autoencoder_contractive

A contractive autoencoder adds a penalty term to the loss
function of a basic autoencoder which attempts to induce a contraction of
data in the latent space.

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

autoencoder_contractive function

<dl><dt>network</dt>
<dd>Layer construct of class <code>"ruta_network"</code></dd>
<dt>loss</dt>
<dd>Character string specifying the reconstruction error part of the loss function</dd>
<dt>weight</dt>
<dd>Weight assigned to the contractive loss</dd></dl>

Arguments

Create a contractive autoencoder — autoencoder_contractive

<dl>

<dt>network</dt>
<dd>Layer construct of class <code>"ruta_network"</code></dd>


<dt>loss</dt>
<dd>Character string specifying the reconstruction error part of the loss function</dd>


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

</dl>

autoencoder_contractive: Create a contractive autoencoder

Description

Usage

Value

Arguments

References

See Also