bernouilliGammaLoss: Custom loss function for Bernouilli-Gamma distributions.

In SantanderMetGroup/downscaleR.keras: A climate4R package for statistical downscaling <http://meteo.unican.es/climate4r>

Custom loss function for Bernouilli-Gamma distributions.

Description

This loss function optimizes the negative log-likelihood of a Bernouill-Gamma distribution. It is a custom loss function defined according to keras functions.

Usage

bernouilliGammaLoss(last.connection = NULL)

Arguments

last.connection

A string with values "conv" o "dense" depending on the type of the net's last connection. DEFAULT is NULL.

Details

Note that infering a conditional Bernouilli-Gamma distribution means to estimate their associated parameters: probability, shape and scale factor. To avoid computational instabilities we actually estimate log alpha and log beta. Therefore, make sure that your output layers are designed according to this property of the distribution.

Author(s)

J. Bano-Medina

See Also

bernouilliGammaStatistics for computing the expectance or simulate from the discrete continuous distribution downscaleTrain.keras for training a downscaling deep model with keras downscalePredict.keras for predicting with a keras model prepareNewData.keras for predictor preparation with new (test) data downscaleR.keras Wiki downscaleR Wiki for downscaling seasonal forecasting and climate projections.

SantanderMetGroup/downscaleR.keras documentation built on July 7, 2023, 1:22 p.m.