make_denoising

The <code>"ruta_autoencoder"</code> object

learner

Type of data corruption which will be used to train the
autoencoder, as a character string. See <code><a rd-options="" href="/link/autoencoder_denoising?package=ruta&version=1.0.2" data-mini-rdoc="ruta::autoencoder_denoising">autoencoder_denoising</a></code> for
details

noise_type

Extra parameters to customize the noisy filter. See
<code><a rd-options="" href="/link/autoencoder_denoising?package=ruta&version=1.0.2" data-mini-rdoc="ruta::autoencoder_denoising">autoencoder_denoising</a></code> for details

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

Type of data corruption which will be used to train the
autoencoder, as a character string. See <code><a rd-options='' href='autoencoder_denoising'>autoencoder_denoising</a></code> for
details

Extra parameters to customize the noisy filter. See
<code><a rd-options='' href='autoencoder_denoising'>autoencoder_denoising</a></code> for details

make_denoising: Add denoising behavior to any autoencoder

Description

Usage

Arguments

Value

See Also