make_sparse

Add sparsity regularization to an autoencoder

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

make_sparse function

<dl><dt>learner</dt>
<dd>A <code>"ruta_autoencoder"</code> object</dd>
<dt>high_probability</dt>
<dd>Expected probability of the high value of the
encoding layer. Set this to a value near zero in order to minimize
activations in that layer.</dd>
<dt>weight</dt>
<dd>The weight of the sparsity regularization</dd></dl>

Arguments

Add sparsity regularization to an autoencoder — make_sparse

<dl>

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


<dt>high_probability</dt>
<dd>Expected probability of the high value of the
encoding layer. Set this to a value near zero in order to minimize
activations in that layer.</dd>


<dt>weight</dt>
<dd>The weight of the sparsity regularization</dd>

</dl>

make_sparse: Add sparsity regularization to an autoencoder

Description

Usage

Value

Arguments

See Also