Variational Autoencoder (VAE) | Skymind

A.I. Wiki

Subscribe to our bi-weekly AI newsletter:

Variational Autoencoder (VAE)

Variational autoencoder models inherit autoencoder architecture, but make strong assumptions concerning the distribution of latent variables. They use variational approach for latent representation learning, which results in an additional loss component and specific training algorithm called Stochastic Gradient Variational Bayes (SGVB).

Further Reading

Ask an Expert

Schedule a 30-minute demo and Q&A with our enterprise Machine Learning experts.

Talk to a Machine Learning Solutions Expert