Ground Truth.
AI, checked against the source.

← All topics

backpropagation

Everything on Ground Truth tagged “backpropagation” — 2 items.

Gradient checkpointing: throwing work away so training fits in memory Lesson

Gradient checkpointing cuts the memory a neural network needs during training by deliberately discarding most intermediate results and recomputing them later, trading roughly 30% extra compute for a memory footprint that drops from linear in network depth to the square root of it.

Backpropagation: how a neural network learns from its mistakes Lesson

The single algorithm behind nearly all AI training - assigning blame for an error backward through millions of dials, so each one knows which way to turn.