new_autoencoder

Internal function to create autoencoder objects. Instead, consider using
<code>\link{autoencoder}</code>.

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

new_autoencoder function

<dl><dt>network</dt>
<dd>Layer construct of class <code>"ruta_network"</code> or coercible</dd>
<dt>loss</dt>
<dd>A <code>"ruta_loss"</code> object or a character string specifying a loss function</dd>
<dt>extra_class</dt>
<dd>Vector of classes in case this autoencoder needs to support custom
methods (for <code>to_keras</code>, <code>train</code>, <code>generate</code> or others)</dd></dl>

Arguments

Create an autoencoder learner — new_autoencoder

<dl>

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


<dt>loss</dt>
<dd>A <code>"ruta_loss"</code> object or a character string specifying a loss function</dd>


<dt>extra_class</dt>
<dd>Vector of classes in case this autoencoder needs to support custom
methods (for <code>to_keras</code>, <code>train</code>, <code>generate</code> or others)</dd>

</dl>

new_autoencoder: Create an autoencoder learner

Description

Usage

Value

Arguments