evaluation_metric

Create a different evaluation metric from a valid Keras metric

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

evaluation_metric function

<dl><dt>evaluate_f</dt>
<dd>Must be either a metric function defined by Keras (e.g.
<code>keras::metric_binary_crossentropy</code>) or a valid function for Keras to
create a performance metric (see <code>\link[keras]{metric_binary_accuracy}</code>
for details)</dd></dl>

Arguments

Custom evaluation metrics — evaluation_metric

<dl>

<dt>evaluate_f</dt>
<dd>Must be either a metric function defined by Keras (e.g.
<code>keras::metric_binary_crossentropy</code>) or a valid function for Keras to
create a performance metric (see <code>\link[keras]{metric_binary_accuracy}</code>
for details)</dd>

</dl>

evaluation_metric: Custom evaluation metrics

Description

Usage

Value

Arguments

See Also