RBFKernel

The squared-exponential (radial basis function) kernel with ARD length scales. This is the default kernel; it models very smooth response surfaces.

cov(x1, x2) = signalVariance * exp(-0.5 * sum_d ((x1_d - x2_d)/lengthScale_d)^2)

Constructors

constructor(signalVariance: Double, lengthScales: DoubleArray)

constructor(problemDefinition: ProblemDefinition, signalVariance: Double = 1.0)

Creates an RBF kernel whose ARD length scales default to the problem's per-input ranges.

open override fun cov(x1: DoubleArray, x2: DoubleArray): Double

The prior covariance between the responses at x1 and x2.

open override fun toString(): String