An autoencoder is a neural network architecture trained to encode input data into a compressed representation and then reconstruct the original input from that representation. It is typically trained without labeled data and learns which information is most important for reconstruction. Autoencoders are used for dimensionality reduction, denoising, anomaly detection, representation learning, and related tasks.
A system that learns to extract the most important information from the input. Autoencoders are a combination of an encoder and decoder. Autoencoders rely on the following two-step process: 1. The encoder maps the input to a (typically) lossy lower-dimensional (intermediate) format. 2. The decoder builds a lossy version of the original input by mapping the lower-dimensional format to the original higher-dimensional input format. Autoencoders are trained end-to-end by having the decoder attempt to reconstruct the original input from the encoder's intermediate format as closely as possible. Because the intermediate format is smaller (lower-dimensional) than the original format, the autoencoder is forced to learn what information in the input is essential, and the output won't be perfectly identical to the input. For example: - If the input data is a graphic, the non-exact copy would be similar to the original graphic, but somewhat modified. Perhaps the non-exact copy removes noise from the original graphic or fills in some missing pixels. - If the input data is text, an autoencoder would generate new text that mimics (but is not identical to) the original text. See also variational autoencoders.