softmax: Softmax and logsoftmax functions and their inverse functions

In bmm: Easy and Accessible Bayesian Measurement Models Using 'brms'

Softmax and logsoftmax functions and their inverse functions

Description

softmax returns the value of the softmax function softmaxinv returns the value of the inverse-softmax function

Usage

softmax(eta, lambda = 1)

softmaxinv(p, lambda = 1)

Arguments

eta	A numeric vector input
lambda	Tuning parameter (a single positive value)
p	A probability vector (i.e., numeric vector of non-negative values that sum to one)

Details

The softmax function is a bijective function that maps a real vector with length m-1 to a probability vector with length m with all non-zero probabilities. The present functions define the softmax function and its inverse, both with a tuning parameter.

The current functions define the softmax as:

\Large P(\eta_i) = \frac{e^{\lambda \eta_i}}{1+ \sum_{j=1}^m e^{\lambda \eta_j}}

Code adapted from the utilities package

Value

Value of the softmax function or its inverse

Examples

softmax(5:7)
softmaxinv(softmax(5:7))

bmm documentation built on May 29, 2024, 11:52 a.m.