Baidu Encyclopedia version
Self-encoding, also known as self-encoder (autoencoder), a type of neural network that can be tried to copy input to output after training. The autoencoder has a hidden layer h inside it that can generate a code representation input. The network can be thought of as consisting of two parts: an encoder represented by the function h = f(x) and a decoder r = g(h) that generates the reconstruction.
Automated encoders are a type of artificial neural network used to learn efficient data value encoding in an unsupervised manner. The purpose of an automatic encoder is to learn the representation (encoding) of a set of data, usually used to reduce the number of dimensions. Along with the reduction side, learn the reconstruction side, where the autoencoder attempts to generate a representation from the reduced encoding as close as possible to its original input, hence its name.