Uploaded January 2020 | Updated September 2026, 1 week ago
Google just released a new Neural Network architecture called "The Reformer" that helps make the state of the art in Natural Language Processing available to people with a smaller budget. They introduced two key ideas here, "reversible layers" and "locality sensitive hashing". Both of these concept build on about a decade of research in neural networks applied to NLP, so to truly understand the Reformer, we've got to understand the timeline of deep learning based NLP. In this episode, I'll take you on a journey through the advances that lead up to the Reformer, what the relevant applications of it are, and how you can get started building your own text application with it today in a few lines of Python code. All the code I demonstrate in this video is from various developers across GitHub, I do not claim any of it as my own, I am using them as examples to enable more people outside of Academia to understand modern NLP. Enjoy!
TWITTER: bit.ly/2OHYLbB
WEBSITE: bit.ly/2OoVPQF
INSTAGRAM: bit.ly/312pLUb
FACEBOOK: bit.ly/2OqOhx1
Please subscribe for more educational videos! It would mean so much to me.
Google's Reformer Code (Text Generation):
colab.research.google.com/github/google/trax/blob/master/trax/models/reformer/text_generation.ipynb
Bintang's winning code (forked, yes, but thanks for bringing this to our attention, cool repo!) :
github.com/baswam95/SUAVE
Are you a total beginner to machine learning? Watch this:
youtube.com/watch?v=Cr6VqTRO1v0
Learn Python:
youtube.com/watch?v=T5pRlIbr6gg
Free Natural Language Processing Curriculum:
youtube.com/watch?v=GazFsfcijXQ
Natural Language Processing:
youtube.com/watch?v=bDxFvr1gpSU
Sentdex has some great playlists on NLP:
youtube.com/watch?v=FLZvOKSCkxY
Google's Initial Reformer Blog Post
ai.googleblog.com/2020/01/reformer-efficient-transformer.html
Word2Vec Explained:
youtube.com/watch?v=LSS_bos_TPI
FastText Explained:
youtube.com/watch?v=4l_At3oalzk
Transformer Explained:
youtube.com/watch?v=iDulhoQ2pro
Jay Alammar is an ML animation beast:
jalammar.github.io/illustrated-transformer
BERT explained:
youtube.com/watch?v=BhlOGGzC0Q0
Backpropagation explained:
youtube.com/watch?v=Ilg3gGewQ5U
Beat used for Hashing rap:
youtube.com/watch?v=zkaT8-NhD5c
Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams!
Signup for my newsletter for exciting updates in the field of AI:
goo.gl/FZzJ5w
And please support me on Patreon:
patreon.com/user?u=3191693 Join my AI community: chatgptschool.io Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available): https://www.wagergpt.xyz
Google just released a new Neural Network architecture called "The Reformer" that helps make the state of the art in Natural Language Processing available to people with a smaller budget. They introduced two key ideas here, "reversible layers" and "locality sensitive hashing". Both of these concept build on about a decade of research in neural networks applied to NLP, so to truly understand the Reformer, we've got to understand the timeline of deep learning based NLP. In this episode, I'll take you on a journey through the advances that lead up to the Reformer, what the relevant applications of it are, and how you can get started building your own text application with it today in a few lines of Python code. All the code I demonstrate in this video is from various developers across GitHub, I do not claim any of it as my own, I am using them as examples to enable more people outside of Academia to understand modern NLP. Enjoy!
TWITTER: bit.ly/2OHYLbB
WEBSITE: bit.ly/2OoVPQF
INSTAGRAM: bit.ly/312pLUb
FACEBOOK: bit.ly/2OqOhx1
Please subscribe for more educational videos! It would mean so much to me.
Google's Reformer Code (Text Generation):
colab.research.google.com/github/google/trax/blob/master/trax/models/reformer/text_generation.ipynb
Bintang's winning code (forked, yes, but thanks for bringing this to our attention, cool repo!) :
github.com/baswam95/SUAVE
Are you a total beginner to machine learning? Watch this:
youtube.com/watch?v=Cr6VqTRO1v0
Learn Python:
youtube.com/watch?v=T5pRlIbr6gg
Free Natural Language Processing Curriculum:
youtube.com/watch?v=GazFsfcijXQ
Natural Language Processing:
youtube.com/watch?v=bDxFvr1gpSU
Sentdex has some great playlists on NLP:
youtube.com/watch?v=FLZvOKSCkxY
Google's Initial Reformer Blog Post
ai.googleblog.com/2020/01/reformer-efficient-transformer.html
Word2Vec Explained:
youtube.com/watch?v=LSS_bos_TPI
FastText Explained:
youtube.com/watch?v=4l_At3oalzk
Transformer Explained:
youtube.com/watch?v=iDulhoQ2pro
Jay Alammar is an ML animation beast:
jalammar.github.io/illustrated-transformer
BERT explained:
youtube.com/watch?v=BhlOGGzC0Q0
Backpropagation explained:
youtube.com/watch?v=Ilg3gGewQ5U
Beat used for Hashing rap:
youtube.com/watch?v=zkaT8-NhD5c
Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams!
Signup for my newsletter for exciting updates in the field of AI:
goo.gl/FZzJ5w
And please support me on Patreon:
patreon.com/user?u=3191693 Join my AI community: chatgptschool.io Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available): https://www.wagergpt.xyz










