Sign inSign in
ConceptAI & ML

Scaling law

Scaling law dictates that increasing compute and model size predictably improves performance.
as Ming Ding defines itStanford UniversityThe wording closest to all 3 definitions
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

3

Each in their own terms, from the easiest level.

  • Adam Brown

    Perimeter Institute · Undergraduate

    A scaling law states that spending more compute to train a larger neural network yields better performance on a linear log-log plot.
    • 8:56Training Sand to Think: Artificial General Intelligence & Future of Physics
  • Phillip Isola

    MIT · Graduate

    The observation that model accuracy improves predictably as either train-time compute or test-time compute increases.
    • 10:06Inference Methods for Deep Learning

Connections

6

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

3 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.