to_keras.ruta_sparsity

Translate sparsity regularization to Keras regularizer

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_sparsity function

<dl><dt>x</dt>
<dd>Sparsity object</dd>
<dt>activation</dt>
<dd>Name of the activation function used in the encoding layer</dd>
<dt>...</dt>
<dd>Unused</dd></dl>

Arguments

Translate sparsity regularization to Keras regularizer — to_keras.ruta_sparsity

<dl>

<dt>x</dt>
<dd>Sparsity object</dd>


<dt>activation</dt>
<dd>Name of the activation function used in the encoding layer</dd>


<dt>...</dt>
<dd>Unused</dd>

</dl>

to_keras.ruta_sparsity: Translate sparsity regularization to Keras regularizer

Description

Usage

Value

Arguments

References