Cross-entropy
The standard loss for classification: −Σ y·log(p). Designed to pair cleanly with softmax/sigmoid outputs.
Companion explanation in Step by Token, chapter 6.
Where this term gets built
Continue
The standard loss for classification: −Σ y·log(p). Designed to pair cleanly with softmax/sigmoid outputs.
Companion explanation in Step by Token, chapter 6.
Continue