noise_saltpepper

A data filter which replaces some values with zeros or ones

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

noise_saltpepper function

<dl><dt>p</dt>
<dd>Probability that a feature in an instance is set to zero or one</dd></dl>

Arguments

Filter to add salt-and-pepper noise — noise_saltpepper

<dl>

<dt>p</dt>
<dd>Probability that a feature in an instance is set to zero or one</dd>

</dl>

noise_saltpepper: Filter to add salt-and-pepper noise

Description

Usage

Value

Arguments

See Also