Fig.1

Concept

VAE

A VAE (Variational Autoencoder) is a neural network that learns to compress data into a continuous latent space and reconstruct it, while forcing that latent space to follow a known distribution (usually a unit Gaussian).

The rest of “VAE” 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

VAE, explained · Fig. 1