The course is very good and has taught me the all the important concepts required to build a sequence model. The assignments are also very neatly and precisely designed for the real world application.
Great hands on instruction on how RNNs work and how they are used to solve real problems. It was particularly useful to use Conv1D, Bidirectional and Attention layers into RNNs and see how they work.
By Qiang C•
The low-level framework, such as torch, should be used in the assignment. keras is complicated to understand for newbie.
By Anxo T A•
Great course, specially the programming assignments, they help much mor than the videos to undertand the core concepts.
By Holman B•
Had some issues related with the jupyter notebook. Sometimes I had to restart the kernel to get the keras model working
By Anand S•
I think a totally different course for NLP & CNN neeeds to be rolled out including their implementation in tensorflow.
By Marcin K•
Last notebook causing server problems. Large amount of material (theory) covered by compressed programming excercises.
By Naveen K m•
Great course content and well explained by Andrew, looking forward to apply the learning to solve real world problems.
By Agustín D•
Some items on the assignments were confusing or misleading. But the content of the course was rich and well explained.
By Paulo S•
Excellent course. It would be better, however, if I could easily download the course slides and notes for quick recap.
By Jérémy M•
Really nice course but some programmation exercises isn't well built. (Compared to the other courses of this section)
By Niranjan K•
Week 3 last assignment must be improved.I faced a lot of problems related to submission.All other aspects are amazing
By Li P Z•
Excellent as usual, but not quite up to the usual standards, I felt some of the lectures and exercises were rushed...
By vincent p•
Cool exercises and good explanation, just too much focus on text mining and too little on actual RNN's if you ask me.
By Václav R•
Nice intro in recurrent neural networks.
I'd prefer more focus on why the architectures are designed the way they are.
By Scott R•
I would have liked to have had an assignment covering beam search but overall it was excellent introduction to RNNs.
By Lin Y•
overall it's great, but I think this course is a little bit high level on RNNs, I expected more content on GRU/LSTM.
By Andrey S•
Great course but it took them forever to finally open it.
The course also has issues with submitting last assignment.
By NIKHLESH P•
Text Processing exercises should be added. Most of the examples are from image and speech. Overall good experience.
By Sachin k•
Great Course. But could improve on explanation part. And could teach more about architectures such as LSTM and GRU.
By Tianpei X•
Great course ! However, there are several errors in the project assignments and it has been delayed for two months.
By Cameron W•
I felt like important concepts were glossed over far more in this course than previous courses in this curriculum.
By Pengfei J•
The update and correction of error should be more effectively and actively managed. That's the only error so far.
By Andres F O J•
The assignments should be after each topic or lecture because in the end is difficult to enhance the knowledge.
By Claus E•
Good course, but the errors in the last exercise was annoying and I missed a bit more about speech recognition.
Only complaint is that the exercises are too easy when all answers are practically given in the hints section.
By Jan Z•
Interesting topics but some fairly frustrating assignments. Happy to get a better understanding of NLP though!