Gradivex
Home
Academy
Arena
Visualizer
Models
Log in
NLP & Transformers
Module 3 · NLP & Transformers · ~35 min
The Transformer
The architecture that changed everything: attention is all you need.
The attention mechanism
7 min
Up next
Multi-head attention
7 min
Positional encoding
7 min
Full transformer architecture
7 min
Why transformers beat RNNs
7 min