It was a bit repetitive of the 'Sequence Model' course from the Deep Learning specialization, only with the exception of implementing in TRAX.

Assignments are good. Can we have these using pytorch. Or better: Can a person choose his own language and build entire code on that !!

Great course, although would have been better if assignments were implemented in Keras or PyTorch. Otherwise, definitely worth it!

Great information, but some of the assignments had errors and there weren't many interactions from the TAs on the Slack or Forum

Great course! I would have liked Keras/TensorFlow 2.x or Pytorch to be used instead of Trax which is not as frequently used.

Interesting and well explained altough assignment excercise are difficult to understand and they are just focus on Trax

The clarity of exposition was superb! 1 star less for using TRAX. I would have rathered to use Keras or Tensorflow.

We might have included little bit more details on dimensions of the inputs and outputs of the Sequence models.

T​he course is very good, but its not complete in itself. The way course was taken and everything is good.

Overall the content was great. Please make sure that errors in the notebooks are corrected.

The course is designed quite well to boost understanding of Sequence Models in great depth

Excellent course, but probably worth doing the deep learning specialisation first!

I dont like to use TRAX. If it is using tensorflow, then I will give 5 stars

I prefer that the lecturer using TensorFlow instead of Trax for exercises

Almost perfect. More Explanation in implementation is needed.

Good information, but some assignments were an embarrassment.

Not as good as original courses by Andrew

it was good but it could be better

some errors in the assignments

NA

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 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.

I​s 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!