ConceptAI & ML
Stochastic depth
A regularization technique where entire layers of a deep network are randomly dropped during training and the full network is used at test time.
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
1Fei-Fei Li, Justin Johnson & Serena Yeung
Connections
5The lectures that define it or assume it, and the concepts next to it.