't mean it is not helpful to me. I think this course might be helpful as guideline when I hand on the real project in future

very good course, but I felt like it was lacking one more week of course to get deeper knowledge about how to really get data sets and how to set them up for real applications.

While the course teach valuable concepts, the material (especially the quizzes) contained many problems, ranging from grammar mistakes, to ambiguous writing, to wrong answers.

you may think because the course is shorter will be much easier but the videos has a lot of information to process. I am excited to tried this techniques on real applications!

A good course. Provided general high level thinking and reasoning for quick problem solving, data management, multi-tasking, transfer learning, and error reduction techniques.

Not as exciting as the previous courses, but informative nonetheless. A section for handling imbalanced or skewed datasets would be useful, especially for multi-task learning.

Not as deep into details as the two first courses in the specialisation, but nevertheless I learnt a lot of techniques that I hope will be feasible when I work on AI projects.