Sign inSign in
ConceptAI & ML

Energy-based models

A class of models that define probability distributions using an unnormalized density function based on an energy function.
as Stefano Ermon 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.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Phillip Isola

    MIT · Undergraduate

    Energy-based models represent unnormalized probability distributions where probabilities are proportional to the negative exponential of an energy function.
    • 44:38Generative Models: Basics
  • Yann LeCun

    Harvard University · Research

    Models that capture dependencies between variables by associating a scalar energy to each configuration using an energy function.
    • 35:52Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan

Connections

12

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.