Sign inSign in
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.
Watch it explained

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

2

Each in their own terms, from the easiest level.

  • Jason Wei & Hyung Won Chung

    Stanford University · Undergraduate

    A Transformer architecture using a single stack with causal self-attention that can both process concatenated inputs/targets and generate output sequences.
    • 52:45Intuitions on Language Models and the History of Transformer Architectures

Lectures that assume it

1

Connections

5

The lectures that define it or assume it, and the concepts next to it.

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.