to_keras.ruta_layer_variational

This block contains two dense layers representing the mean and log var of a Gaussian
distribution and a sampling layer.

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

to_keras.ruta_layer_variational function

<dl><dt>x</dt>
<dd>The layer object</dd>
<dt>input_shape</dt>
<dd>Number of features in training data</dd>
<dt>model</dt>
<dd>Keras model where the layers will be added</dd>
<dt>...</dt>
<dd>Unused</dd></dl>

Arguments

Obtain a Keras block of layers for the variational autoencoder — to_keras.ruta_layer_variational

<dl>

<dt>x</dt>
<dd>The layer object</dd>


<dt>input_shape</dt>
<dd>Number of features in training data</dd>


<dt>model</dt>
<dd>Keras model where the layers will be added</dd>


<dt>...</dt>
<dd>Unused</dd>

</dl>

to_keras.ruta_layer_variational: Obtain a Keras block of layers for the variational autoencoder

Description

Usage

Value

Arguments

References