Click or drag to resize
Accord.NET (logo)

GaussianEstimateTInput, TDistance Method (TInput, Int32, TDistance)

Estimates appropriate values for sigma given a data set.

Namespace:  Accord.Statistics.Kernels
Assembly:  Accord.Statistics (in Accord.Statistics.dll) Version: 3.8.0
Syntax
public static Gaussian Estimate<TInput, TDistance>(
	TInput[] inputs,
	int samples,
	TDistance distance
)
where TDistance : Object, IDistance<TInput>
Request Example View Source

Parameters

inputs
Type: TInput
The data set.
samples
Type: SystemInt32
The number of random samples to analyze.
distance
Type: TDistance
The distance function to be used in the Gaussian kernel. Default is SquareEuclidean.

Type Parameters

TInput
TDistance

Return Value

Type: Gaussian
A Gaussian kernel initialized with an appropriate sigma value.
Remarks
This method uses a simple heuristic to obtain appropriate values for sigma in a radial basis function kernel. The heuristic is shown by Caputo, Sim, Furesjo and Smola, "Appearance-based object recognition using SVMs: which kernel should I use?", 2002.
See Also