Sign inSign in
ConceptAI & ML

Foundation models

Large-scale models trained on vast amounts of data that can be adapted to a wide range of downstream tasks.
as Russ Tedrake defines itMITThe wording closest to all 4 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

4

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Undergraduate

    Large-scale models trained on vast amounts of data that are generally useful for many downstream tasks without extensive fine-tuning.
    • 56:23Transfer Learning: Models
  • Aron Walsh

    Imperial College London · Graduate

    Large-scale machine learning models trained on massive datasets of material simulations across diverse structures and properties.
    • 15:20AI for Materials on Demand: Accelerating Discovery
  • Irina Rish

    Université de Montréal, MILA · Research

    Models that are pre-trained in an unsupervised or self-supervised way on a huge amount of data without any particular goal of doing a particular task.
    • 11:18Emergent Behaviors in Foundational Models

Lectures that assume it

4

Connections

17

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

4 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.