nice course as always! I need really thanks Andrew and team for this, it is very well structured & informative, provide good intuition and solid base for future self-learning of this area.

However to get full 5 for this course, there are some thing to improve ( video cuts ~ repeatable sections, sometimes mistakes, long pauses ) , also courses some of them was harder to pass trough aka from descriptions and template was not certain what to do ( one thing it is good that you need to think more and reread x-times, however sometimes grader vs 'official' output are not aligned which results in wasted time ~ hours ) ~I guess most of it was because it was rushed out too soon, but evendo very good one!

Overall, I liked the Machine Learning Stanford class' programing assignments better than the one in the deep learning specialization. For me, coming up with a full implementation of a function (and then having it unit tested by the grader), is more conducive of learning and more entertaining than a step by step, line by line guidance, as we get in the Jupiter notebooks. That said the notebook themselves are incredibly well designed and put together. I love how Andrew Ng, beyond his stature, unmatched knowledge, and outstanding teaching skills, puts his whole heart to work. That makes the world of a difference to me and helps me do the same with others. Thank you for everything!

This was a VERY thorough overview of the machine learning architectures required to tackle a wide range of natural language processing problems. It's quite dense and I had to watch each lecture several times and break it down into chunks to avoid getting lost, but now that I'm finished there I feel like a lot of technology has been demystified. The assignments really hold your hand and mostly just test your ability to follow instructions with even a hazy understanding of the weekly concepts, so you shouldn't expect to graduate and then immediately build a machine translation system from the ground up, but I do feel very ready to dive into technical interviews.

This was a good course mainly on Recurrent Neaural Networks, including LSTMs, and Encoder/Decoder networks, and the Attention model. In the last week there a brief overview of the Transformer networks and a long exercise fleshing that out. This is an interesting combination of merging Recurrent Network and a convolution style network.

The one think that has me leaving off the last star is that there were no lecture style classes training users how to use tensorflow, or how tensorflow works. That was all learned 'on the programming exercises', so it is helpful to have deep experience with Python, and with using different libraries and styles of coding.

Review of the 5 courses:

Good:

Well summarized lectures that are easy to understand. Everything is broken down into small problems making most of the content accesible.

Interesting programming assignments, which are well structured.

Bad:

Jupyter notebooks, where the programming assigments are done crash often.

On rare moments I did require extra material from youtube or medium to understand what was going on.

On the quizes, formulas are not correctly visualized and I can still see the markdown code, making it hard to read the formulas correctly.

Some technical issues in the course but I would highly recommend overall.

A very helpful and enlightening course, though it felt a bit "hand-wavy" at times. It never really felt like we were getting the full story, like I was missing something the whole time. Word embeddings cleared up a lot, but the entire course was a lot of information to digest at once. Coming from an image processing background, most of the terminology was unfamiliar, and the programming assignments weren't quite as guided as previous ones.

In the end, I think it was a great course, and I'd recommend it highly to anyone interested in the field. If you can't apply it to your work, it probably isn't as beneficial.

It's a lot of great content for becoming aware of all the various concepts in deep learning. And it does a great job of pointing at the original papers explaining all of those things. The homeworks are often very pointless: a lot of learning exactly what things they want you to copy paste, but minimal understanding of the actual algorithms, especially for the later more complicated ones. (Transformers remain a complete mystery to me, this course did not explain them sufficiently or connect them to CNN or anything else clearly, and the homework was especially meaningless in this regard.)

I'm a fan of Andrew Ng's machine learning classes on Coursera. This was my least favorite. I'm not sure if it's because of the complexity of the material or that so much material is presented in a short time, but I feel that I'm not as confident about my knowledge of the material in this course compared to the earlier courses. In the last few assignments, I felt like I was mechanically plugging stuff in without really understanding the thought process. His teaching style seems much the same as the other courses though, so it's possible this could be due to me rather than the course.

I am grateful for the opportunity to have learned from an exceptional instructor, and one of the luminaries, in artificial intelligence. Insofar as this particular course is concerned, theory was well explained, as always. I feel like there was a bit of a disconnect in the implementations, though. Some of this was just the sheer challenge of using a still-unfamiliar platform (Keras). And, in concert with this latter point, some was due to a sort of "fill in the blank" approach to using the platform. Nonetheless, that I have learned, and learned a lot, is undeniable!

the last exercise is a bit hard to understand especially

the Exercise 4 - EncoderLayerhttps://ntwjrryqcvtz.labs.coursera.org/notebooks/W4A1/C5_W4_A1_Transformer_Subclass_v1.ipynb#Exercise-4---EncoderLayer

which says You will pass the Q, V, K matrices and a boolean mask to a multi-head attention layer. Remember that to compute self-attention Q, V and K should be the same. Let the default values for return_attention_scores and training. You will also perform Dropout in this multi-head attention layer during training. 

altough Q,V,K does not come in as function inputs.

a more intuitive materials been used while teaching would be helpful to more effieciently and enjoyably grasp the concepts. what i mean is that the description or the summary the lessons been taught in a week are in the corresponding week's assignments; those summarys were more clear and visually pleasing than the inclass presentation. for example, usage of pens for drawing networks and the likes can be migrated to better animations ,etc. the crux is that the content in the course is great, but it feels like there is a good scope for improvement in presentation.

Firstly, thank to the course instructors and Dr.Ng for teaching us deep learning. You are all a gem. I enjoyed this course, and how simple it made coding RNNs. However, I believe the concepts could be simplified some more, even in the form of a pseudocode or conceptual outline. This is my 3rd course from Andrew Ng, so I know he's skilled at distilling deep learning concepts with ease. Week 1 was the best for me as the operation of the LSTM, GRU RNNs were succinctly outlined and set a solid foundation , Week 2 could be presented a less abstract way though.

I think with sequence models, the course details were very challenging. I strongly believe that do take a course in Deeplearning Specialization, one must at least learn Python from basics to advanced level. However, Andrew Ng has made it easy for a first time student with programming background to understand most of the concepts in this specialization. Thank you Deeplearning.ai for this course. I have learned some of the cutting-edge skills that can't be easily found anywhere. I have learned a skill that will set me apart from the crowd.

I really enjoyed this course. I'm not crazy about the fill-in-the-blank style of the programming assignments. I think I'd learn the material better if it just gave me the arguments and returns of the functions and forced me to write everything in between. I think it makes sense to emphasize keras in the later parts of this sequence, but I feel like I never got a basic introduction to how models in keras are supposed to be structured. Maybe there should be an assigned reading on this, if not a video or an optional programming assignment.

Great content, and leaves me set to build systems making predictions for or conversions between sequences- particularly including text posts, which are an interest of mine.

Deducted a star because a couple of ungraded exercises contained errors which had been left uncorrected; they were still valuable, especially the manual implementation of backprop one, but there's some missing attention to detail there. But the level and effectiveness and practical applicability of the course remains excellent and I'd still heavily recommend it.

I found the first week of this course a bit tough compared to all the other 4 courses in this specialization. Perhaps there should be one more week to give much more programming exerises to help understand the concepts clearly. But having said that, the last two weeks, especially the last one about hot-word, is very neatly done and provides very good understanding of such models are implemented. Overall satisfied. Thanks Andrew and team, I feel much more confident in my understanding of these terms and the concepts behind them.

I never been exposed to this subject Sequence Models before. I learned a lot from this course. But the materials is more advanced than all previous ones, especially the program exercises. The exercise guideline is helpful but not leave many guess works for students not well skilled in Python and Keras. I completed the program exercises by blindly trying different keras commands.

Little suggestion: include a short but complete example code for building Keras Sequence models in the tutorial.

Over all, a great course. Thanks a lot.

Overall, it is very good course unless for some minor problems with the assignments.

For example, in Week1 the optional assignment, there are many bugs there, one may waste a lot of time trying to figure out the correct solutions. Though, it has been widely discussed in the forum, the instructors should have updated the material or at least warn the students somewhere in the assignment to read forum ahead of time. You must admit that many won't resort to the forum only after trying and wasting enough time..

Hope may help.

Much more challenging than the other courses in the DL specialisation. It forced me to delve a little deeper into the topic in order to overcome obstacles in the assignments. Content-wise, it's a great introduction to DL for NLP. Professor Ng's explanations are perfect.

Admittedly, compared to the other courses, this one is "messier". Spelling mistakes, some contradictory instructions, and a somewhat broken notebook for the last assignment. It felt rushed and I'm surprised that a lot of the errors haven't been fixed yet.

The course itself is cutting-edge, so a 5-star for this.

But the following amount to a -1 star:

1 Too sloppy, lots of typos.

2 Wrong answers wrong expected values in the notebook.

3 Grading server sometimes runs slow.

4 Saving the notebook fails quite often.

5 Too much is done for the learners, while you could've make the programming assignments more challenging.

6 Deep learning itself has too much black magic and inexplanability in it.

I'm quite sure that harsher comments and a few 2-star or 3-star will be among the reviews.

In general, about all the specialization, I think that some of the programming assigments could be more didactive to understand the concepts of the courses and not to find what the code is doing in that specific task. For all the others aspects of the course I think it's perfect for a litlle bit more than an introduction.

For the last course, I feel that some concepts were explained very fast and for some of these i took me a lot of time to understand what I was doing.

Congratulations for all the good work you made.

The lectures were very helpful - Dr. Ng has a gift for providing context and intuition. The programming assignments were not as instructive as I would have hoped since they mostly involved "fill in the blanks" and matrix math operations. I would have liked more "ground up" development that forced me to learn how to create solutions on my own vs be dependent upon scaffolding and examples. I know that's hard from an automated grading perspective, but perhaps one keystone assignment per class makes sense.

It's a good intro to RNNs (LSTMS and GRU). Very interesting use cases for RNNs. I feel that there could have been more room to try more programming exercises for different use cases & RNN architectures. Be aware that Keras is very sensitive to changes and you will find yourself reloading the jupyter kernels repeateadly when you get stuck. This is not a problem of the course itself but it is something that could end up wasting a lot of your time chasing problems when your code actually should work.

The lecture videos are great. Andrew is a great teacher in teaching concepts at the most intuitive level. By the time I finished the course, I had sufficient knowledge to be able to read and understand the paper.

One shortcoming of the course is that - the applied coding skills you gain from the course are quite limited, as the quiz and the assignments are a bit too simple. I wish there could be an optional advanced version of quizzes and assignments that are more thought-provoking.

Another great course by Andrew Ng! This course is part of the CS230 class currently being taught at Stanford University. Only reason for 4 rather than 5 stars is that at this stage (April 2018), there are few knowledgeable mentors and virtually no Instructors present in the Forum. Course provides little introduction to the syntax of Keras, which makes for some problems implementing models. Therefore one might spend a lot of time spinning one's wheels until finding a way forward.