Create a contractive autoencoder

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)

Arguments

network

Layer construct of class "ruta_network"

loss

Character string specifying the reconstruction error part of the loss function

weight

Weight assigned to the contractive loss

Value

A construct of class "ruta_autoencoder"

References

• A practical tutorial on autoencoders for nonlinear feature fusion

See also

Other autoencoder variants: autoencoder_denoising(), autoencoder_robust(), autoencoder_sparse(), autoencoder_variational(), autoencoder()