ConceptMathematics
Mini-batch SGD
A variation of stochastic gradient descent that computes the gradient estimate by averaging over a small subset of data points rather than a single point.
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
2The lectures that define it or assume it, and the concepts next to it.