Concept information
Terme préférentiel
generative adversarial network
Définition
- Framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. (Goodfellow et al., 2014, p. 1).
Concept générique
Synonyme(s)
- GAN
Traductions
-
français
-
GAN
URI
http://data.loterre.fr/ark:/67375/8LP-QT7ZMZVT-N
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}