Click or drag to resize

FactorizationByFastIndependentComponentAnalysisICAWithEvdWhitening Method

Runs a symmetric FastICA implementation based on an eigenvalue-decomposition (EVD) whitening step.

Namespace: Altaxo.Calc.LinearAlgebra.Double.Factorization
Assembly: AltaxoCore (in AltaxoCore.dll) Version: 4.8.3572.0 (4.8.3572.0)
Syntax
C#
Copy
public static (Matrix<double> S, Matrix<double> W, Matrix<double> A) ICAWithEvdWhitening(
	Matrix<double> X,
	int components,
	int maxIter = 200,
	double tol = 1E-06
)

Parameters

X  MatrixDouble
Input data matrix (samples x features). The matrix is centered in-place.
components  Int32
Number of independent components to estimate.
maxIter  Int32  (Optional)
Maximum number of iterations.
tol  Double  (Optional)
Tolerance used as convergence criterion.

Return Value

ValueTupleMatrixDouble, MatrixDouble, MatrixDouble
A tuple containing:
  • S: estimated source signals (components x samples)
  • W: unmixing matrix (components x components)
  • A: mixing matrix (components x components), equal to W-1
See Also