make_robust

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

Implementation of several unsupervised neural networks,
from building their architecture to their training and evaluation. Available
networks are auto-encoders including their main variants: sparse, contractive,
denoising, robust and variational, as described in Charte et al. (2018)
<doi:10.1016/j.inffus.2017.12.007>.

David Charte

ruta

Implementation of Unsupervised Neural Architectures

Francisco Charte

Francisco Herrera

make_robust function

<dl><dt>learner</dt>
<dd>The <code>"ruta_autoencoder"</code> object</dd>
<dt>sigma</dt>
<dd>Sigma parameter in the kernel used for correntropy</dd></dl>

Arguments

Add robust behavior to any autoencoder — make_robust

<dl>

<dt>learner</dt>
<dd>The <code>"ruta_autoencoder"</code> object</dd>


<dt>sigma</dt>
<dd>Sigma parameter in the kernel used for correntropy</dd>

</dl>

make_robust: Add robust behavior to any autoencoder

Description

Usage

Value

Arguments

See Also