Dimensionality ReductionHigh-dimensional data often contains structure that can be described with fewer variables than the raw representation suggests.
Sparse AutoencodersAn undercomplete autoencoder constrains the representation by reducing the latent dimension.
Denoising AutoencodersA denoising autoencoder learns to reconstruct a clean input from a corrupted version of that input. Instead of copying $x$ to $\hat{x}$, the model receives a noisy input $\tilde{x}$ and must recover the original $x$.
Variational AutoencodersA variational autoencoder, or VAE, is an autoencoder with a probabilistic latent space.
Latent Space ManipulationA latent space is the internal coordinate system learned by an encoder or generative model.
Representation LearningRepresentation learning is the study of how a model converts raw data into useful internal variables.