configure

This function builds all the necessary Keras objects in order
to manipulate internals of the models or train them. Users won't generally
need to call this function, since <code>train</code> will do so automatically.

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

configure function

<dl><dt>learner</dt>
<dd>A <code>"ruta_autoencoder"</code> object</dd>
<dt>input_shape</dt>
<dd>An integer describing the number of variables in the input data</dd></dl>

Arguments

Configure a learner object with the associated Keras objects — configure

<dl>

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


<dt>input_shape</dt>
<dd>An integer describing the number of variables in the input data</dd>

</dl>

configure: Configure a learner object with the associated Keras objects

Description

Usage

Value

Arguments