Talk:Variational autoencoder: Difference between revisions

Revision as of 19:47, 26 December 2024

Revision as of 19:48, 26 December 2024

Line 57:

:I also found this incredibly confusing. As the prior on z is usually fixed and doesn't depend on any parameter. [[User:EitanPorat|EitanPorat]] ([[User talk:EitanPorat|talk]]) 00:16, 19 March 2023 (UTC)

::I see the confusion. p(z) is a probability distribution, but sometimes the same notation is used in conjunction with a parameter set to indicate that actually it is a parameterized function! The article should be cleared up. The encoder should be called q_phi everywhere and the decoder should be called p_theta. The reason is that to optimize the decoderencoder you need gradients that only come from the KL divergence and then you take the derivative of the free energy with regard to the parameters of the encoder. Those gradients update only the encoder parameters. But the encoder also gets the reconstruction gradients from theta! [[Special:Contributions/46.199.5.20|46.199.5.20]] ([[User talk:46.199.5.20|talk]]) 19:47, 26 December 2024 (UTC)

== The image shows just a normal autoencoder, not a variational autoencoder ==