make_contractive

Converts an autoencoder into a contractive one by assigning a
contractive loss to it

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_contractive function

<dl><dt>learner</dt>
<dd>The <code>"ruta_autoencoder"</code> object</dd>
<dt>weight</dt>
<dd>Weight assigned to the contractive loss</dd></dl>

Arguments

Add contractive behavior to any autoencoder — make_contractive

<dl>

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


<dt>weight</dt>
<dd>Weight assigned to the contractive loss</dd>

</dl>

make_contractive: Add contractive behavior to any autoencoder

Description

Usage

Value

Arguments

See Also