BesselKernel<T>
Models & Types · AiDotNet.Kernels
Implements the Bessel kernel function for measuring similarity between data points.
Implements: IKernelFunction<T>
For Beginners
A kernel function is a mathematical tool that measures how similar two data points are. The Bessel kernel is a specialized similarity measure that works well for certain types of data, especially data with circular or radial patterns (like sound waves, vibrations, or heat distribution in circular objects). It’s named after Friedrich Bessel, a mathematician who studied these special mathematical functions in the 19th century.
How It Works
The Bessel kernel is based on the Bessel functions of the first kind, which are solutions to Bessel’s differential equation. This kernel is particularly useful for problems involving circular or cylindrical data patterns.
Think of the Bessel kernel as a way to compare data points while taking into account their “wave-like” or “oscillating” properties, similar to how ripples spread in water.
Example
using AiDotNet.Kernels;
using AiDotNet.Tensors.LinearAlgebra;
var kernel = new BesselKernel<double>();
var a = new Vector<double>(new[] { 1.0, 2.0, 3.0 });
var b = new Vector<double>(new[] { 1.5, 1.0, 2.5 });
double similarity = kernel.Calculate(a, b);
Console.WriteLine($"BesselKernel: K(a, b) = {similarity:F4}");
Constructors
| Constructor | Summary |
|---|---|
BesselKernel(T order, T sigma) |
Initializes a new instance of the Bessel kernel with optional parameters. |
Methods
| Method | Summary |
|---|---|
T Calculate(Vector<T> x1, Vector<T> x2) |
Calculates the Bessel kernel value between two vectors. |