New answers tagged

4 votes

Is plain autoencoder a generative model?

An autoencoder is not considered a generative model, because it only reconstructs the given input. You could use the decoder like a generative model by putting in different vectors. However, the ...
user avatar
  • 346
1 vote

How to generate new data given a trained VAE - sample from the learned latent space or from multivariate Gaussian?

Maybe there's a misconception, we are not learning a mu and log_var but a mapping (encoder) from an image to ...
user avatar
  • 136
0 votes

How to generate new data given a trained VAE - sample from the learned latent space or from multivariate Gaussian?

I think method 1 will provide the best output. Approximating the empirical distribution of $z$ should provide decoder inputs in the subset of latent space that the decoder was trained on. Sampling ...
user avatar
2 votes

Why don't we also need to approximate $p(x \mid z)$ in the VAE?

What I can guess here is that, in VAEs, we assume $p(z)$ (prior), so we are able to calculate $p(x \mid z)$, but for $p(x)$ we can't assume its distribution? Is it right? You could assume $p(x)$ is ...
user avatar
  • 33.8k
0 votes

Why do we use the same parameters for the joint, marginal and conditional distributions in VAEs?

I think this is very confusing to many people. I had to deal with VAEs (and Bayesian neural networks) multiple times in the past, and I've seen so many inconsistent notations and unclear explanations. ...
user avatar
  • 33.8k

Top 50 recent answers are included