noise_zeros

A data filter which replaces some values with zeros

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_zeros function

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

Arguments

Filter to add zero noise — noise_zeros

<dl>

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

</dl>

noise_zeros: Filter to add zero noise

Description

Usage

Value

Arguments

See Also