Sign inSign in
ConceptAI & ML

Layer normalization

A technique to normalize the inputs of a layer to have a specific mean and variance, often followed by learnable scaling and shifting parameters.
as Chris Ré 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.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

2

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Undergraduate

    A technique to normalize the activations of the features for each individual example across its embedding dimensions to have zero mean and unit variance.
    • 1:30:00Let's Build GPT: From Scratch, in Code, Spelled Out

Lectures that assume it

2

Connections

13

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.