CompetenceBasedScheduler<T>

Models & Types · AiDotNet.CurriculumLearning.Schedulers

Curriculum scheduler that advances based on model competence/mastery.

Inheritance: CurriculumSchedulerBase<T> → CompetenceBasedScheduler<T>

Implements: ICompetenceBasedScheduler<T>

For Beginners

This scheduler tracks how well the model is learning and only advances to harder content when the model has “mastered” the current difficulty level. Think of it like a tutor who won’t move to harder problems until you’ve shown you understand the current ones.

How It Works

How It Works:

Competence Metrics:

References:

Constructors

Constructor Summary
CompetenceBasedScheduler(int totalEpochs, T competenceThreshold, CompetenceMetricType metricType, int patienceEpochs, T minImprovement, T smoothingFactor, T minFraction, T maxFraction, int? totalPhases) Initializes a new instance of the CompetenceBasedScheduler class.

Properties

Property Summary
T CompetenceThreshold { get; set; } Gets or sets the competence threshold required to advance phases.
T CurrentCompetence { get; } Gets the current competence level of the model.
string Name { get; } Gets the name of this scheduler.

Methods

Method Summary
Dictionary<string, object> GetStatistics() Gets scheduler-specific statistics.
T GetDataFraction() Gets the current data fraction based on competence-driven phase.
bool HasMasteredCurrentContent() Gets whether the model has mastered the current curriculum content.
bool StepEpoch(CurriculumEpochMetrics<T> epochMetrics) Updates the scheduler after an epoch, potentially advancing phases.
void Reset() Resets the scheduler to initial state.
void UpdateCompetence(CurriculumEpochMetrics<T> metrics) Updates the competence estimate based on model performance.