to_keras.ruta_filter

Noise filters can be applied during training (in denoising autoencoders),
for this a generator is used to get data batches.

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_filter function

<dl><dt>x</dt>
<dd>Filter object</dd>
<dt>data</dt>
<dd>Matrix where the filter will be applied</dd>
<dt>batch_size</dt>
<dd>Size of the sample (for the training stage)</dd>
<dt>...</dt>
<dd>Additional parameters, currently unused</dd></dl>

Arguments

Get a Keras generator from a data filter — to_keras.ruta_filter

<dl>

<dt>x</dt>
<dd>Filter object</dd>


<dt>data</dt>
<dd>Matrix where the filter will be applied</dd>


<dt>batch_size</dt>
<dd>Size of the sample (for the training stage)</dd>


<dt>...</dt>
<dd>Additional parameters, currently unused</dd>

</dl>

to_keras.ruta_filter: Get a Keras generator from a data filter

Description

Usage

Arguments