Models & Architecture

Autoencoder

A network that learns to compress data into a compact code and reconstruct it, useful for denoising and finding structure.

An autoencoder is trained to copy its input to its output through a narrow middle layer, which forces it to learn an efficient compressed representation of the data. That bottleneck code captures the essential structure, making autoencoders handy for compression, denoising, anomaly detection, and learning features without labels. Variants like the variational autoencoder can also generate new data.

Reference: Wikipedia: Autoencoder