Course content is excellent, I would have given 5 stars, if the Programming assignments wouldn't have bugs. Fortunately people in forum help out with solving issues with assignments. I believe it's due to the short time frame the course is online and bugs get corrected.

While this was the most relevant course for me, I missed how it was focused on "helper functions" instead of core RNN concepts. While I feel like I understand concepts like the Bleu score, I would definitely need to spend more time to fully grasp the RNN architecture.

Good introduction into NLP and Sequence models in general. Too many things are done for you in order to fit this course into 4 weeks. I felt like I could not say that I built a system doing something. It was pre-built, while I just filled in some portions of code.

Very nicely put together, takes a difficult topic and gives you just enough to get your head around it. Only thing keeping it from 5 stars is that a few times it was more difficult to figure out what the auto grader wanted than what was needed to complete the topic

Would have been nice to get more extensive training in Keras en Tensorflow because programming excercies were somewhat too pre-compiled at times or other times difficult to code because of scarse knowledge of these packets. Otherwise great lecture material as usual

This was a great course and teaches you everything you need to know about RNN to get started doing your own research. With background in economics and finance it would have been nice to have one small assignment with time series data. Beside that, awesome course :)

Thank you for this course. The content is very throughout and yet explained simply. I had a hard time with understanding the attention model, the explanation in the course is not enough, but after all, it is a complicated architecture. The labs help. Thank you.

The grader has some bug.Even with correct output and with no bug in the code, it gives incorrect grading. Firstly the criteria to pass is so stiff(80% means to pass for every function).Secondly the bug in grading function grades incorrect for correct codes.

Andrew Ng does a great job in introducing Sequence models in this course. However, I have the feeling the theory behind all the concepts falls short. There are just too many different subtopics being covered instead of focusing on the main concepts of RNNs.

Great course, it will help much to be more creative using deep learning within own projects. But the last week about transformers could have been more detailed/in-depth - leaving with the feeling having some "gaps" there, especially regarding the math.

Compared to the previous 4 courses in this specialization, I felt this course a bit less on details. It may be just me not having the required level of understanding. It just felt like I could've used a little more details. Andrew is awesome as always.

The programming assignments were pretty hard this time. I think, Andrew should spend more time to explain the concepts in the video lectures. Took me a while to get this stuff since it is a little bit more abstract than the previous specializations..

This last course of the series while still being excellent, it had a few minor issues in the assignments and was quite hard compared to the previous four. Nevertheless, I still learned a lot from it and I am really grateful for it being available.

Very interesting and well taught course. The only disappointment is that it focuses almost completely on NLP. I would have much preferred working on other topics too, like for example time series with LSTM, which instead didn't even get mentioned.

You should try to leave access to the previous code I wrote in the previous weeks or help out a little in week2 exercise I really struggled to get some of the code done because I didn't have access to my previous notebooks because you locked them

The course is very interesting and well organized. Certainly the content is appropriate for the cost of the course. The only flaw, for me, is the lack of mathematical demonstrations, but I know it is impossible to cover this in a single course

This course helps you build the basics for natural language processing using deep learning methods.

The assignments at the end of every week test your understanding of the subject and improves your understanding of the topic. Highly Recommended

Good continuation of RNNs covering theory and Python exercises using a few algorithms and uses cases. I would love to see more content and more interesting examples to implement in Python. Still, this is a nice introduction to sequence models

Amazing information. My one complaint is that the assignments don't help you understand how to work with TensorFlow. Most of the time I would read the documentation on the functions and follow the syntax. Maybe it simply comes with practice.

I really liked it, however I don't feel like it really went into some of the more practicle issues with sequence models. I was left feeling like I wouldn't really know what to do in a situation where I had highly variable sequence lengths.

I preferred the first specialization courses. The explanations are not so clear as the explanations in the first courses. I will make the NLP specialization to have a better understanding. Anyway, I recommend the specialization. Very good!

It is a very good course. Andrew Ng explanations are very clear and easy to understand with a lot of good examples. On the other hand there are some confusions or errors in the backpropagation part of the programming assignment about LSTM.

I am rating this course 4 because It doesn't give any guidance about future career paths and next things to learn. The explanations are very good. I understood complex things like GRU, LSTM, Bidirectional RNN, attention model very well.

While a great introduction on RNNs, I felt there could be another week of lectures given the complexity of the algorithms being explained. Likewise, the programming exercises felt unpolished in some parts, like in the expected outputs.

Very good. To make it perfect, would have liked it for the Assignments to have less bugs (cf. LSTM backprop), and a longer course with extra weeks to present LSTM in the context of prediction (finance, weather, pattern recognition,...)