softmax()

Compute softmax probabilities.

Usage

softmax(values)

For a vector \(z\), the softmax of element \(j\) is:

\[ \text{softmax}(z)_j = \frac{e^{z_j}}{\sum_{k=1}^{K} e^{z_k}} \]

Parameters

values: list

Input values.

Returns

list

Probability distribution that sums to 1.