Needs:
Autoencoders
Neural Distribution Families
Needed by:
None.
Links:
Sheet PDF
Graph PDF

Variational Autoencoders

Why

1

Definition

A variational autoencoder (VAE) from latent set Z to observation set X is an ordered pair ((pz(θ),pxz(θ)),qzxϕ) whose first coordinate is a deep latent generation pair from Z to X (with parameters θ) and whose second coordinate is a deep conditional distribution from X to Z (with parameters ϕ).

A VAE inherits its joint function from its deep latent generation pair. pz(θ) is called the latent distribution (or prior distribution, latent model). pxz(θ) is called the decoder distribution. qzx(θ) is called the encoder distribution (or inference distribution, recognition distribution).

A variational autoencoder family, from Z to X, is a family of autoencoders {((pz(θ),pxz(θ)),qzx(ϕ)}(θ,ϕ)Θ×Φ.


  1. Future editions will include. Future editions may also change the name of this sheet. It is also likely that there will be added prerequisite sheets on variational inference. ↩︎
Copyright © 2023 The Bourbaki Authors — All rights reserved — Version 13a6779cc About Show the old page view