Class LinearScheduler<T>

Namespace

AiDotNet.CurriculumLearning.Schedulers

Assembly

AiDotNet.dll

Curriculum scheduler with linear progression from easy to hard samples.

public class LinearScheduler<T> : CurriculumSchedulerBase<T>, ICurriculumScheduler<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance

object

CurriculumSchedulerBase<T>

LinearScheduler<T>

Implements

ICurriculumScheduler<T>

Inherited Members

CurriculumSchedulerBase<T>.NumOps

CurriculumSchedulerBase<T>.TotalEpochs

CurriculumSchedulerBase<T>.MinFraction

CurriculumSchedulerBase<T>.MaxFraction

CurriculumSchedulerBase<T>.CurrentPhase

CurriculumSchedulerBase<T>.CurrentEpoch

CurriculumSchedulerBase<T>.TotalPhases

CurriculumSchedulerBase<T>.CurrentPhaseNumber

CurriculumSchedulerBase<T>.IsComplete

CurriculumSchedulerBase<T>.GetDifficultyThreshold()

CurriculumSchedulerBase<T>.StepEpoch(CurriculumEpochMetrics<T>)

CurriculumSchedulerBase<T>.AdvancePhase()

CurriculumSchedulerBase<T>.Reset()

CurriculumSchedulerBase<T>.GetCurrentIndices(int[], int)

CurriculumSchedulerBase<T>.GetIndicesAtPhase(int[], int, T)

CurriculumSchedulerBase<T>.InterpolateFraction(T)

CurriculumSchedulerBase<T>.GetStatistics()

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: This scheduler increases the data fraction linearly over training epochs. It starts with easy samples and gradually includes more difficult samples at a constant rate.

Progression Pattern:

fraction(epoch) = min_fraction + (epoch / total_epochs) * (max_fraction - min_fraction)

Example: With minFraction=0.2 and maxFraction=1.0 over 10 epochs:

• Epoch 0: 20% easiest samples
• Epoch 5: 60% easiest samples
• Epoch 10: 100% of all samples

Best For:

• Tasks with evenly distributed difficulty
• When constant progression rate is desired
• Simple, predictable curriculum schedules

Constructors

LinearScheduler(int, T?, T?)

Initializes a new instance of the LinearScheduler<T> class.

public LinearScheduler(int totalEpochs, T? minFraction = default, T? maxFraction = default)

Parameters

totalEpochs int

Total number of training epochs.

minFraction T

Initial data fraction (default 0.1).

maxFraction T

Final data fraction (default 1.0).

Properties

Name

Gets the name of this scheduler.

public override string Name { get; }

Property Value

string

Methods

GetDataFraction()

Gets the current data fraction using linear interpolation.

public override T GetDataFraction()

Returns

T