Data-Targeted Prior Distribution for Variational AutoEncoder

Data-Targeted Prior Distribution for Variational AutoEncoder

Bayesian methods were studied in this paper using deep neural networks. We are interested in variational autoencoders, where an encoder approaches the true posterior and the decoder approaches the direct probability. Specifically, we applied these autoencoders for unsteady and compressible fluid flo...

Full description

Bibliographic Details
Main Authors: Nissrine Akkari, Fabien Casenave, Thomas Daniel, David Ryckelynck
Format: Article
Language:English
Published: MDPI AG 2021-09-01
Series:Fluids
Subjects:
kernel proper orthogonal decomposition (KPOD)
variational autoencoder (VAE)
inference model
prior distribution
Gaussian kernel
unsteady and compressible fluid flows
Online Access:https://www.mdpi.com/2311-5521/6/10/343

Internet

https://www.mdpi.com/2311-5521/6/10/343

Similar Items