ConceptAI & ML
Energy-based models
A class of models that define probability distributions using an unnormalized density function based on an energy function.
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.
Probability density function2Boltzmann distribution1Neural networks1Normalization constant1Probability distribution1Scalar functions1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Phillip Isola
Energy-based models represent unnormalized probability distributions where probabilities are proportional to the negative exponential of an energy function.Yann LeCun
Models that capture dependencies between variables by associating a scalar energy to each configuration using an energy function.
Connections
12The lectures that define it or assume it, and the concepts next to it.