dense

Wrapper for a dense/fully-connected 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

dense function

<dl><dt>units</dt>
<dd>Number of units</dd>
<dt>activation</dt>
<dd>Optional, string indicating activation function (linear by default)</dd></dl>

Arguments

Create a fully-connected neural layer — dense

<dl>

<dt>units</dt>
<dd>Number of units</dd>


<dt>activation</dt>
<dd>Optional, string indicating activation function (linear by default)</dd>

</dl>

dense: Create a fully-connected neural layer

Description

Usage

Value

Arguments

See Also

Examples