Skip to main content
Cloud & AI Hub
Browse
Glossary AI Directory Playgrounds Models Prompts Explainers Strategy Matrix Benchmark Decoder

Backpropagation

The algorithm that calculates loss gradients backwards through neural layers to update model weights.

Backpropagation uses the calculus chain rule to calculate the gradient of a loss function relative to each network weight. Optimizers use these gradients to adjust weights, reducing training loss.

Historical figures and technical concepts for informational purposes only. Not technical, professional, legal, or financial advice. Sources: Official Documentation.