AI engineering glossary · Generative media multimodal
What is VAE (variational autoencoder)?
Variational autoencoder (also called VAE): A generative model that pairs an encoder, which maps data to a probability distribution over a latent space, with a decoder that reconstructs data from samples of it. A regularising term keeps that space smooth, so sampling random latent points yields new, plausible outputs.
Variational autoencoder: an example
A VAE trained on handwritten digits can decode a random 2-D latent point into a new, believable digit and interpolate smoothly between 3 and 8.
Related terms
More Generative media multimodal terms
- Video generation
- Vision encoder
- Vision-language model
- Visual grounding
- Visual instruction tuning
- Visual question answering
- VITS
- Voice activity detection
Where you learn it
Variational autoencoder is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.