make_robust: Add robust behavior to any autoencoder

In fdavidcl/ruta: Implementation of Unsupervised Neural Architectures

Add robust behavior to any autoencoder

Description

Converts an autoencoder into a robust one by assigning a correntropy loss to it. Notice that this will replace the previous loss function

Usage

make_robust(learner, sigma = 0.2)

Arguments

learner	The "ruta_autoencoder" object
sigma	Sigma parameter in the kernel used for correntropy

Value

An autoencoder object which contains the correntropy loss

See Also

⁠\link{autoencoder_robust}⁠

fdavidcl/ruta documentation built on July 5, 2023, 6:32 p.m.