Last exercise need to be clafired more, I think.

Not as good as original courses by Andrew

Some assignments are not managed correct

it was good but it could be better

some errors in the assignments

NA

Very mediocre course and specialization, in my opinion. All of the topics in this course are much better covered in the Deep Learning specialization by Andrew Ng. There is no didactic element here, it seems like the lecturer is just reading out bullet points from a script. On the practical side, the examples in courses 3 and 4 all use Trax, which I am finding to be a very questionable choice (in real life, there are Tensorflow/Keras and PyTorch, so it would make sense to learn how to implement these models in one of those libraries while also getting valuable practical experience with them; While PyTorch has great documentation and Tensorflow's documentation is at least okay, the documentation for Trax is really quite minimal and you cannot find examples anywhere, neither in the documentation nor on Stackoverflow). The examples are hardly more complex than what you have to do on DataCamp.

Feels like the whole course is designed to achieve the assignement, not focused on explaining the core concepts or giving inuitions behind the ideas. For example, the lab notebooks (non graded notebooks) are basicually chunks of code giving the answers for the assignment. The assignemnt are very well done though.

Andrew Ng does a better job in giving intuitions, perhaps by going back and forth between concepts, by referring to research papers and trying to explain the basic idea behind them. Besides, the course gives no references.

Minus point : the course uses trax, a deep learning framework developped by google brain which is not maintained anymore. Keras looks pretty similar and would have been preferable.

The 4th week on Siamese networks was well done. The Weeks on RNN GRU and LSTMs basically gave the equations and some intuition but most of the emphasis was on building a model with them using Googles TRAX Deep learning Framework model. Which the lecturers believe to be better than Tenserflow2. At least when it comes to debugging - it isn't. Make the smallest error (say with shape parameters) - and you get a mass of error messages which don't really help. Now at least for shape errors there is no excuse for this - since all that is needed is to run checks on the first batch of the first epoch that pinpoint exactly where there's a shape discrepancy.

Despite the theoretical underpinings I do not feel this course lets you write an NER algo on your own . Majority of these courses have been using data Whats supplied by coursera and so is the case with models. In real life we have to either create this data or use some opensource data like from kaggle or whatever. I think it'd be better if we orient the course using publicly available appropriate data and models trained by students to be used for actual analysis.

Like some of the other courses in this specialization, this one has promise but comes off as a so far somewhat careless effort compared to the usual quality of content from Andrew Ng. The lecturers are OK but not great, and it is unclear what the role of Lukasz Kaiser is beyond reading introductions to many of the lecture. There is a strange focus on simplifying with the Google Trax model at the cost of not really teaching the underlying maths.

The third course in the NLP specialization has been a bit of a disappointment to me. I feel that the video lectures are very robotic and don't add much to the written lectures, mainly reading out formulas and technical details, which can be tedious, especially when articulating any subscript or superscript detail in a formula rather than providing some intuition.

The course requires a solid background on deep learning, it does not explain in detail the LSTMs or how is the programming part keeping the weights of the 2 parts of the siamese network identical.

Is Trax providing other ways of generating data for siamese networks for training other than writing a custom function?

I regret a lack of proper guidance in the coding exercises, compounded with the incomplete documentation of the trax library. I also feel we could build models with greater performance. An accuracy of 0.54 for the identification of question duplicates doesn't seem to be the state of the art...

You could do better!

Too much focus on the Data generator in the assignments. There should be a library function in Trax to do it. Might have to do some data preparation before hand but the generator should be a standard library function. Also, I hoped to learn a bit more indepth in terms of entity labelling.

The course videos are too short to convey the ideas behind the methodology. It requires understanding of the methodology before following the course material. Also, the introduction on Trax is fine, but would prefer to have a version of the assignments on TensorFlow.

Good videos, however assignments weren't up to par with videos. Often I had to write assignments that weren't very much related to the videos and the stuff that were actually in the videos was already implemented.

Good course teaching the applicatons of LSTMs/GRUs in language generation, NER and for matching question duplicates using Siamese networks. Would have been more helpful if there was more depth in the topics.

This course is good for practical knowledge with really good projects but it lags in the theoretical part you must be familiar with the concepts to get the most out of this course.

I am now confusing by too many Deep learning framework. Also the content is somehow repeated with the Deep learning specialization.

I just want them to use Keras, since I have no inclination to study new shiny fancy framework such as Trax.

Great Course! But it would be better if use Tensorflow or Pytorch, Trax is not very friendly to Mac users.

Lectures are quite good, but assignments are really bad. Not helpful at all

assignments were easy and similar.learned less than expected.

Content is interesting, but some details are under explained.