correntropy

A wrapper for the correntropy 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

correntropy function

<dl><dt>sigma</dt>
<dd>Sigma parameter in the kernel</dd></dl>

Arguments

Correntropy loss — correntropy

<dl>

<dt>sigma</dt>
<dd>Sigma parameter in the kernel</dd>

</dl>

correntropy: Correntropy loss

Description

Usage

Value

Arguments

See Also