rückgekoppeltes neuronales Netz (en.: recurrent neural network (RNN))

Neuronales Netz, bei dem Eingaben einer aktuellen Schicht in eine voherige Schicht eingespeist werden.

ETSI GR ENI 004 ANN that is connected between nodes form a directed graph across a temporal sequence.

Note: RNNs contain cyclic connections that make them effective in storing history and state. This is done by using feedback loops in the processing of an output.

ISO/IEC DIS 22989 neural network (3.3.7) in which outputs from both the previous layer and the previous processing step are fed into the current layer

Quelle: AI-Glossary.org (https://www.ai-glossary.org), Lizenz d. Definitionstextes (ausschl. Norm-Referenzen): CC BY-SA 4.0, abgerufen: 2024-11-21

BibTeX-Information

@misc{aiglossary_rckgekoppeltesneuronalesNetz_90s0ld,
author = {{AI-Glossary.org}},
title = {{rückgekoppeltes neuronales Netz}},
howpublished = "https://www.ai-glossary.org/index.php?p=90s0ld\&l=de",
year = "2024",
note = "online, abgerufen: 2024-11-21" }