What is "autoencoder"

n. (context computing English) a form of neural network designed to learn codings

An autoencoder, autoassociator or Diabolo network is an artificial neural network used for learning efficient codings. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction. Recently, the autoencoder concept has become more widely used for learning generative models of data.