to_keras.ruta_weight_decay

Builds the Keras regularizer corresponding to the weight decay

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

to_keras.ruta_weight_decay function

<dl><dt>x</dt>
<dd>A <code>"ruta_weight_decay"</code> object</dd>
<dt>...</dt>
<dd>Rest of parameters, ignored</dd></dl>

Arguments

Obtain a Keras weight decay — to_keras.ruta_weight_decay

<dl>

<dt>x</dt>
<dd>A <code>"ruta_weight_decay"</code> object</dd>


<dt>...</dt>
<dd>Rest of parameters, ignored</dd>

</dl>

to_keras.ruta_weight_decay: Obtain a Keras weight decay

Description

Usage

Arguments