HilbertSchmidtSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Nonlinear

Hilbert-Schmidt Independence Criterion (HSIC) based Feature Selection.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> โ†’ HilbertSchmidtSelector<T>

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

HSIC uses kernel methods to measure dependence between variables in a high-dimensional space. It can detect subtle nonlinear relationships that other methods might miss. Higher HSIC means stronger dependence between the feature and target.

How It Works

Selects features based on HSIC, a kernel-based measure of independence that can detect complex nonlinear relationships.

Constructors

Constructor Summary
HilbertSchmidtSelector(int nFeaturesToSelect, double kernelWidth, int[] columnIndices)

Properties

Property Summary
Vector<T> HSICValues { get; }
bool SupportsInverseTransform { get; }
double KernelWidth { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target)
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)
void Fit(Matrix<T> data, Vector<T> target)