Calculates a softmax-like normalisation for the class frequencies.
norm.softmax(x, t = 0.2)Vector of softmax normalised values.
vector of votes for classes
temperature parameter.
Softmax function is applied to a vector to squeeze the values in a way that they sum up to 1.0:
som.nn.softmax(x) = exp(x/T) / sum(exp(x/T))
Low values for T result in a
strong separation of output values. High values for T
make output values more equal.