Bewertung und Feedback des Lernenden für Natural Language Processing with Attention Models von deeplearning.ai

I am so happy

Thank you!

AWESOME!!!

very good

Very good

Awesome

Thanks

Best

I was a bit disappointed by the fact that although 3 instructors are mentioned, in practice we only see Younes. Lukasz just says some intro and conclusion for each lesson, I would have liked seeing him really teach. And we don't see at all Eddy.

There are also some typos in the text in some notebooks and some slides but they don't hurt the quality of the course.

Overall the course is well made. I like the fact that it teaches recent architectures like Reformer. I was surprised that trax is used, at a time where the community is only starting to tame Tensorflow2. It would have been nice to have some words about where we are in the set of frameworks: why trax and how it compares to Tensorflow2, what's the trend and priority comparing TF vs trax (features support, flexibility, targeted audience, production readiness...etc...)

Some notebooks are only about filling the blanks with a big hint a couple lines before but I don't know how to make it more complex without leaving many people stuck, especially with a new framework like trax. I also liked the diagrams very much, especially for the last week with the complex transformations for LSH.

Quite a good course overall. Thanks!

I really enjoyed the course, thank you Younes, Lukasz, Eddy and all the staff of Deeplearning.ai and Coursera. I applaud your effort in trying to teach what seem to me cutting edge NLP techniques like Transformers, even though it is a very new and complex topic. The reason I didn't give you five stars is because I didn't feel the final course on Transformers and Reformers does not seem self contained, feels incomplete, a bit too haphazard for me, unlike the first 3 courses in the specialization. I don't feel enough foundation was covered for student to appreciate the topic being discussed or what choices led to the current design e.g. why Q, K, V and not just Q, V? Why not feed NER output as context instead of just the source input? I have to search for supplementary content on the internet to round out my understanding.

The course could have been expanded to an entire specialization. There's a little too much information and the first two assignments are disproportionately long and hard compared with the last two. It is cutting edge material though, and well worth it.

Slight annoyance at the script reading meaning the videos lack a natural flow and you end up with nonsense sentences like "now we multiply double-uwe sub en superscript dee by kay sub eye superscript jay to get vee sub eye". Variables such as X_i should be referred to by what they actually represent and not the algebraic representation, because this is not how the brain processes them when they are read from a page.

The content is interesting and current, citing some 2020 papers. I was disappointed by the amount of lecture material - around 40-45 minutes per week in weeks 1-3 and only 20 minutes in week 4, plus two Heroes of NLP interviews. The lectures have the feel of reading from a script rather than engaging with the learner. They're not bad but there's room for improvement. Explanations are usually adequate but some areas could have been explained more clearly.

Programming assignments worked smoothly in my experience, though not particularly challenging: they're largely "painting by numbers".

Great course for the understanding basic concept of attention module in NLP. What I learned in this course mainly based on text data processing. (I feel that the voice or sound data will be a little different to apply.) I was able to make a solid understanding through practical examples.

One thing that I felt was lacking is

There is no theoretical background on the convergence. I don't understand why such NLP model can be converge to optimal solution. It may work. But why? I need to search more literature.

The materials in Week 3 are not sufficiently clear to explain the BERT model. The instructors sometimes repeated itself and only explain the surface but never going inside. The assignment of week 3 was designed lack of comprehension. One thing is very interesting but didn't mention is that how BERT model can achieve to be trained by the self-supervised method on almost any dataset. Would be good to show how does BERT prepare the training dataset, can it be generalized to other types of dataset?

Overall the course is a nice introduction to new or cutting-edge NLP techniques using deep learning with good explanations and diagrams. The course is a bit too easy in terms of hand-holding; a large part of the assignments can be easily completed given the hints without deeply understanding what is going on. Also, occasionally there are typos or incoherent wording which detract from the overall experience.

C​ontent wise it's excellent as always, I am not giving 5 stars, because of two reasons: a) audio including transcript is sometimes not of best quality (in english) as it would be generated by a machine b) readings are very brief and just quickly summarizing what has been taught in the video (could go in more depth). I would give 4,5 stars if that would be possible.

The course gives an encompassing overview of the latest tools and technologies which are driving the NLP domain. Thus, the focus gradually shifts from implementation and towards design.

Since the models require specialized equipment, they go beyond the scope of a personal computer and create a requirement for high-performance computing.

Great content, although the focus is definitely more on the attention mechanisms and on the Transformer architecture than on the applications themselves. Still really enjoyed it and I now feel like I have a better grasp of Transfer Learning and its associated methods. Content is very clear and well explained

This is really an interesting specialization with lots of things to learn in the domain of NLP ranging from basic to advanced concepts. It covers the state of the art Transformer architecture in great detail. The only thing with which I felt uncomfortable is the use of Trax Library in assignments.

Covers the state of the art in NLP! We get an overview and a basic understanding of designing and using attention models. Each week deserves to be a course in itself - could have actually designed a specialization on the attention based models so that we get to learn and understand better.

It would have been better if we use standard frameworks like PyTorch instead of Trax. Also, the Course Videos are a bit confusing at times. It would have been great if the Math part would have been taught as Andrew Ng Taught in Deep Learning Course.

Not new to NLP, I enjoyed this course and learned things I didn't know before. From an educational perspective, I didn't like that the two "optional" exercises were way harder than the too easy "fill in x here" assignment.

Overall good quality, but seems a bit short and content are squeezed.

I don't like the push of Trax neither, it is has yet become the mainstream and personally I don't find that helpful for my professional career.

I think that we could go deeper in the last course because you taught a lot of complex concepts but I did not feel confidence to replicate them. It was better to explain transformers with more detail