loss_variational

Specifies an evaluation function adapted to the variational autoencoder. It combines
a base reconstruction error and the Kullback-Leibler divergence between the learned
distribution and the true latent posterior.

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

loss_variational function

<dl><dt>reconstruction_loss</dt>
<dd>Another loss to be used as reconstruction error (e.g. "binary_crossentropy")</dd></dl>

Arguments

Variational loss — loss_variational

<dl>

<dt>reconstruction_loss</dt>
<dd>Another loss to be used as reconstruction error (e.g. "binary_crossentropy")</dd>

</dl>

loss_variational: Variational loss

Description

Usage

Value

Arguments

References

See Also