A contractive autoencoder adds a penalty term to the loss function of a basic autoencoder which attempts to induce a contraction of data in the latent space.
autoencoder_contractive(network, loss = "mean_squared_error",
weight = 2e-04)Layer construct of class "ruta_network"
Character string specifying the reconstruction error part of the loss function
Weight assigned to the contractive loss
A construct of class "ruta_autoencoder"
Other autoencoder variants: autoencoder_denoising,
autoencoder_robust,
autoencoder_sparse,
autoencoder_variational,
autoencoder