gk: Two dimensional Gaussian kernel

In rijpma/capelinker: Machine Learning-based Record Linkage for Historical South Africa

Two dimensional Gaussian kernel

Description

gk calculates the Gaussian similarity as the parallel distances between the elements of two vectors

Usage

gk(x1, x2, sigma = 1)

Arguments

x1	the numbers in x1 that should be compared to those in x2
x2	the numbers in x2 that should be compared to those in x1
sigma	parameter controlling the spread of the gaussian curve. The higher, the more tolerant we are are of differences. Defaults to 1.

Details

The Gaussian similarity is calculated as d(x_1, x_2) = e ^{ - \frac{\sqrt{(x_1 - x_2) ^ 2}}{\sigma^2}}

rijpma/capelinker documentation built on Nov. 7, 2024, 3:06 a.m.