Graded, non-optional assignments should really be added to this, and the rest of the courses.

It would help ensure the understanding of the tools in question. Providing the answers as Colabs is nice and helpful, but does not drive you to actually try things out.

In last week, the course gets really worse. The code are not well explained. And no tutor is there for answering the questions. For example, suddenly change the model from sequences2vector to sequences2sequences without any notification. What a shame.

Teacher is not anywhere close to Andrew, plus the grading tools are non-existent. It goes too heavy on preprocessing when we want to learn tensorflow, you could've spent all that time in teaching Tensorflow appart from Keras.

Barely scratched the surface of the topic. For this particular course (alongside NLP too), I constantly had to look for more sources of information as certain aspects of the code implementation was not thoroughly explained.

Compared to the first two courses in the specialization, the last two lack a lot of practical coding homework, and there is really where the concepts are fixed. The course should have more graded coding excercises.

Good course but could have been better. Many obvious issues with time series forecasting / prediction were not discussed, such as the inability of the model to predict some of the peaks and troughs better.

It's a relatively shallow course. They don't really dive down to the details or even don't cover whole a lot when it comes to examples, exercises or assignments. So, This is very much for the beginners.

The week 2 quiz is super bad (even pro NN people didn't couldn't answer some questions cos they're badly worded).

I honestly am not a fan of getting the notebook after the video that explains it.

Nice course. Despite it's a practical one, you should consider to get just some deeper in the theory embedding the models you presented, to make the audience understand better what's going on.

As from fulltime ML practitioner and occasional user of TF this course is not too much in "practice" as many things are left untouched. However can be beneficial to complete newbie.

Good course, but seems a bit hastily put together. I really liked the technique for determining optimal learning rate. Thank you Mr. Moroney and the entire Coursera team.

This course teaches how to use the tools in Tensorflow for predictive analysis. It would be more helpful if you're familiar with sequence models.

Course should more focus on real time data set, and assignments should be based on building the model, rather than this kind of simple questions.

This course was less detailed than I had hoped. I feel I have learnt more from the CNN and NLP courses in this specialisation.

The sound keeps getting lower and lower but the materials is good. i hope you can explain in real data more than dummy data.

I didn't expect the course would be this easy and simple. But overall, this course is useful for introduction to TensorFlow.

This course lacks content, does not really teach much. Most of the time instructor just reads out code

More explanatory links can be given about different concepts. Other than that, course is fine.

Well done and structured, I only wish the assignement would be more difficult!

Would have preferred notebook evaluations which were there in the CNN course.

Time series future predictions is something I really missed from this course.

More real world examples and datasets would have been beneficial

Would ask more difficult tasks to solve, the level is just entry

It is the most interesting course of this specialization.

could have emphasized more on the time-series data...