VAE (Variational Autoencoder)
/viː eɪ iː/
A generative model that learns a probabilistic latent space representation of data.
In italiano: VAE (Variational Autoencoder)VAEs encode data into a distribution in latent space (typically Gaussian) and decode samples back to data space. They enable controllable generation and interpolation in latent space.
Examples
- Image generation
- Anomaly detection
- Data compression