Timeline for Why do we use Gaussian distributions in Variational Autoencoder?
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 11, 2020 at 14:32 | history | edited | CommunityBot |
Commonmark migration
|
|
| Apr 12, 2019 at 15:07 | comment | added | Jan Kukacka | Perhaps, but the number of samples you need to get a good density estimate in the latent space grows exponentially with the dimensionality of the latent space. Also, density estimation itself is a tricky problem, so you may start with one problem and end up with two (which does not mean VAEs don't have their own difficulties, compared to standard AE)... | |
| Apr 12, 2019 at 15:05 | history | edited | Jan Kukacka | CC BY-SA 4.0 |
added 1 character in body
|
| Apr 12, 2019 at 14:59 | comment | added | Tbertin | Thank you for your answer ! But would it work if we use a classic auto encoder (without any specific distribution for the hidden representation) and we sample vectors by approximating the distribution for the hidden representation... | |
| Apr 12, 2019 at 14:53 | vote | accept | Tbertin | ||
| Apr 12, 2019 at 8:12 | history | edited | Jan Kukacka | CC BY-SA 4.0 |
added 201 characters in body
|
| Apr 12, 2019 at 7:55 | history | answered | Jan Kukacka | CC BY-SA 4.0 |