Class CurriculumTeacherModel<T>

Namespace

AiDotNet.KnowledgeDistillation.Teachers

Assembly

AiDotNet.dll

Curriculum teacher that wraps a base teacher for curriculum learning scenarios.

public class CurriculumTeacherModel<T> : TeacherModelBase<Vector<T>, Vector<T>, T>, ITeacherModel<Vector<T>, Vector<T>>, IJitCompilable<T>

Type Parameters

T

The numeric type for calculations (e.g., double, float).

Inheritance

object

TeacherModelBase<Vector<T>, Vector<T>, T>

CurriculumTeacherModel<T>

Implements

ITeacherModel<Vector<T>, Vector<T>>

IJitCompilable<T>

Inherited Members

TeacherModelBase<Vector<T>, Vector<T>, T>.NumOps

TeacherModelBase<Vector<T>, Vector<T>, T>.OutputDimension

TeacherModelBase<Vector<T>, Vector<T>, T>.GetLogits(Vector<T>)

TeacherModelBase<Vector<T>, Vector<T>, T>.SupportsJitCompilation

TeacherModelBase<Vector<T>, Vector<T>, T>.ExportComputationGraph(List<ComputationNode<T>>)

TeacherModelBase<Vector<T>, Vector<T>, T>.CheckWrappedModelJitSupport(ITeacherModel<Vector<T>, Vector<T>>)

TeacherModelBase<Vector<T>, Vector<T>, T>.DelegateJitExport(ITeacherModel<Vector<T>, Vector<T>>, List<ComputationNode<T>>, string)

TeacherModelBase<Vector<T>, Vector<T>, T>.ThrowJitNotSupported(string, string)

TeacherModelBase<Vector<T>, Vector<T>, T>.ValidateInput(Vector<T>, string)

TeacherModelBase<Vector<T>, Vector<T>, T>.Softmax(Vector<T>, double)

TeacherModelBase<Vector<T>, Vector<T>, T>.ApplyTemperatureSoftmax(Vector<T>, double)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

Architecture Note: This class provides a simple wrapper around a base teacher. Curriculum learning logic (adjusting difficulty over time) should be implemented in the training loop or distillation strategy, not in the teacher model.

The teacher model's responsibility is only to provide predictions (logits). Curriculum decisions (which samples to show, how to adjust temperature/alpha) belong in the strategy or trainer layer.

Constructors

CurriculumTeacherModel(ITeacherModel<Vector<T>, Vector<T>>)

Initializes a new instance of the CurriculumTeacherModel class.

public CurriculumTeacherModel(ITeacherModel<Vector<T>, Vector<T>> baseTeacher)

Parameters

baseTeacher ITeacherModel<Vector<T>, Vector<T>>

The underlying teacher model.

Properties

OutputDimension

Gets the output dimension from the base teacher.

public override int OutputDimension { get; }

Property Value

int

SupportsJitCompilation

Gets whether this teacher supports JIT compilation.

public override bool SupportsJitCompilation { get; }

Property Value

bool

true if the base teacher implements IJitCompilable and supports JIT; otherwise, false.

Methods

ExportComputationGraph(List<ComputationNode<T>>)

Exports the computation graph by delegating to the base teacher.

public override ComputationNode<T> ExportComputationGraph(List<ComputationNode<T>> inputNodes)

Parameters

inputNodes List<ComputationNode<T>>

List to populate with input computation nodes.

Returns

ComputationNode<T>

The output computation node from the base teacher.

Exceptions

NotSupportedException

Thrown when the base teacher does not support JIT compilation.

GetLogits(Vector<T>)

Gets logits from the base teacher.

public override Vector<T> GetLogits(Vector<T> input)

Parameters

input Vector<T>

The input data.

Returns

Vector<T>

Raw logits from the base teacher.