Lesson 8 - Official topic

Applying CNNs to NLP is apparently a thing, at least before transformers!


End of the class :frowning:

Thanks for a great course amid this pandemic! :mask:

I learned a lot even though I went through last year’s course.

I hope Part 2 is coming up soon! :slight_smile:


try https://paperswithcode.com/

1 Like

Mikaela from the USF Data Institute will distribute certificates to those registered for the course (although unfortunately they are not signed).


Thank you @jeremy and @rachel as always, awesome new material in the fastbook! Can’t wait to get the official O’Reilly version. I’m still working on COVID19 and will talk to you all again soon!


Especially the big “Browse State of the Art” button.

1 Like

I got the book, do you think it will be possible to have your autographs (all of you 3) on it, in the future? Thank you so much, amazing journey


Thank you so much for the best weeks of Deep Learning even under these stressful times! :pray:


Thank you Jeremy, Rachel & Sylvain for all your untiring efforts. This will be a memorable experience.


Thank you Jeremy, Rachel and Sylvain. This has been an amazing journey and I’m sad it finished but excited of everything you taught us and it was amazing to be part of it and to build things thanks to your teachings. Very grateful for being part of the course :slight_smile:


Thank you for a great course!!. Wonderful learning experience!! Looking forward to meet you again at Part II!!

1 Like

Thanks @rachel, @jeremy @sgugger

Thank you a thousand times!

Loved the course! Very sad it’s over.

Thanks again @sgugger @rachel @jeremy

1 Like

Thank you all for the course! Can’t wait to re-watch all the lessons and focus more on implementation and projects. Looking forward to any future content as well!

When will the course be available to the public?

Is Rachel’s NLP course based on fastai v2 or v1? Thanks!!

Thanks @sgugger, @rachel, @jeremy! Really enjoyed this - looking forward to Pt 2!

It’s on v1

1 Like

Hmm… I am not sure how a Siamese network would work in @sbrunk’s example of TD+NLP data? I thought Siamese network uses the same layers/models for the two input, but the TD and NLP data should need different layers/models/archi’s to process? Curious to hear more about what you think is possible to do though, with Siamese on TD+NLP : )



1 Like