Fig.1

Concept

Variational auto-encoder

A variational auto-encoder (VAE) is a generative model that pairs an encoder and decoder network, like a standard autoencoder, except the bottleneck is probabilistic rather than a fixed vector. Instead of mapping an input to one latent code, the encoder outputs the…

The rest of “Variational auto-encoder” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library