Compared to the previous courses, this was a disappointment. There is not as much content as I expected and the homework exercises are not well prepared. If one spends more time with debugging than with "learning concepts" in a basic course like this, then something seems wrong.

Moreover, in a situation where so many people pay so much money (because of Andrew Ng's credit)...

That was tough, how the weights are stored and their dimensions inside the 'time steps' can be explained by adding one more video, btw the course is awesome if you want to learn the basics of sequence models, you should have completed the previous 4 courses before diving into this. I will always remain thankful to Andrew Ng for providing this type of platform.

Positives : Excellent lecture material. Assignments broadly are well structured. HIgh bar set by Andrew Ng. Negatives: Assignments have too many errors and mistakes as of Jan 2019 (especially but not only in the optional / ungraded sections) for me to be confortable 100% recommending the course. Instructions for assignments are also not fully fleshed out.

This course is good for introduction to sequence networks, but I felt this is not at par with the previous course 4 (CNN). This feels a bit hurriedly done, with many important things only just touched upon. This should have been a 4 week course like the previous module. Then due attention could have been given to the field of speech, audio, sequence domain.

The course is generally good. However there are some issues with lecture videos editing (some sentences are said multiple times), and with activities (e.g. default settings hardcoded in one of notebooks, didn't let have output shown as reference, also in some cases automated grader has some assumptions, which need to be found using trial and error method).

I've got mixed feelings about the whole Specialization. Many very interesting topics, but on the other hands I don't feel like there's any takeaway knowledge for me. Until the very end I've been feeling completely lost in the exercices. I'm proud to have been able to hold on until the end but I'm not sure it's been an useful use of my time.

Really interesting course with fascinating applications. However, in terms of difficulty, it is a significant step up from all the previous courses. A lot of time is spent figuring out the syntax even though the concepts are crystal clear. ( Probably as it is a collaboration with NVIDIA). The programming assignments could be improved.

The course was great, as ever. But some of the programming exercises were very frustrating. Oscillating from very easy to very difficult, with some unclear (and sometimes erroneous) instructions. I felt this was in sharp contrast with the previous 4 courses of this specialisation, for which the course and exercises were perfect.

Great lectures, great teacher!

I would have given 5 stars but for the problems in the exercises / grader. Some problems that are know for weeks or even months are not resolved. This causes many wasted hours for many hundreds of students. Please solve this and make it a 5 star course.

Many thanks to Andrew Ng and the mentors!

The lectures were OK ... better LSTM tutorial by Chris Olah

The exercises really need some review ... very frustrating ... and not all that illuminating .

The course was a good intro to DNN ... but I think either replace Week 3 - Structuring ML Projects with a course on Keras ... or add a course just on Keras.

The course does not explain how to use Keras (it's assumed you've finished the previous course). What's more a lot of code parts is implemented in some difficult way (for loops instead of Python's builtins and idioms like any or list comprehensions). I'd love to see more materials on speech recognition.

I guess as the subject matter becomes more complex, more training is required on the underlying frameworks being used- Keras, TensorFlow etc. Did not feel that sufficient time was spent on understanding the underlying frameworks. Also the TA work is of spotty quality. But I love the way Andrew teaches.

For me, there was a large gap on time between when course 4 and 5 were offered (months). This unfortunately was enough for me to forget everything I learned about Keras.

Of course, this course assumes you know Keras so I was behind for the labs

Material is interesting though.

Too many thing introduced in programming assignments without explanation. Why the high dropout values? Why sometimes one dropout layer, sometimes two? Many things are just given as a formula, and not explained in a way that would let me make my own network for my own problem.

Had to rate this lower due to problem with the final assignment. Submission and saving situation was a nightmare, I had to redo my work several times. Please fix this, it's a real downer at the end of the course. Otherwise, content stellar as always.

The course content is pretty good for breadth. However, it falls short in going into depth. Assignments need to be more open-ended and probably a bit more involved. It appears that we are cutting and pasting code that is already written in comments.

This course presents an interesting review of several strategies that are part of the state of the art. However, it is impossible to assimilate how they work in the time devoted to each one. The "fill in the blanks" exercises do not help much.

This course gives a nice overview of sequence models. If it is true that I do not have an engineering background, I felt it got sometimes a little bit too abstract as compared to other courses of the specialisation. However, I recommend it.

The programming exercises can be better polished, there was quite a few errors that caused unnecessary confusion to the students. Many times, I felt like I was fighting with the Keras/Tensorflow API rather than solving a ML problem.

Courses had some issues with the grader, and there were some instances where the expected output in the assignment didn't match the actual output, despite it being correct.

See forums for a range of complaints on the matter.

Need more detailed explanation and programming assignments are way too easy.I would suggest to make advanced courses for people to improve their knowledge keeping all this courses also considering not all feel it very easy.

With respect to the others, this one seems to be prepared almost in a hurry and the learning curve is very steep and sometimes the programming assignment don't have a nice progression as the others.

Quite a few bugs or abstractions in this course, in comparison to the others the projects feel a bit rushed and pushed together. Andrews's explanations and video lectures were still great though.

this course is the most difficult in deep learning specification, but i think Andrew NG should design more homework for word embeddings and bidirectional rnn, i do not understand how it works yet

I gave 5 stars to other courses in this series but this one doesn't deserve 5 stars. There were many typos and bugs in the assignments compared to the other courses of the specialization.