ConceptAI & ML
Mini-batch gradient descent
Performing the forward, backward pass, and update on a randomly selected small batch of the dataset rather than the entire dataset.
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.
Brian Yu
A technique where the data set is divided into small batches to calculate gradients.
Connections
6The lectures that define it or assume it, and the concepts next to it.