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.
I was really happy because I could learn deep learning from Andrew Ng.\n\nThe lectures were fantastic and amazing.\n\nI was able to catch really important concepts of sequence models.\n\nThanks a lot!
By Gregory S•
Excellent content, although the exercises - at this stage of specialization - should focus more on NN architecture, than on pure computational and matrix slicing tasks, imho.
By Kaan A•
Even though it has some flaws in audio clips and homeworks, programming assignments are fun to do. Great real world applications on this whole specialization is just perfect!
By Lap-hang H•
The content was quite good as with previous courses in this specialization. Just dropping a star because week 1 material wasn't as clear to follow as the rest of the content.
By Juan Z•
Compared to the first two sections, I don't think this section is better than those. Anyway, I learnt some concepts about sequence models which I need to dive into in future
By Tang Y•
The videos are of high quality as always, while the programming exercises had some error in it. Compare with the previous few courses this one seems not polished so well.
By Steven W•
I learned a lot, but it really felt like there could have been a whole other week's worth of material, especially talking about newer innovations like transformers, etc.
By Jonathan H•
This course and assignments helped me understand concepts in NLP. However, it is a little less comprehensive compared to the previous courses in the deep learning series
By David J•
Thank you Deep learning team for putting together this course. The course has really helped me understand the various possibilities with the knowledge of deep learning.
By Bhavul G•
The first week was a bit too tough compared to the second and third. So, I felt it was a bit hurried. It could have been distributed into two separate weeks, perhaps.
By Cristhian P•
This course was very useful. I would make the programming assignments for the first session a bit clear. Other than that, everything was easy to understand and clear.
Good, but not as in depth as the other lecture series I found. It is faster paced and skips over much more of the detail at which they go into in the earlier modules.
By joris b•
If the programming exercises weren't plagued by some bugs, I would have given 5 star. It's a very complex subject matter, but Andrew takes you through it by the hand.
By Robert L•
I feel week 2 and week 3 materials were covered a bit too quick. Would appreciate more explanation of the implementation details of beam search and activation model.
By Amir A•
It was really helpful, every topics explained very well. However, in my standpoint of view, It did not cover some part in sequence learning, like graphical models.
By Jürgen R•
Really nice course. Very informative. Unfortunately some programming exercises were a little buggy (the grader especially)...only a total reset of notebook helped!
By dann p•
this course provide an adequate and what you want to know about recurrent neural network but it does require lots of programming skills to accomplish this course.
By Tom S•
Good course, but I needed more time than expected, especially for the exercises. For me, that was the most demanding course out of the 5 from that specialization.
By Timothy A•
A lot of cool material covered from RNNs to LSTMs to Sequence Modeling. But it is a lot to grasp and a lot to understand. Overall, rigor and course is decent.
By Yogeshwar D•
programming assignments are not teaching us to code independently because of the helpers functions given in utils file. Feels like copy pasting the assignments
By SIRAM N N D S K•
It is a really awesome course for those who want to get started with deep learning methods in NLP.
Got a very clear insight about GRU,LSTM,RNN,Word Embeddings.
By Rohan S•
The course is really good, one star less because it requires keras understanding to complete assignments properly. Including a basic intro of keras will help
By Nitin S•
The time allocated to some of the assigments should be increased. The estimated time in many cases seems to assume that one is aware of Keras and Tensorflow
By Cazaubieilh G•
To the point ; sometimes it would be nice to explain the research papers more in depth, and link other courses to have more formal mathematical explanations
By ignacio v•
Give us one more week to learn RNN for time series in economics, finance, etc!
Programming Exercises need more hints and more training in simple Keras models
By Péter D•
Well-made course, but unfortunately there are tons of mistakes in the programming assignments - in the comments, formulas, even in the prepared code pieces.