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

1 Answer

0 votes

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.

Related questions

0 votes
asked Jun 12, 2021 in Deep Learning by Robindeniel
0 votes
asked Dec 31, 2019 in Data Science by sharadyadav1986
0 votes
asked Jan 27, 2020 in TypeScript - JavaScript's Superset by AdilsonLima