Revision as of 20:22, 26 December 2024 edit 46.199.5.20 (talk) →The ELBO section needs more derivation: Reply Tag: Reply ← Previous edit		Latest revision as of 18:57, 27 December 2024 edit undo 82.102.110.228 (talk) →The image shows just a normal autoencoder, not a variational autoencoder: Reply Tag: Reply
Line 66: I'm not sure that image should just be removed, or whether it make sense in the section anyway. [[User:Volker Siegel\|Volker Siegel]] ([[User talk:Volker Siegel\|talk]]) 14:18, 24 January 2022 (UTC) :Just to make this point clear: The reparameterization trick is for the gradients! The trick separates the source of randomness to another node in the DAG that does not have any parameters, so that we can propagate gradients through the rest of the DAG that is now a deterministic function. [[Special:Contributions/82.102.110.228\|82.102.110.228]] ([[User talk:82.102.110.228\|talk]]) 18:57, 27 December 2024 (UTC) == This is a highly technical topic ==

Talk:Variational autoencoder: Difference between revisions