classification.jl
Unit for classification and related functions.
Category | Output |
---|---|
1. Probability | functions taking probabilities as input or output |
Probability
Function | Description |
---|---|
softmax | compute softmax probabilities |
Documentation:
PosDefManifold.softmax
— Function.softmax(χ::Vector{T}) where T<:Real
Given a real vector of $k$ non-negative scores $χ=c_1,...,c_k$, return the vector $π=p_1,...,p_k$ of their softmax probabilities, as per
$p_i=\frac{\textrm{e}^{c_i}}{\sum_{i=1}^{k}\textrm{e}^{c_i}}$.
Examples
χ=[1.0, 2.3, 0.4, 5.0]
π=softmax(χ)