add_weight_decay

Adds a weight decay regularization to the encoding layer of a
given autoencoder

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

add_weight_decay function

<dl><dt>learner</dt>
<dd>The <code>"ruta_autoencoder"</code> object</dd>
<dt>decay</dt>
<dd>Numeric value indicating the amount of decay</dd></dl>

Arguments

Add weight decay to any autoencoder — add_weight_decay

<dl>

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


<dt>decay</dt>
<dd>Numeric value indicating the amount of decay</dd>

</dl>

add_weight_decay: Add weight decay to any autoencoder

Description

Usage

Value

Arguments