How to Sample From Latent Space With Variational Autoencoderby@owlgrey
711 reads
711 reads

How to Sample From Latent Space With Variational Autoencoder

by Dmitrii Matveichev 17mFebruary 29th, 2024
Read on Terminal Reader
Read this story w/o Javascript

Too Long; Didn't Read

Unlike traditional AE models, Variational Autoencoders (VAEs) map inputs to a multivariate normal distribution, allowing novel data generation through various sampling methods. The sampling methods covered in this article are posterior sampling, prior sampling, interpolation between two vectors, and latent dimension traversal.
featured image - How to Sample From Latent Space With Variational Autoencoder
Dmitrii Matveichev  HackerNoon profile picture
Dmitrii Matveichev

Dmitrii Matveichev

@owlgrey

No

L O A D I N G
. . . comments & more!

About Author

Dmitrii Matveichev  HackerNoon profile picture
Dmitrii Matveichev @owlgrey
No

TOPICS

Languages

THIS ARTICLE WAS FEATURED IN...

Permanent on Arweave
Read on Terminal Reader
Read this story in a terminal
 Terminal
Read this story w/o Javascript
Read this story w/o Javascript
 Lite