Backpropagation

Entity Type: Glossary ID: backpropagation

Definition: A supervised learning algorithm used to train neural networks by calculating gradients of the loss function with respect to network weights. It propagates errors backward through the network to update weights and minimize loss.

Related Terms: - neural-network - gradient-descent - chain-rule - training

Source Urls: - https://en.wikipedia.org/wiki/Backpropagation

Tags: - neural-networks - training - optimization

Status: active

Version: 1.0.0

Created At: 2025-08-31

Last Updated: 2025-08-31