Variational Autoencoders are not autoencoders
paulrubenstein.co.uk
paulrubenstein.co.uk
This post [0] does a good job showing the difference between latent variables for log-likelihood and KL losses.
[0]https://towardsdatascience.com/intuitively-understanding-var...
http://web.archive.org/web/20190129144610/http://paulrubenst...