ArtificialBeeColony<T>
Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Metaheuristic
Artificial Bee Colony for feature selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> โ ArtificialBeeColony<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
Bees work together to find the best flowers. Some bees (employed) keep working on known flowers, others (onlookers) watch and join the bees with the best finds, and scout bees explore randomly for new flowers. This balance of exploitation and exploration helps find optimal feature subsets.
How It Works
Artificial Bee Colony is inspired by the foraging behavior of honey bees. Employed bees exploit known food sources, onlookers choose sources based on quality, and scouts search for new sources when old ones are exhausted.
Constructors
| Constructor | Summary |
|---|---|
ArtificialBeeColony(int nFeaturesToSelect, int colonySize, int maxIterations, int limit, int? randomState, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> FeatureScores { get; } |
|
bool SupportsInverseTransform { get; } |
|
int ColonySize { get; } |
|
int MaxIterations { 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) |