very tough for beginners

Keras is a ball-ache.

Amazing experience

too hard

good

As a course i think this was way too fast and also way too assumptive. I wish the instructions were a bit slow and we broke down more into designing bilstms and how they work and more simple programming excercises. As a whole i think 1 full week of material is missing from this course which would concentrate on the basic RNN building for GRUs and LSTMs and then move on to applications. I usually do not review these courses and they are pretty standard but this course left me wanting and i will consult youtube and free repos to learn about it better. I did not gain confidence on my understanding. Barely scraped through the assignments after group study and consulting people who know this stuff (which defeats the purpose of this course i believe. It is to enable me with concrete understanding and ability to build these models . It shouldn't lead me to consult others and clear out doubts .)

The lectures are pretty good up to Week 4, when the Transformer architecture is thrown at us way too fast. The increase in complexity is abrupt and huge. The programming assignments are far less helpful. I didn't really have to engage with the logic of the various deep learning models involved or understand the bigger picture of how the code works, because the starter code takes care of all that. All I really needed to do was type the obvious functions into the fill-in-the-blanks places, and then fiddle their arguments with trial-and-error until the error messages went away.

i really learned from this course some ideas on recurrent neural net, but the assignments of this course are not completely ready for learners and are full of mistakes which have existed for more than a year. those mistakes in the assignments mislead learners pretty much if they do not study some discussion threads of the forum. this course has the lowest quality among all of Dr. Andrew Ng's. before the updated versions, a learner had better have a look at the assignments discussion forum before starting the assignments.

The material really is great, but work needs to be done to improve the assignments, specifically submission and grading. On the last assignment I spent way more time troubleshooting the grader than the content of the assignment. It can be very frustrating to have to do this on a MOOC where no human support is available. It appears, specifically for this assignment based on discussion that this has been a problem for a very long time.

The week1 and 2 are good. I don't understand week 3 in the sense that most of the content is about beam search, but we get no exercise about it. Instead, we get speech data processing. I don't like this. The week4 is worse. I don't even know how to put it in words. I think you simplify things too much. The instructor should put more detail into showing the shape of matrices. I still don't know the output shape of MultiHeadAttention.

The subject is fascinating, the instructor is undoubtly competent, but there is a strong feeling of lower quality with respect to the other 4 courses in the Spec (in particular the first 3). Many things in this course are only hinted to, without many details. Man things are just said but not really explained. Many recording errors as well. Maybe another week could have helped in having a little more depth in the subject

Although the course lectures are great, as are all the lectures in this specialization, some of the assignments have rough edges that need to be smoothed out. It is particularly frustrating for those trying to work on the optional/ungraded programming assignment sections that have some incorrect comparison values, as much time will be wasted trying to figure out the source of the error.

Excellent lectures, terrible exercise material. E.g. "You're implementing how to train a model! But we've done the actual training for you already! Your exercise is to add numbers A and B! Number A is 4. Number B is 11! Enter A + B in the box below!" Also, someone did a search-and-replace and converted every sentence into an individual bullet point to reduce readability.

Unfortunately, this course is the less valuable in the specialization. Programming assignment very interesting but no introduction to Keras. To pass the assignments, forum support has been vital. I also found lectures not clear even to the point that to catch some concepts you have to google around for more resources. Unfortunately, I could not suggest this course.

Compared to the other courses in the specialization, this appears to lack depth and clarity one could expect. LSTMs and GRUs are somewhat out-dated now, given the speed of innovation in the field, and Transformers are here to stay (for now). Unfortunately, Transformers are very poorly covered.

Getting the input parameters correct for the Keras assignments is on par with the satisfaction of dropping a ring, contact lens, or an expensive object into the sink, and spending an hour looking for it inside the disassembled pipes, through built up hair debris and molded dirt.

Overall a great course, thanks to Andrew NG for his great explanations. But a very bad support, I faced many issues in submitting the assignment due to technical issues (notebook not saving) but no dedicated resource to help me. I spend lot of time in resolving my self.

Feels again like authors tried to put everything into just a couple of weeks, thus the course turned out to be messy with lots of details hidden. Even though there was a lot to learn, I am still not sure if I understand correctly how to build a simple sequence model.

Really good to understand the basics, however, it doesn't use the latest TF2 and the exercises are either trivial because too much pre-worked, or too hard because it doesn't give the information required to succeed.

This course really needs to be updated.

Programming assignment instructions are not well written (clear), and as a result it is easy to get stuck on something of little relevance to deep learning. Also, I would suggest that you make the lecture notes in written format available.

Assigments are pretty bad. I think in CNN and in RNN we should focus more on fundementals and build everything in numpy. RNN course isnt for building intuintion(deep knowledge) you just scratch surface.

The lectures cover the basic design of the models but don't help teaching you how to actually use them. I learned more by reading blogs to get the programming assignments to work then this course.

Lectures/Videos were excellent, the assignments were very poor (loads of errors in the code not corrected over 7 months since the course went live)

The course videos were very lengthy and difficult to follow. Many topics discussed in course video were not part of programming assignment

Good introduction to the concepts. Really poor quality videos and exercises. Very frustrating when working on the assignments.