New answers tagged generative-model
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 ...
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 ...
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 ...
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 ...
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. ...
Top 50 recent answers are included
Related Tags
generative-model × 106generative-adversarial-networks × 43
neural-networks × 27
deep-learning × 24
machine-learning × 23
image-generation × 16
variational-autoencoder × 14
papers × 10
convolutional-neural-networks × 7
training × 6
reference-request × 5
autoencoders × 5
latent-variable × 5
classification × 4
datasets × 4
natural-language-processing × 3
computer-vision × 3
recurrent-neural-networks × 3
math × 3
objective-functions × 3
geometric-deep-learning × 3
reinforcement-learning × 2
tensorflow × 2
terminology × 2
image-recognition × 2