Glossary · Term

focal loss

← all terms

Definition

A training objective that pays extra attention to the examples a model is still getting wrong.

A modification of cross-entropy that downweights easy examples and upweights hard ones via a focusing factor; originally from object detection, applied as a cross-domain substitution in Autoresearch agentic training.

Mentioned in 1 episode

  1. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script