Difficult to rate this course. I'm definitely glad I took it as it gives a valuable information, but it could've been much better. It should not be a 4-week course as it takes 4 to 8 hours of time to complete. Most of real world time series are multivariate, so I was expecting the course to touch them at least a little. Also I'm not a fan of the "if you do everything exactly as you've seen in the videos, you will pass" style of assignments - I'd expect at least some improvisation to be required.

Too much focus on creating synthetic data and arbitrary code. Unlike the first three courses this was hard to follow with significant gaps in the material not explained.

Although I passed I am still unsure of what I have learnt on this course.

My advice would have been to use a real dataset from the start and build on this and eliminate all the helper functions that just really proved a distraction. This would also be a great motivator if the dataset was interesting.

Just like Course 3, Course 4 was a let down. The content is interesting but I think unlike Courses 1 and 2 it is presented in a way that is kind of plain and not really all that engaging. I also think the assignments should still be required as this adds incentive to really work hard at it. I learned a decent amount, but Courses 3 and 4 of this specialization were a disappointment.

The materials are outdated and they are not as described as the first 2 courses (the effort and quality to make the curse is not the same as the others). The notebook from the first courses are very well documented and the ones from the last two are just code. Other than that the curse is great and well explained

Much preferred the Andrew Ng courses where we spent time coding specific sections of various neural nets. This ourse was practical, I guess, focusing on the mechanics of prepping data, but I don't feel it helped my understanding of the various machine learning techniques at all.

Some of the topics could have been described in details. There was always some kind of rush going on. By the way, I have come across several datasets and those labs introduced me to various neural network and their application using Tensorflow and Keras. Thanks to Laurence.

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!