backpropagation (machine learning) (de.: Fehlerrückführung (maschinelles Lernen))

Backpropagation is an algorithm that updates the weights of a neural network based on the measured error at the output layer by layer up to the input.

ISO/IEC TR 29119-11:2020 method used in artificial neural networks to determine the weights to be used on the network connections based on the computed error at the output of the network

Note 1 to entry: It is used to train deep neural networks (3.1.27).

@misc{aiglossary_backpropagationmachinelearning_18yqgrl,
author = {{AI-Glossary.org}},
title = {{backpropagation (machine learning)}},
howpublished = "https://www.ai-glossary.org/index.php?p=18yqgrl\&l=en",
year = "2024",
note = "online, accessed: 2024-11-21" }