Models and training

Variational autoencoder (VAE)

stable definition

Definition

A probabilistic generative model that learns a distribution over latent representations and reconstructs or generates data by sampling from that latent space.

Distinguish it from nearby terms

A conventional autoencoder maps inputs to latent codes and back. A VAE learns a structured probability distribution over the latent space, which enables sampling but adds a variational training objective.

Check your understanding

A VAE can generate new examples by sampling latent points, not only reconstruct inputs it has already encoded.