What is VAE?

A Variational Autoencoder (VAE) is a type of artificial neural network belonging to the families of autoencoders and Bayesian methods. VAEs learn a latent representation of input data and can generate new data points that resemble the training data. They are commonly used for generative modeling tasks such as image generation, anomaly detection, and data imputation. Unlike traditional autoencoders, VAEs learn a probability distribution over the latent space, allowing for the generation of new samples by sampling from this distribution.