The assignments were not good i think. Because they explained the consepts too long and complicated as like we've never seen these on lectures. I was waiting assignment to require more insight about architecture and less python programming knowledge. This comment is for week1 assignments in special.

Programming assignments were not to the level of the prior courses in the series. Should have more illustration of using Keras/Tensorflow. Assignments either were too spoon fed or there was too little reference information whereas prior courses had a good balance. Many of the keras links are dead.

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.

Of the courses in the specialization, this one seemed the least organized and rushed. Some of the assignments had some annoying auto-grader quirks that made troubleshooting a pain. Overall it is still worthwhile, just be ready to search forums for help during the assignments.

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.

The lessons are very good as always, but I'd like to be tested more in the programming exercises rather than literally being told what to do and then fill in missing parts of already completed code. Still super glad I took the specialisation, it has been extremely helpful.

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.

I would advise giving more tutorials about TensorFlow and Keras. Those are your main tools and eventually, in many cases we were only required to complete the gaps which don't give you a true understanding of how to use those frameworks.

The assignments are more like quests - most of the time is spent guessing what is required. The changes made require more programming skills rather than the understanding of ML principles.

The "Attention" topic was not in good detail.

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.

this one was quite fast, should cover transformer in details and also other NLP models like BERT, GPT, MORE QUIZES should to be added based on tranformer acrchitechture, GRU and LSTM should me made short as LSTM is dead

Every notebook was super well explained and made except the last one, which was very confusing, unfortunately. I did not enjoy doing that one :( Also, I think the transformers network were not deep explained as hoped.

Video content is excellent but I am not very much happy with the assignment task. There should must also be some video content based on the assignment because the some codes some libraries are not taught.

In comparison with other courses in this specialisation a lot of assignments were poor quality - vague descriptions and code logic (especially week1, asign 2 & 3) or just broken (last week3 assignment)

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.

Videos were really informative and were equally interesting, but I believe that the programming assignments lacked a bit in clarity. The instructions were really unclear, it could have been better

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

The course was great. However, coming from finance I was also hoping to see some examples which use time series so I can get a picture of how I can extend this knowledge to my specific domain.

The module was really good in explaining the concepts, but there wasn't any deep dive on the equations and mathematics behind with the results of making the code assignment harder to achieve.