loss_variational

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

reconstruction_loss

<p>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.</p>

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

loss_variational: Variational loss

Description

Usage

Arguments

Value

References

See Also