Knowledge Graph — Coursera Notes › Academic disciplines › Information Technology / Computer Science › Artificial Intelligence › Generative AI › Generative AI Models

Variational Autoencoders (VAEs)

concept · part of Generative AI Models

A generative AI model that encodes data into a latent space and decodes it for variations. Ideal for image generation or anomaly detection (e.g., in medical imaging).

VAEs learn a probability distribution over the latent space, enabling smooth interpolation between data points and controlled generation by sampling from the distribution. They are trained by maximizing the evidence lower bound (ELBO), which balances reconstruction accuracy and regularization of the latent space toward a prior (typically a standard normal distribution).

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.

🧠 Knowledge Graph

Select a node

The owner's editing tools — shown here so you can see how the graph is grown, but read-only.

Click a bubble to drill in · click again to collapse · drag to move around