Auto-encoder models are used to model 
, the joint probability of 
, the observed data, and 
, the latent variable. The joint probability 
is normally factorized as 
. During inference, we are interested in finding good values ...
Variational autoencoders
Get Hands-On Generative Adversarial Networks with Keras now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
