Variational Autoencoder
Variational Autoencoder (VAE) er en dyb generativ latent-variabel model, introduceret af Diederik Kingma og Max Welling i 2014, der koder data som en sandsynlighedsfordeling i et latent rum og sampler fra denne fordeling for at generere nye eksempler. Den anvendes til datagenerering, anomalidetektion og feature-læring.
Læs hele metoden
Log ind med en gratis konto for at læse dette afsnit.
Method map
The neighbourhood of related methods — select a node to explore.
+26 more
Kilder
- Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗
- Higgins, I. et al. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations (ICLR). link ↗
Sådan citerer du denne side
ScholarGate. (2026, June 1). Variational Autoencoder (VAE). ScholarGate. https://scholargate.app/da/deep-learning/variational-autoencoder
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- AutoencoderDyb læring↔ compare
- DiffusionsmodelDyb læring↔ compare
- Generativ modstridende netværkDyb læring↔ compare
- Principal Component AnalysisMaskinlæring↔ compare
- Score-baseret generativ modelDyb læring↔ compare
Refereret af
Har du fundet en fejl på denne side? Indberet den eller foreslå en rettelse →