Sign inSign in
ConceptAI & ML

Mixed precision training

A training technique that uses 16-bit floating-point numbers for storage, inputs, and activations, while using 32-bit floating-point numbers for accumulations and weight updates.
as Song Han 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

1

    Lectures that assume it

    2

    Connections

    9

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

    1 lecturer. 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.