AI Rookies

VAE — Variational Autoencoder

Fact

A neural network that learns a hidden pattern and makes new samples.

In Plain Words

A VAE is like a smoothie shop with a tiny secret menu. It squeezes a big recipe into a flavor code, then blends a new drink from it.

You meet it in image work, data shrinking, and feature learning. It is steady, but fine details can look soft.

Related Concepts

Generative Model
A VAE is a classic member of the generative model family.

Embedding
It compresses data into a hidden code you can sample.

KL Divergence
It uses KL Divergence to keep the hidden space from getting wild.

GAN
VAEs are steadier, but GANs often make sharper images.