New answers tagged

0

In my experience, it's not a matter of performance benefits; Variational Auto-Encoder GANs are much more useful if you want to have "knobs" to turn to influence the generated output. Since you have a latent layer that represents possibly the mean and the distribution of the data, you can tune to different "positions" in that latent space ...


1

Practically, when optimizing VAE, you assume that prior $p(z)\sim N(0,1)$; i.e. the unit Gaussian distribution. However, in testime you sample z from $p(z|x)$; the encoder model. Why is that? Let's go back to the start. We have a model $p_{\theta}(x)$ and the data $\{x_1, ..., x_N\}$. Solving the maximum log-likelihood problem, we have \begin{equation} \...


Top 50 recent answers are included