-
what's wrong with using just a plain auto-encoder, or a vae with some desired prior?
I have yet to see a non-image example where GANs are the best way to learn the latent manifold of the data.
-
-
adversarial autoencoder / adversarial variational bayes? Mainly image datasets, but the GAN loss is on a latent space
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
uhum... So, GAN works best mainly for Images...yeah?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
to play devil's advocate, gans for text generation with the gumbel softmax trick did pretty well
-
do you got any pointer for GANs for text?
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.