kernel-distance: Compute an Distance kernel
In pfocal: Fast Convolution of Matrices

euclidean_distance_kernel

R Documentation

Compute an Distance kernel

Description

Functions to compute a distance kernel.

Usage

euclidean_distance_kernel(vertical_radius, horizontal_radius = vertical_radius)

manhattan_distance_kernel(vertical_radius, horizontal_radius = vertical_radius)

minkowski_distance_kernel(
  p,
  vertical_radius,
  horizontal_radius = vertical_radius
)

chebyshev_distance_kernel(vertical_radius, horizontal_radius = vertical_radius)

vertical_distance_kernel(vertical_radius, horizontal_radius = vertical_radius)

horizontal_distance_kernel(
  vertical_radius,
  horizontal_radius = vertical_radius
)

distance_kernel(vertical_radius, horizontal_radius = vertical_radius)

Arguments

`vertical_radius`	[numeric] The kernel's radius in the vertical dimension.
`horizontal_radius`	[numeric] The kernel's radius in the horizontal dimension.
`p`	[numeric] Exponent parameter for the Minkowski distance.

Value

A matrix corresponding to the kernel.

Examples


distance_kernel(vertical_radius = 2, horizontal_radius = 2)
euclidean_distance_kernel(vertical_radius = 2, horizontal_radius = 2)
manhattan_distance_kernel(vertical_radius = 2, horizontal_radius = 2)
minkowski_distance_kernel(vertical_radius = 2, horizontal_radius = 2, p = 1)
chebyshev_distance_kernel(vertical_radius = 2, horizontal_radius = 2)
vertical_distance_kernel(vertical_radius = 2, horizontal_radius = 2)
horizontal_distance_kernel(vertical_radius = 2, horizontal_radius = 2)

pfocal documentation built on June 17, 2022, 5:07 p.m.