Glossary

Backpropagation — Glossary

The algorithm for efficiently computing gradients in neural networks via the chain rule.

Also known as: backprop

Reviewed:

Full definition

Backpropagation enables gradient-based training of deep models by propagating error signals backward through layers. Automatic differentiation frameworks implement it for composable architectures.

Related encyclopedia topic

Backpropagation — Backpropagation computes gradients of the loss with respect to neural network parameters efficiently, enabling gradient-based training of deep models.

← Back to glossary · Learning hub