• Bookmarks

    Bookmarks

  • Concepts

    Concepts

  • Activity

    Activity

  • Courses

    Courses


A Variational Autoencoder (VAE) is a type of generative model that learns to encode input data into a latent space and then decodes it back to reconstruct the original data, while also allowing for the generation of new data samples. It combines principles of deep learning and Bayesian inference to produce a continuous and smooth latent space, facilitating efficient sampling and interpolation between data points.
History Empty State Icon

Log in to see lessons

3