layer_keras

Gets any layer available in Keras with the specified parameters

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

layer_keras function

<dl><dt>type</dt>
<dd>The name of the layer, e.g. <code>"activity_regularization"</code> for a
<code>keras::layer_activity_regularization</code> object</dd>
<dt>...</dt>
<dd>Named parameters for the Keras layer constructor</dd></dl>

Arguments

Custom layer from Keras — layer_keras

<dl>

<dt>type</dt>
<dd>The name of the layer, e.g. <code>"activity_regularization"</code> for a
<code>keras::layer_activity_regularization</code> object</dd>


<dt>...</dt>
<dd>Named parameters for the Keras layer constructor</dd>

</dl>

layer_keras: Custom layer from Keras

Description

Usage

Value

Arguments

See Also