This a the last and the most anticipated course for me. It's hard, informative and most useful. I've got chance to learn some popular and powerful methods within the years, like word embedding and attention mechanism. I start to understand the way deep learning community deal with NLP, i.e., ingenious design of network structure inspired by the pattern human beings perceive the world. It doesn't enjoy solid foundation as statistical learning does, but is works and suitable for engineering. That's astonishing! I hope I can combine deep learning with traditional methods to better understand NLP.

I just want to say Thanks to Andrew and the team for a great content. I may not be able to create award winning NLP models after this course, but I have learned a bunch about them. Lots of work went into creating great videos and even more in creating the programming projects. I really appreciate the format of the programming assignments. For someone with not much experience in DL, they were pretty close to perfect: I felt I was not left to fend for myself, yet they were not overly simple and forced me to solidify what was thought in the lectures and learn better. Thank You Andrew and team!

Thanks very much for Andrew Ng and the other teachers, who made a series of these awesome classes including videos or programming works running on the jupyter-notebook. And also thanks the finical aid provided by the Coursera, I can't finished this course without your generous help. After a hard work with the Deep Learning classes, not only gained the knowledges, but inspired by the spirt from Andrew that "try to help people with your technology", which actually changed my mind, I will study more, do better to remember that in my life. Thank you and hope the world be a better place.

Awesome Course! Learned a lot. Would highly recommend this to anyone willing to learn NLP, Sequence Modelling, Word Embeddings, Machine Translation and related stuff. The course builds from fundamentals of NLP like RNNs then LSTMs/GRUs to Word Representations to Sequence-to-Sequence Modelling. At the end you'd learn so much that by just looking at a single slide of an overview of Trigger Word Detection you could make the entire DL model yourself. You'd be fluent with Keras after completing this course. I'd like to thank the Instructor, the Teaching Assistants and the mentors.

I have taken now 6 or 7 courses conducted by Andrew Ng, including this series of 5, and it is absolutely amazing to me that a person of his eminence & level of achievements would even take the time to offer courses like this series. And, what makes it still more incredible is his sincerity, humility and genuine enthusiasm for the subject matter and his gift for explaining it, especially when it becomes very complex. It is just so inspiring; he is truly a rare & exceptional person & teacher and I look forward to taking whatever other courses he is conducting or recommending.

The last course is a little bit more difficult than the previous! Although I majored in Civil Engineering and got my Master's degree in 2018, since I finished the Machine Learning class of Ng 2 months ago,I found this art is so charming and powerful ,so I continued to finish the CS229, That is also a wonderful course!! And today,this DL course was also completed, now I am attending the CS231N class~ Thank you Ng ,thank u cousera, because of you,I have a chance to attend those amazing course from the most famous university. Ng,thanks,you are doing a great thing,thank u!!

Amazing course. This course was very informative. The assignments gives students the ability to code in keras and use those NLP models described in lectures in the programming assignments.

I felt there was enough help during the programming assignments from the instructors /mentors on the discussion board.

The only thing I wish about this course is to let the students program the Data science part of the programming assignment. I felt some of the details of the pre-processing of the data was already done. It would have been nice to do that or add as an optional part.

Very frustrating grader. Really time wasting. What is this team trying to accomplish with such disorganized efforts? I hope to see more improvements in the future. I have just completed week1's assignments and revising my reviews from 1 to 4 because the course content is really good and has softened the disappointments caused by the grader.

After week1, the grader frustrations eased as it was working more and more consistently. Most importantly, I learned lots of cool stuff and so I am revising my reviews from 4 to 5. I hope all grader issues are now resolved.

Superb instruction mode that strikes a good balance between the nitty gritties of working with language data and actual model building. The only disappointing bit about the latter parts of this "sequence models" course was that the models (esply the transformer models) are too time consuming to train in the context of a programming assignment and so we used pretrained models to check results. This was a bit of a let down (albeit justifiable) since the satisfaction of seeing the transformer model we coded perform still seemed far away (also understandably).

A huge thanks for this journey in the specialisation. The material is of high quality and the pedagogie of high qualiber! My only regret is that the course is not longer :P I would have love a course about GAN for example. Also an advanced followup on this specialisation would be amazing. Wanting to learn more i will probably continue my path with https://eu.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893?referrer=nvidia&utm_source=nvidia&utm_medium=partner&utm_campaign=referrerpage, however i would love to continue with deeplearning.ai !

With time and perseverance, most of us are able to complete this final course of a rather challenging specialization. I particularly like the final course because the programming assignments combine architectures and techniques we learned in previous courses/weeks including CNN, RNN, GRU, Attention, LSTM, just to name a few. We also repeatedly write codes in Keras which give us a lot of practice and without being bogged down to every little detail. Big thanks to Andrew and team for making this specialization available to world's deep learning community.

You can learn deep learning from scratch, learning the detailed mechanics of and implementing forward pass and back propagation of MLP, CNN, RNN and LSTM using numpy. You will also learning a lot of useful tricks in practice here and there. That's exactly what I am looking for, as I don't want to just use a NN framework like a black box. You also get to learn a good part of the functional API of TensorFlow (the sequential API is much more obvious). You also get a lot of exposure to many diverse typical applications, which is very eye-opening.

El curso es muy bueno, particularmente estoy muy agradecido con COURSERA, por darme la oportunidad de hacer los cinco cursos de la Especialización en Deep Learning con ayuda economica y permitirme tener acceso a este tipo de capacitacion y certificacion. Muchas Gracias…!

The course is very good, particularly I am very grateful to COURSERA, for giving me the opportunity to do the five courses of the Deep Learning Specialization with financial aid and allowing me to have access to this type of training and certification. Thank you very much!

This is a superb module which provides you with the skills that will enable you get going fast in developing real world applications that can be modeled as sequence data. You learn of the latest state of the art techniques of developing sequence models using techniques such as GRU's, LSTM's, how to debug them and also how to employ Attention models to make your models that much efficient for problems in NLP, Machine Translation and Speech Recognition. This course is a must for anyone who wants to be a sound practitioner of AI. I love it.

Though there are some minor lost clarifications in the flow, the general learning experience of this course is overwhelmingly practical and relevant to many real world scenarios. Personally felt this course completed the knowledge graph (of course I only have a preliminary understanding of everything) and opens many doors for future learning.

One nit-pick is Keras documentation can be annoying confusing and misleading at times. Would suggest to revise programming assignment instructions based on some popular threads in Forum discussions.

As usual, Andrew makes AI almost look easy. I have one comment about programming exercises. There are errors in the text sometimes and, at least personally, I don't have a habit to check discussion forums first, before starting work on the assignment so these things were sometimes a source of lost time, scratching my head where have I gone wrong only to find that the results are correct and it was the notebook that was not up to date.

This aside, I would recommend this course to anyone interested in AI. Keep up the good work!

Finally, I understood LSTMs, thanks to this course, thanks to Andrew! Before this course, I spent many hours reading papers on LSTMs and trying to figure out what is going on with all these "Gates", but couldn't understand intuitions behind them. In this course not only I learned and understood them, but also I learned a lot about machine translation and speech recognition which I was frightened to approach them. This course gave me all fundamental concepts and tools that I needed to be able to deal with sequential data.

Completed Deep Learning specialization in the DeepLearning.ie. I really liked this course, it will be useful not only for the beginners, but also for the specialists, which want to have an overview about current neural networks trends and see the interview from the best specialists of AI. To make this course perfect I would recommend to fix some errors in the theory of programming assignments (specially in the last 2 courses). Sometimes this issues are confusing and forcing to check on the forums correctness of the task.

The material was interesting and very clear (like previous courses in this specialisation)

I think due to the complexity and nature of these subject, it's hard to grasp it all based on this programming assignment because in each exercise I was only able to implement a fraction of the "big picture". It would be very helpful to have a kind of "running" assignment, in which you start with an actual blank slate, and build all the building blocks from scratch so I can have much better understanding of the bigger picture.

Lectures are great as expected. Thanks Andrew for everything! Programming practices are so good that everyone can see the designers must have put tons of hours to prepare for learners. Especially all the steps about the GRU, LSTM, Attention and etc are listed very clearly with no confusion. As of today as far as I know this course must be The Best online course about Sequence Model. Will keep learning from going over all the materials it provides. Debugging is a part of learning though painful and time consuming.

Great course!!! The best online course I have ever taken! I enjoyed almost every day I participated in that specialization, really an educational treasure! It is so comprehensive and detailed at the same time. Due to the good presentation of the topics it was really understandable. The only thing I would wish for future participants: please make it easier to get the complete Jupyter notebook environments from the Coursera platform once completed. I spent a lot of time here - even after consuming the related blogs.

Great content! Andrew's lectures are great as always. The assignments are absolutely exciting and fun. Obviously the team put a tremendous effort on the programming exercises to make them doable for laymen yet not trivial. The exercises avoid using libraries (like Keras and TensorFlow) at the very beginning. Instead, they started with the more basic Numpy implementations. After these practice, I am able to grasp what each layer is actually doing.

My only suggestion is to correct some trivial typos in the Notebook.

I like how it injects the idea of a subjective language/audio processing into a mathematical model learned by a computer. The whole team managing this class has been very careful in setting up the quizzes and machine problems to let the students get their hands dirty on machine learning projects. I gave 5 stars because it encourages people to read research papers, tells if a particular paper is hard to read, recommends papers that are easy to read. This way, more people can be interested in the world of research.

Thank you for helping me to get over the initial barrier to entry in NLP and audio data with this Sequence Models course. LSTM's are core to so many current technologies, and building them from scratch has provided me with good intuition for working with them. There was a good mix of numpy and Keras, as well as having the homework be clear enough to work through without getting stuck on minutia. It's always a pleasure to listen to Andrew Ng walk us through a problem with clarity, simplicity, and enthusiasm.

The course is well thought and easy to follow. I regret not starting on this earlier in my quest to understand RNNs. It is the best source I found through shopping around. The courses is scheduled for three weeks, but is actually doable in an afternoon + a morning session if you have some python programming skills and enjoy 2x on your lectures. My one complaint is not with the course itself but the whole series. I mislike the subscription model for payments. I prefer a one time payment for life-time access.