I liked this course, but not as much as the others. It is however setting the foundation for the remainder of the course material. It carries with it wisdom, which I think will make more sense at a later point when confronted with real life challenges

This is the course that really confirms Andrew Ng's grasp on the practically application of AI and ML. As long as you pay attention to what is said, you will get a lot from this course. I wish there was an edited collection of notes for this course

Very useful part of the course set. Would like it to be slightly longer with more examples of TensorFlow and Keras. I felt that I put to much effort of trying to understand Keras in course number 5 instead of learning the principles and algorithms.

I like the "flight simulator" quizzes a lot and other courses might benefit from a similar assessment (in addition to regular quizzes and programming exercises), but I do think this course would benefit from some programming exercises too. Thanks!

It is a great course! thanks everyone involved in making it! If you can make more questions in every video or so i think it would be better. Also different case scenarios like the one you presented here in order for students to generalize better

I enjoyed the course content a lot, but noticed a lot of errors in test materials and test sections that didn't seem to make sense. For example, there were references to a flight simulator in quizzes that actually never appeared in any questions

I wish it could have had some coding practices and more mathematical insights. For instance, more insights on the different metrics (precision, recall, f-measure) and having some coding practices to get better sense of it on real world examples!

Very useful and practical information. Some of the videos had sound issues and minor editing glitches. I wish there had been more hands-on assignments. The few that were supplied were good but I think one more, less guided example would be good.

Comparing other courses before, it focus more on structing deep learning program and evaluate properly. However, the content in this week is really boring. In my opinion, it is better to imptove the course by teaching more implementation codes.

Some questions in week 2 test are ambiguous and the last videos have edition errors. But overall strategies for guiding projects are very useful. It's a great course about practical aspects of Deep Learning you'll probably not find anywhere.

I have previously worked on DL project and its performance was not good in real-world data, I wasn't able to draw any reason for it. This course taught me how to deal with such kind of problem and how one can approach the possible solution.

Was a good course with a lot of useful tips that I am sure I am able to use in my job as a data scientist. However, I would've liked if there were a few more hands-on examples (e.g. using jupyter) to really drives these concepts more home.

The course could have been much shorter than it is because Andrew seems to be repeating his simple ideas a lot in the lectures. However, each simple advice seems important for practical purposes (I am willing to take Andrew's word for it).

It might be not that trivial. But some hand-on experience with some code might be good here as well. As many practice as possible would be beneficial to the learners, coupled with great explanations from Andrew that are already in place.

I think the quizzes should be considerably longer, to include more scenarios, and also have fewer questions that rest on technicalities (where some of the answers are almost correct except they misuse a term or give a wrong description).

While the simulation is unique and very useful feature of this specialization. I believe examples with data would add to the leaning experience by allowing a student to actually run the scenarios and experience the qualitative changes.

This course is at all an important part during the learning journey. The only reason why I not rate full 5 stars that the recommendation ramen little bit on high level and do not address typical frame conditions in real world projects.

Lots of practical stuff about training models. But you should try building a few models before doing the course. Otherwise, you may not fully appreciate how much time can be wasted unless you use Andrew's clear and logical approaches.

Lots of interesting and useful idea. Unfortunately the editing is poor and Professor Andrew Ng has gone a little bit repetitive in his talking in this course only. The two previous courses were great but this one is kind of dragging.

I am a big fan of the jupyter notebook assignments. I can understand that it could be hard to build python assignments for this course, but not impossible I think (maybe around error analysis, impact of artificial data synthesis...)

The content of the course lecture is great. The teaching is great. One problem is the quality of subtitles. The black background does not allow to see what is shown behind. It would be better if the background would be transparent.

Great material! Some of the videos went a bit long, and I think the point could have been made in much less time. However, overall this series has been great and I still got some very valuable info out of this course, so I'm happy.

The course was very well structured and Andrews explanations was wonderful as usual. The only thing I was missing was more practical hands-on in the form of a programming exercise or two to really demonstrates the different ideas.

Andrew really provided great content, but the edition of this course is not as good as the first two, sometimes you will hear some repetitive sentences or a long pause. Hope they can upgrade this part, all the others are terrific.

This course give a lot of useful practical advices on training a machine learning/deep learning models. However, some of the advices are rather subjective and experience based, and some of the homework answers are quite debatable.