The Linux Foundation Projects
Skip to main content

Variational Autoencoders (VAEs)

A type of generative model in machine learning that learns to encode data into a compressed representation in a latent space and then decode it back to the original data space. They are particularly known for their ability to generate new data samples that resemble the training data, by optimizing the parameters of the distribution representing the latent space to improve the likelihood of generating real data samples.