Variational autoencoders

Neural networks

Variational autoencoders (VAEs) are a type of generative Autoencoders.

VAEs vs. GANs

VAEs have fallen out of fashion when GANs became popular, because they were able to get visually interesting results more easily. However, some works a few years later seem to show that they have similar potential (Vahdat and Kautz 2020).


Vahdat, Arash, and Jan Kautz. 2020. “NVAE: A Deep Hierarchical Variational Autoencoder.” arXiv:2007.03898 [Cs, Stat], July.

← Back to Notes