Autoencoder (AE) DL
noun
Definition: A type of artificial neural network that learns to reproduce its input at the output by encoding data into a compressed latent representation and then reconstructing it, typically for dimensionality reduction, denoising, or representation learning [Anglo-Russian AI & Robotics Dictionary 2022].
Example in context: “The autoencoder transforms raw input into a latent feature space, and the prototype classifier uses the latent features for classification.” [Ras et al. 2022]
Synonyms : AE; auto-encoder; auto encoder
Related terms: denoising autoencoder, contractive autoencoder, stacked autoencoder, variational autoencoder (VAE)