softmax: Soft-Max function

In reservr: Fit Distributions and Neural Networks to Censored and Truncated Data

Soft-Max function

Description

Softmax for a vector x is defined as

Usage

softmax(x)

dsoftmax(x)

Arguments

x	A numeric vector or matrix

Details

s_i = \exp(x_i) / \sum_k \exp(x_k)

It satisfies sum(s) == 1.0 and can be used to smoothly enforce a sum constraint.

Value

softmax returns the softmax of x; rowwise if x is a matrix.

dsoftmax returns the Jacobi-matrix of softmax(x) at x. x must be a vector.

Examples

softmax(c(5, 5))
softmax(diag(nrow = 5, ncol = 6))

reservr documentation built on June 24, 2024, 5:10 p.m.