ConceptAI & ML
Covariance regularization
A criterion that brings the covariance matrix of the output vectors as close to the identity matrix as possible to decorrelate the components.
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
1Connections
3The lectures that define it or assume it, and the concepts next to it.