Variational autoencoder

A Variational Autoencoder (VAE) is a type of artificial intelligence (AI) that is used to turn data into pictures. It does this by taking data and breaking it down into smaller parts called "encodings". The encodings are like clues about the data, and are used to generate a picture that looks like the original data. It's like the AI takes a bunch of pieces of a puzzle, and puts them together to make a complete picture.