Neural-network building blocks · MLD-0086
Backpropagation
Reverse-mode derivative propagation through a computation graph to obtain parameter gradients.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Compute gradients of loss with respect to network weights.
Original caveat
Backpropagation computes gradients; the optimizer updates weights.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · Vision · NLP.
Aliases: Backprop.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗