ExpertDefinedDifficultyEstimator<T, TInput, TOutput>
Models & Types · AiDotNet.CurriculumLearning.DifficultyEstimators
Difficulty estimator using pre-defined or expert-provided difficulty scores.
Inheritance: DifficultyEstimatorBase<T, TInput, TOutput> → ExpertDefinedDifficultyEstimator<T, TInput, TOutput>
For Beginners
This estimator uses difficulty scores provided by domain experts or predefined heuristics. Unlike model-based estimators, it doesn’t require a trained model to estimate difficulty.
How It Works
Use Cases:
Difficulty Sources:
Constructors
| Constructor | Summary |
|---|---|
ExpertDefinedDifficultyEstimator(Func<TInput, TOutput, T> difficultyFunction, bool normalize) |
Initializes a new instance with a difficulty function. |
ExpertDefinedDifficultyEstimator(Vector<T> difficulties, bool normalize) |
Initializes a new instance with a difficulty function. |
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 |
|---|---|
ExpertDefinedDifficultyEstimator<T, TInput, TOutput> FromIndex(int totalSamples, bool ascending) |
Creates an estimator with difficulty based on sample index. |
ExpertDefinedDifficultyEstimator<T, TInput, TOutput> Random(int totalSamples, int? seed) |
Creates an estimator with random difficulty scores. |
T EstimateDifficulty(TInput input, TOutput expectedOutput, IFullModel<T, TInput, TOutput> model) |
Estimates the difficulty of a single sample. |
Vector<T> EstimateDifficulties(IDataset<T, TInput, TOutput> dataset, IFullModel<T, TInput, TOutput> model) |
Estimates difficulty scores for all samples in a dataset. |
void Update(int epoch, IFullModel<T, TInput, TOutput> model) |
Updates the difficulty estimator (no-op for expert-defined). |