contraction: Contractive loss

In ruta: Implementation of Unsupervised Neural Architectures

Contractive loss

Description

This is a wrapper for a loss which induces a contraction in the latent space.

Usage

contraction(reconstruction_loss = "mean_squared_error", weight = 2e-04)

Arguments

reconstruction_loss	Original reconstruction error to be combined with the contractive loss (e.g. "binary_crossentropy")
weight	Weight assigned to the contractive loss

Value

A loss object which can be converted into a Keras loss

See Also

\link{autoencoder_contractive}

Other loss functions: correntropy(), loss_variational()

ruta documentation built on Jan. 9, 2023, 1:20 a.m.