Concept information
Preferred term
backpropagation
Definition
- Learning rule in multilayer artificial neural networks. The error of the output neurons is propagated backwards through the layers of the network and the synaptic weights are fitted.
Broader concept
Belongs to group
Bibliographic citation(s)
-
• Abdi, H. (1994). Les réseaux de neurones. Presses Universitaires de Grenoble.
[Study type: literature review / Access: closed]
-
• Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing. Vol. 1: Foundations (pp. 318–362). MIT Press.
[Study type: empirical study / Access: closed]
Creator
- Frank Arnould
In other languages
-
French
-
règle delta généralisée
-
rétropropagation du gradient d’erreur
URI
http://data.loterre.fr/ark:/67375/P66-FXM2S5M3-P
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}