ANN used for unsupervised learning of efficient codings: learning a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction.
an unsupervised neural network
which is trained to reconstruct a given input
from its latent representation (Bengio, 2009).
Unlike principal components analysis, the encoding and decoding steps are not limited to linear transformations (PCA learns an "encoding linear transform", while auto-encoders learn an "encoding program").