A neural network that compresses data, then tries to rebuild it.
An autoencoder is like stuffing a whole pizza into a tiny lunchbox. Later, it tries to make the pizza look normal again.
People use it to shrink data or clean messy data. It also learns compact patterns used in some generative models.
Representation Learning
An autoencoder learns key representations by compressing data and rebuilding it.
Unsupervised Learning
An autoencoder often trains on unlabeled data to find hidden structure.
VAE
A VAE adds probability modeling to the autoencoder idea.
Embedding
An autoencoder's middle layer can work as a compact vector representation.