ConceptAI & ML
Cross-entropy loss backward pass
The analytical derivative of the cross-entropy loss with respect to the logits simplifies to the softmax probabilities minus one at the correct label index.
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.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.