LRPExplanation<T>

Models & Types · AiDotNet.Interpretability.Explainers

Represents the result of an LRP analysis.

Constructors

Constructor Summary
LRPExplanation()

Properties

Property Summary
LRPRule Rule { get; set; } Gets or sets the LRP rule used.
T OutputValue { get; set; } Gets or sets the output value being explained.
T TotalNegativeRelevance { get; set; } Gets or sets the sum of negative relevance scores.
T TotalPositiveRelevance { get; set; } Gets or sets the sum of positive relevance scores.
Vector<T> Input { get; set; } Gets or sets the input instance.
Vector<T> Prediction { get; set; } Gets or sets the model prediction.
Vector<T> RelevanceScores { get; set; } Gets or sets the relevance scores for each input feature.
int OutputIndex { get; set; } Gets or sets the output index that was explained.
string[] FeatureNames { get; set; } Gets or sets the feature names.

Methods

Method Summary
List<ValueTuple<string, T>> GetNegativeRelevance() Gets features with negative relevance (contradicting the prediction).
List<ValueTuple<string, T>> GetPositiveRelevance() Gets features with positive relevance (supporting the prediction).
List<ValueTuple<string, T>> GetSortedRelevance() Gets relevance scores sorted by absolute value (most relevant first).
string ToString() Returns a human-readable summary.