Lesezeichen

D Variational Autoencoders are not autoencoders : MachineLearning


Beschreibung

iii) However, if you were to use your same Gaussian decoder to model data that is itself Gaussian, you'd find that the VAE learns to ignore the latent code!

Vorschau

Tags

Nutzer

  • @becker

Kommentare und Rezensionen