Dimensionality ReductionDeep learning often begins with data that has many coordinates.
Sparse AutoencodersAn ordinary autoencoder compresses information by forcing the latent representation to have fewer dimensions than the input.
Denoising AutoencodersA denoising autoencoder learns to recover a clean input from a corrupted version of that input.
Variational AutoencodersA variational autoencoder, or VAE, is a generative latent variable model trained with neural networks.
Latent Space ManipulationLatent space manipulation studies how to change a learned representation $z$ in order to produce controlled changes in the decoded output. In an autoencoder, the encoder maps an input into a latent vector,
Representation LearningRepresentation learning is the study of how models learn useful internal descriptions of data.