Label Smoothing

AI and Machine Learning · Training and Optimisation · 2015 · label-smoothing.yaml

Replaces the one-hot target with a slightly softened distribution, so the model is never asked to be infinitely confident.

Colour is the family; a dashed line is the second member of it.

Drag to pan · scroll to zoom · click a node to open it
G cross-entropy-loss Cross-Entropy Loss label-smoothing Label Smoothing label-smoothing->cross-entropy-loss a one-hot target pushes logits apart without bound

This node

References