ConfidenceBasedDifficultyEstimator<T, TInput, TOutput>

Models & Types · AiDotNet.CurriculumLearning.DifficultyEstimators

Difficulty estimator based on model prediction confidence.

Inheritance: DifficultyEstimatorBase<T, TInput, TOutput> → ConfidenceBasedDifficultyEstimator<T, TInput, TOutput>

Implements: IConfidentDifficultyEstimator<T, TInput, TOutput>

For Beginners

This estimator uses the model’s confidence in its predictions as a measure of difficulty. Low confidence predictions indicate the model is uncertain, suggesting the sample is harder.

How It Works

How It Works:

Confidence Metrics:

References:

Constructors

Constructor Summary
ConfidenceBasedDifficultyEstimator(ConfidenceMetricType metricType, bool normalize) Initializes a new instance of the ConfidenceBasedDifficultyEstimator class.

Properties

Property Summary
bool RequiresModel { get; } Gets whether this estimator requires the model.
string Name { get; } Gets the name of this estimator.

Methods

Method Summary
T EstimateDifficulty(TInput input, TOutput expectedOutput, IFullModel<T, TInput, TOutput> model) Estimates the difficulty of a single sample based on prediction confidence.
ValueTuple<T, T> EstimateDifficultyWithConfidence(TInput input, TOutput expectedOutput, IFullModel<T, TInput, TOutput> model) Gets both difficulty estimate and confidence for a sample.
Vector<T> EstimateDifficulties(IDataset<T, TInput, TOutput> dataset, IFullModel<T, TInput, TOutput> model) Estimates difficulty scores for all samples.