ConceptAI & ML
Decoder-only architecture
An architecture using a single stack with causal self-attention that handles both inputs and targets via concatenation to generate output sequences.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Causal attention2Self-attention2
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Jason Wei & Hyung Won Chung
A Transformer architecture using a single stack with causal self-attention that can both process concatenated inputs/targets and generate output sequences.
Lectures that assume it
1Connections
5The lectures that define it or assume it, and the concepts next to it.