SimulatedAnnealingSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Optimization

Simulated Annealing based Feature Selection.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → SimulatedAnnealingSelector<T>

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Like cooling metal, this starts with high “temperature” where it accepts almost any change, then gradually cools down and becomes pickier. This helps find good feature combinations by exploring broadly first, then refining.

How It Works

Uses simulated annealing optimization to find optimal feature subsets by accepting both improvements and occasionally worse solutions to escape local optima.

Constructors

Constructor Summary
SimulatedAnnealingSelector(int nFeaturesToSelect, double initialTemperature, double coolingRate, int nIterations, int? randomState, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureImportances { get; }
bool SupportsInverseTransform { get; }
double CoolingRate { get; }
double InitialTemperature { 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)