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.

This course is quite complete as it presents major hot NLP tasks with transformers, but unfortunately it presents only one framework: Trax, and not Hugging Face's which is also really useful and used in the field. I would have liked to have a lesson about chatGPT like models.

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.

A good introduction to the transformer model. Some of the exercises felt a bit more lead (more code written by the instructor) than earlier courses - this may be to do with the volume of material necessary to cover transformers.

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.

A good course, that I can recomment without a doubt. I would strongly recomment to complement it by reading the additional ressources (see week 4 -> "References") as well as hugging face tutorial for NLP.

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

The lectures need more insights to understand not only the 'how' but a reasonable amount of the 'why', too. Andrew is very good at doing this in his lectures and provide his intuitions and insights.

It could have been better if Transformers library from hugging face is explored more. and topics like Vision Transformers and utilization of Transformers for computer vision is explored.

It's a great course, more difficult than I thought but very well structured and explained. Although more didactic free videos can complete the lessons from others websites.

great course content but go for this only if you have done previous courses and have some background knowledge otherwise you won't be able to relate

The content is great, but it will be even better if we have a more in-depth understanding of the knowledge rather than a very quick crash course.

good course covers everything i guess, the only down side for me is trax portion, i would've prefered if it was on TF maybe, but still great job

The course covers cutting edge content and the exercises are well paced. Found the transformer lessons a bit difficult to understand.

Not up to expectations. Needs more explanation on some topics. Some were difficult to understand, examples might have helped!!

need more detailed explanation in the last course of this specialization, especially Attention and BERT models.

This is the toughest AI course I have taken. I hope your Python coding skills are better than mine.

It's a really good course to learn and get introduced on the attention models in NLP.

An amazing experience throughout the state-of-art NLP models

Labs required a bit more context, to understand.

The programming assignment is too simple

great explanation of the topic I guess!