F# Data
Deedle
R Provider
F# ChartingSquaredExp
Isotropic squared exponential covariance function also known as the Gaussian kernel or RBF kernel
k(x,y) = σ² exp(-1/(2lengthscale²) * (x - y)²) + δ[x=y] σ²_{noise}
σ² is the signal variance σ²_{noise} is the noise variance
Constructors
| Constructor | Description |
new(...)
Signature: (lengthscale:float * signalVariance:float * noiseVariance:float) -> SquaredExp
|
|
Instance members
| Instance member | Description |
GaussianProcess()
Signature: unit -> GaussianProcess<float>
|
Creates Gaussian process with squared exponential kernel function and zero mean. |
Kernel(x1, x2)
Signature: (x1:float * x2:float) -> float
|
Construct a kernel function that can be used in a Gaussian process |
Lengthscale
Signature: float
|
|
NoiseVariance
Signature: float
|
|
Parameters
Signature: float []
|
|
SignalVariance
Signature: float
|
|
