Sign inSign in
ConceptAI & ML

Sliding window attention

An attention mechanism where each token only attends to a local neighborhood of surrounding tokens to increase efficiency.
as Douwe Kiela defines itStanford University
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.

Lecturers

2

Each in their own terms, from the easiest level.

  • Albert Jiang

    Stanford University · Graduate

    An attention variant where tokens in lower transformer layers attend only to a short local span of previous tokens, accumulating broader context in deeper layers.
    • 2:58Demystifying Mixtral of Experts

Connections

4

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

Concepts2

Lectures2

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.