ConceptAI & ML
Knowledge distillation
A project addressing the difficulty of using massive models by transferring knowledge to smaller models.
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.
Cross-entropy loss1Model size1Neural networks1Softmax1Stochastic gradient descent1Vision transformer models1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Sara Beery
A technique where a smaller student model is trained to mimic the output distribution of a larger, pre-trained teacher model.
Lectures that assume it
2Connections
13The lectures that define it or assume it, and the concepts next to it.