I learn to hate Trax in this course. In the assignements, Trax is used only for toy problems, and then, we use a precomputed model. Even the fastnp is used in a very slow mode. Why to learn NLP in a obscure and really bad documented framework if we will finish to use a precomputed models?

Moreover, I try to replicate the results in my own machine (or even in colab) it does not work, because Trax change a lot between versions. Again, why to use, in a course, a framework that is not stable?

In my opinion, using a new and obscure framework to tech new concepts, only because you love it, is (at least) antipedadogical.

As other course reviewers noted, this course did not help much to build the intuition underlying the methods used. The video lectures were short and the explanations, though concise, were convoluted and not clear at all. For a real understanding of what sequence models are capable of I recommend watching the lecture videos of Stanford CS224N. I

This course material is not good compare to the Deeplearning Specialization. I hope the instructor will write down to explain detail, not just reading from slide

I was disapointed by this course:

I did not like at all the use of Trax. At our level (student), we need a well established and documented library like Keras or Pytorch to illustrate the concepts. Trax is badly documented. And since the installation of the Trax version used in the assignement fails in Google Colab (!!), I had hard time reproducing the assignements in google colab.

Week 3 is just a scam since it says "go and read this blog" or "watch this video in another specialization". At that moment I simply felt robbed.

Very superficial course, just like the rest in the specialization. Quizzes and assignments are a joke. Didn't want to give negative feedback at first, but now that I am doing course #4 in the specialization, which covers material I don't know much about (Attention), I've realized how bad these courses are. Very sad.

This was another great course. I previously put on my to do list learning or reviewing about classes and I was happy to see it covered here. I enjoyed learning about data manipulation, sampling, and iteration or generation process and Trax. At first I was a little hesitant about learning a new program or library like Trax but I found Lukas' talk to be helpful and convincing. I feel Trax does simplify the coding process quite nicely. The homework seemed repetitive but I found that approach to be very useful because I think the intent was to help us familiarize with the coding process and Trax more quickly. I previously completed the DL Specialization and appreciated this course very much. Imo, someone new to DL and RNN might find this course confusing because the concepts are not explained as much in depth as in the DL Course.

Didn't like that the labs are in Tensorflow instead of PyTorch, but that is a personal preference In other terms, it is a great course, especially the last week, in which the basics of metric learning are smoothly explained

Great Course as usual. Tried siamese models but got a very different results. Will need to study more on the conceptual side and implementation behind them. But overall, I am glad I touched LSTMs.

Learning about the Trax library and solving practical problems with the library was really interesting. Siamese network architecture was great thing to learn.

This is an excellent course with some cutting edge material, and also an introduction to a new learning framework trax.

Great course! However the assignments are handholding too much step by step... I'd prefer the assignments to allow students to think more for themselves when implementing functions etc. (and only unhide hints or seek help on Slack when struggling for a long time)

First two courses were much better. It introduces trax, which is great. However, the materials of this course is already covered in the 5th course in the deep learning specialization. On the whole, great course, great efforts by the team.

Sequence models are heavy subjects and it would be unrealistic to expect a 4-week course to go into all the depths of RNN, GRN, LSTM etc. This course does a great job covering important types of neural networks and showing their applications. However, the labs and assignments could have done more in (a) helping us look a little deeper into the implementations of different NN building components, and (b) aligning better with the lecture videos.

Really Good examples: Week1 labs and assignment illustrate the implementations of some of the basic layer classes, and outline the overall flow of NN training with Trax. Week4 labs and assignment illustrate the implementation of the loss layer based on the unique triple loss function.

Not so Good examples: Week1 uses a whole video explaining gradient calculation in Trax. Yet there is no illustration of how it's integrated in backward propagation in Trax. Week2 videos and the labs/assignment are more disjoint. There is a video explaining the scan() function, but it does not show up in the assignment at all.

Compared to prior deepLearning Ai courses. the lecturers were very robotic and un natural. The explanations were much less clear and less effort was made to explain the intuitons behind formulas.

I can not give a good rating for this specialization. The teaching style seems antiquated to me. Instructors are reading text like an AI from a text ticker (you can even see the eyes moving). Sometimes the quality is not good ("plopp-noise" because a bad microphone or headset was used). The Jupyter Notebooks for the Assignements do hang often. Moreover I think the quality of the code could be better. Be warned: All the exercises are based on TRAX, which is a Python library not maintained anymore. So you will learn it here and never use it again. I'm working through the Specialization because my employer paid it. I can not say, it's very motivating. Despite my negative review, I learned something from it.

Sadly, the quality of the material is much lower than the previous two courses. Assignment repeatedly asks to implement data generators with a lot of for-loops. We should focus more on the network architecture rather than python programming. That being said, the implementation is not good either. Learners would have to learn to program anyways.

Assignments are very difficult to complete because of inaccurate information (off by one on indices and other sloppy mistakes). You also don't learn much from them because almost all the code is already provided. It would be much better if they built up your understand from first principles instead of rushing through fill in the blank problems.

The course did well in explaining the concepts of RNNs... but it may in fact have provided less knowledge than the NLP course in Deep Learning specialization.

I was looking forward to see more details on how translation works using LSTMs, go over some famous LSTM networks such as GNMT, and explain some accuracy measures such as the BLEU score.

Course could be completed without watching videos - just by using hints and comments in assignments, videos are short and shallow, choice of Deep Learning framework (TRAX) is questionable - I won't use it in production.

Despite the course is 4 weeks long it could be accomplished in 4 days - I don't feel that it was worth the time.

Compared with the Deep Learning specialization, this specialization was designed in a way that nobody can understand. Although the assignment could be easy at times, the point is being missed when people cannot really understand and learn. Bad teacher. Andrew Ng, please!

All the assignments are extremely similar.

I did not enjoy the course at all. It looks like the instructor is just reading materials rather than really teaching. He just focused on reading and did not explain anything. I took Andrew's deep learning specialization, and that course was really great. But I am so disappointed at this course. deeplearning.ai please do strict quality control on the courses otherwise it harms your brand

Oversimplified illustration of all core definitions and it is not reasonable from any sense to use trax instead of a popular framework like Tensorflow or Pytorch for the assignment. Also, the design of assignment is weak, you can barely learn anything from filling the blanks.

1) The course videos just throw out various nouns and you need to goole them to understand what they mean.

2) The assignments try their best to explain concepts in a way that often seems redundant.

For me, it is very dissapointing, time is spent on irrelevant things, like python syntax and generators in first week. There are missing video tutorials on how to use Trax.