Attention Is All You Need - Transformer Paper Explained

Attention Is All You Need - Transformer Paper Explained

Aleksa Gordić - The AI Epiphany via YouTube Direct link

source attending MHA

8 of 10

8 of 10

source attending MHA

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Attention Is All You Need - Transformer Paper Explained

Automatically move to the next video in the Classroom when playback concludes

  1. 1 A high-level overview
  2. 2 tokenization
  3. 3 embeddings and positional encodings
  4. 4 encoder preprocessing splitting into subspaces
  5. 5 single MHA head explanation
  6. 6 pointwise network
  7. 7 causal masking MHA
  8. 8 source attending MHA
  9. 9 projecting into vocab space and loss function
  10. 10 decoding

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.