An encoder compresses the input into a latent code, and a decoder maps that code back toward the original data. The constraint or training objective encourages the latent code to capture useful structure rather than simply copy the input.
An autoencoder learns to reconstruct its input through a constrained intermediate representation.
An encoder compresses the input into a latent code, and a decoder maps that code back toward the original data. The constraint or training objective encourages the latent code to capture useful structure rather than simply copy the input.