ConceptAI & ML
Contrastive divergence
An approximation algorithm used to estimate gradients for training Restricted Boltzmann Machines.
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
2Each in their own terms, from the easiest level.
Phillip Isola
An algorithm for training energy-based models where the model updates by balancing the decrease of energy at data points and the increase of energy at model-generated sample points.
Connections
5The lectures that define it or assume it, and the concepts next to it.