AI Glossary

Backpropagation

Coverage in development

Backpropagation computes gradients of a neural network’s loss with respect to its parameters by applying the chain rule from output to input layers.

Definition

Backpropagation computes gradients of a neural network’s loss with respect to its parameters by applying the chain rule from output to input layers.

Plain English explanation

It is the accounting method that tells each layer how to adjust after a prediction error.

Last reviewed

Sources

Correction request

If a technology assignment or hub description is inaccurate, submit a correction via the Corrections Policy.

All technologies → · AI Models → · APIs & SDKs → · Integrations → · Compliance → · Browse all companies → · Explore industries → · Compare →