make_denoising

Converts an autoencoder into a denoising one by adding a filter
for the input data

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

make_denoising function

<dl><dt>learner</dt>
<dd>The <code>"ruta_autoencoder"</code> object</dd>
<dt>noise_type</dt>
<dd>Type of data corruption which will be used to train the
autoencoder, as a character string. See <code>\link{autoencoder_denoising}</code> for
details</dd>
<dt>...</dt>
<dd>Extra parameters to customize the noisy filter. See
<code>\link{autoencoder_denoising}</code> for details</dd></dl>

Arguments

Add denoising behavior to any autoencoder — make_denoising

<dl>

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


<dt>noise_type</dt>
<dd>Type of data corruption which will be used to train the
autoencoder, as a character string. See <code>\link{autoencoder_denoising}</code> for
details</dd>


<dt>...</dt>
<dd>Extra parameters to customize the noisy filter. See
<code>\link{autoencoder_denoising}</code> for details</dd>

</dl>

make_denoising: Add denoising behavior to any autoencoder

Description

Usage

Value

Arguments

See Also