Relative Entropy#

Relative Entropy (or Kullback-Leibler divergence) is a measure of how the expectation and activation of the network diverge. It is different from Cross Entropy in that it is asymmetric and thus does not qualify as a statistical measure of error.


This cost function does not have any parameters.


use Rubix\ML\NeuralNet\CostFunctions\RelativeEntropy;

$costFunction = new RelativeEntropy();