autoencoder_robust

A robust autoencoder uses a special objective function,
correntropy, a localized similarity measure which makes it less sensitive
to noise in data. Correntropy specifically measures the probability density
that two events are equal, and is less affected by outliers than the mean
squared error.

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

autoencoder_robust function

<dl><dt>network</dt>
<dd>Layer construct of class <code>"ruta_network"</code></dd>
<dt>sigma</dt>
<dd>Sigma parameter in the kernel used for correntropy</dd></dl>

Arguments

Create a robust autoencoder — autoencoder_robust

<dl>

<dt>network</dt>
<dd>Layer construct of class <code>"ruta_network"</code></dd>


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

</dl>

autoencoder_robust: Create a robust autoencoder

Description

Usage

Value

Arguments

References

See Also