This course should be broken into 4 weeks and spend more time building skills with Keras. The number of hours listed next to each assignment is unrealistically low.

The lecture was great but the errors in the programming assignment (especially in formal-typed formulas) really wasted a lot of time and make me confusing at first.

The ideas presented here were clear, however I found the programming assignments non-intuitive and not practical. I spent on them way more time than I wish i had.

The first courses in the deep learning series were amazing but this one was not great. Had to read about transformers elsewhere because it was poorly explained

I enjoyed all the courses, from my personal point of view this course was not that fun as the other courses. Except for the trigger assignment it was awesome!

Too much was given in external python code for the first week's assignment (that should be learnt by us): not a good thing for us to gain a good understanding

Worst course of the specialization, content is interesting and Andrew keeps explaining really well but programming assignments are clearly of a lower quality

The course is great but the tasks in Keras are too complex without background knowledge. Therefore, a reasonable introduction in Keras would be desirable.

Far less detailed than the other ones. The programming assignements are less interesting too, as a great part of the work consist of reading documentation

There were lot of bugs in the assignments taking up lot of time to fix. The course was okay, I liked the other courses in the specialization more.

The Keras programming exercises are quite weak. Please re-think how to teach them more systematically. Currently it is quite a lot of hit and miss.

The course content is very interesting, but the lectures are difficult to follow. The notation is unclear, and the key details are not explained.

The lectures were great, but the programming assignments could have been structured better, especially the final assignment which drove me nuts.

That was much harder than the previous courses of the specialization. However it felt like the videos are more hasty and less understoodable

There was a bug in a programming assignment notebook that took too much time to notice that i was doing ok but the expected ouptut was wrong

The programming assignments required some extra effort to understand Keras which I thought may need an introduction video like tensorflow.

Several grader issues, only 3 weeks of work, and a lot of errors in the solutions... In addition, less content than in the other courses...

The earlier courses were easy to understand, however, this was way too difficult. Andrew Ng did not make this easy like the other courses.

Compared with previous courses, this one seems to be rushed. The focus on applications seems to be much higher than the theoretic side.

Not as great as the other courses in the specialisation. The assignments can be a little off putting, but lectures are top class again.

Week 1 took double time to be completed. Times proposed for the assingnement are underestimated.

Please readjust the assingement time.

Assignments are not up t the mark.. Expected to have high vocabulary size word embedding assignment, Machine Translation assignments

The theory part was great as always. Compared to the first 4 courses the labs were not that good and some of them very confusing.

This course was good but in comparison to the other courses in the deeplearning course series, this course lacked adequate depth.

The course is a good course because the lecture Ng.W ,but the exercises is not easy for our beginers for such tools like kears.