ConceptAI & ML
Batch gradient descent
Gradient descent where weight updates are computed using all examples in the training set at once.
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.
Chris Ré
A variant of stochastic gradient descent that computes the gradient over a small batch of training examples to reduce noise and improve computational efficiency.
Connections
4The lectures that define it or assume it, and the concepts next to it.