Sign inSign in
ConceptAI & ML

Pretraining

Pretraining teaches a neural network to mimic its training data from the internet by predicting the next word given a block of text.
as Adam Brown defines itPerimeter InstituteThe 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.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Undergraduate

    The first stage of training a large language model where it learns from a large corpus of internet text.
    • 1:06Deep Dive into Large Language Models: Pretraining to RLHF
  • Sara Beery

    MIT · Undergraduate

    Training a neural network on prior tasks to give it access to prior knowledge.
    • 8:08Transfer Learning: Models

Lectures that assume it

5

Connections

17

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.