output

This layer acts as a placeholder for the output layer in an autoencoder. The
number of units is not needed as it is deduced from the data during training.

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

output function

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

Arguments

Create an output layer — output

<dl>

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

</dl>

output: Create an output layer

Description

Usage

Value

Arguments

See Also