Lec 08. Architectures: Transformers
This video introduces transformers, focusing on three key ideas: tokens, attention, and positional codes. It also explores how transformers relate to MLPs, GNNs, and CNNs as variations on common principles.
Course Info
Instructors
Departments
As Taught In
Fall
2024
Level
Learning Resource Types
notes
Lecture Notes
theaters
Lecture Videos
assignment
Problem Sets
grading
Projects with Examples
auto_stories
Readings