No graded assignments. No conceptual explanation.

Need more explanations on the RNN models itself.

Please add Coursera assignment based on coding

I wish there were more graded projects.

No practical exercises that one must do

A bit too easy and no real assignments

I wish there were graded assignments.

Coding assignments are much needed!

Assignments need some improvment.

not enough programming exercises

Concepts explained too quiclky

Code should be explained more

Not challenging enough....

No programming assignments

Force me to write code.

Need more practice

Felt a bit rushed

Good course

too easy

good

Normally the courses of this specialization are well-structured and, although not very demanding, quite complete and self-contained, but in this case the content covered didn't go deep enough and there was very little insight provided into the principle of RNNs and specifically LTSMs, other than pointing to other lectures.

Also, while sentiment recognition seemed to be an interesting and promising field, the results of all attempts at text generation were so laughable that it made me wonder as to why was half the course devoted to it instead of some other application area of NLP

Very disappointed in this course. Instructor seems to have limited understanding of how sequence models and word embeddings work, or is unable to communicate the ideas in his teaching. Explanation for the theory is limited, and he has difficulty tying theory to the TensorFlow framework. Not sure why you would begin teaching sequence models with LSTM blocks combined with standard NN, way too complex structure. Instructor doesn't talk about why sequence models are important and useful in the first place. Very very poor.

Instead of taking this course, I could've read the tutorials on the TensorFlow site. Those tutorials are regularly updated, maintained, much more detailed and they're FREE.

This course, along the other courses in this specialization are not good for other than exposition to the TF API. Actually, they're not even good at that because the TF tutorials do a much better job at that.

And it's so frustrating that over-fitting is never tackled in any way and not even a hint at how to solve it is even given.

This was by far the hardest course on the sequence. I actually skip it and did courses on order 1, 2, 4 and now 3.

* Notebooks were not as easy to follow. Maybe put more comments on what was expected and describe the datasets a little more.

* There are typos here and there, for instance "The pervious video referred to a colab environment you can practice one. "-> previous.

The file at https://github.com/tensorflow/datasets/blob/master/docs/datasets.md NOT FOUND

Compared to the first two courses of the IBM specialization, this one is made really bad.

They are rushing through the theory. The programming excercises are only ungraded and not very intuitive to solve. You will almost certainly look at the solutions before getting them to run. If you have a look at the forums of the course, there is not much help to find; it looks as if most people cancel the course before they finish.