GradCAMSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Neural

GradCAM++ based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

GradCAM++ extends GradCAM by using weighted combinations of positive partial derivatives. It identifies which features the model focuses on when making predictions. Features with higher activation weights are considered more important for the model’s decisions.

How It Works

Selects features using gradient-weighted class activation mapping, measuring feature importance through gradient flow analysis.

Constructors

Constructor Summary
GradCAMSelector(int nFeaturesToSelect, int[] columnIndices)

Properties

Property Summary
Vector<T> ActivationWeights { get; }
bool SupportsInverseTransform { 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)