View source: R/bernouilliGammaLoss.R
bernouilliGammaLoss | R Documentation |
This loss function optimizes the negative log-likelihood of a Bernouill-Gamma distribution. It is a custom loss function defined according to keras functions.
bernouilliGammaLoss(last.connection = NULL)
last.connection |
A string with values "conv" o "dense" depending on the type of the net's last connection. DEFAULT is NULL. |
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.
J. Bano-Medina
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.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.