Interface IConfidentDifficultyEstimator<T, TInput, TOutput>

Namespace

AiDotNet.CurriculumLearning.Interfaces

Assembly

AiDotNet.dll

Interface for difficulty estimators that can provide confidence in their estimates.

public interface IConfidentDifficultyEstimator<T, TInput, TOutput> : IDifficultyEstimator<T, TInput, TOutput>

Type Parameters

T

The numeric type.

TInput

The input data type.

TOutput

The output data type.

Inherited Members

IDifficultyEstimator<T, TInput, TOutput>.Name

IDifficultyEstimator<T, TInput, TOutput>.RequiresModel

IDifficultyEstimator<T, TInput, TOutput>.EstimateDifficulty(TInput, TOutput, IFullModel<T, TInput, TOutput>)

IDifficultyEstimator<T, TInput, TOutput>.EstimateDifficulties(IDataset<T, TInput, TOutput>, IFullModel<T, TInput, TOutput>)

IDifficultyEstimator<T, TInput, TOutput>.Update(int, IFullModel<T, TInput, TOutput>)

IDifficultyEstimator<T, TInput, TOutput>.Reset()

IDifficultyEstimator<T, TInput, TOutput>.GetSortedIndices(Vector<T>)

Methods

EstimateDifficultyWithConfidence(TInput, TOutput, IFullModel<T, TInput, TOutput>?)

Gets both difficulty estimate and confidence for a sample.

(T Difficulty, T Confidence) EstimateDifficultyWithConfidence(TInput input, TOutput expectedOutput, IFullModel<T, TInput, TOutput>? model = null)

Parameters

input TInput

The input sample.

expectedOutput TOutput

The expected output.

model IFullModel<T, TInput, TOutput>

The model to use.

Returns

(T Accuracy, T Loss)

Tuple of (difficulty, confidence) where confidence is typically in [0, 1].