Question

Why we generally use Softmax non-linearity function as last operation in-network?

Answer 1

It is because it takes in a vector of real numbers and returns a probability distribution. Its definition is as follows. Let x be a vector of real numbers (positive, negative, whatever, there are no constraints).

Then the i’th component of Softmax(x) is —

 

It should be clear that the output is a probability distribution: each element is non-negative and the sum over all components is 1.