Class TADAMOptions<T, TInput, TOutput>

Namespace

AiDotNet.MetaLearning.Options

Assembly

AiDotNet.dll

Configuration options for Task-Dependent Adaptive Metric (TADAM) algorithm.

public class TADAMOptions<T, TInput, TOutput> : IMetaLearnerOptions<T>

Type Parameters

T

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

TInput

The input data type (e.g., Matrix<T>, Tensor<T>).

TOutput

The output data type (e.g., Vector<T>, Tensor<T>).

Inheritance

object

TADAMOptions<T, TInput, TOutput>

Implements

IMetaLearnerOptions<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

TADAM extends prototypical networks by incorporating task-dependent metric learning. It uses task conditioning (TC) to modulate the feature extraction process based on the task at hand, and metric scaling to adapt distances in embedding space.

For Beginners: TADAM improves on Prototypical Networks by:

1. Task Conditioning (TC): Adjusts features based on the specific task
2. Metric Scaling: Learns how to weight different feature dimensions
3. Auxiliary Co-Training: Uses additional classification to improve features

Think of it as ProtoNets that "pay attention" to what matters for each specific task.

Constructors

TADAMOptions(IFullModel<T, TInput, TOutput>)

Initializes a new instance of the TADAMOptions class with the required meta-model.

public TADAMOptions(IFullModel<T, TInput, TOutput> metaModel)

Parameters

metaModel IFullModel<T, TInput, TOutput>

The feature encoder to be trained (required).

Exceptions

ArgumentNullException

Thrown when metaModel is null.

Properties

AdaptationSteps

Gets or sets the number of adaptation steps.

public int AdaptationSteps { get; set; }

Property Value

int

Default is 1 (TADAM uses feed-forward task conditioning).

AuxiliaryLossWeight

Gets or sets the weight for auxiliary loss.

public double AuxiliaryLossWeight { get; set; }

Property Value

double

Default is 0.5.

CheckpointFrequency

Gets or sets how often to save checkpoints.

public int CheckpointFrequency { get; set; }

Property Value

int

DataLoader

Gets or sets the episodic data loader for sampling tasks. Default: null (tasks must be provided manually to MetaTrain).

public IEpisodicDataLoader<T, TInput, TOutput>? DataLoader { get; set; }

Property Value

IEpisodicDataLoader<T, TInput, TOutput>

EmbeddingDimension

Gets or sets the embedding dimension.

public int EmbeddingDimension { get; set; }

Property Value

int

Default is 512.

EnableCheckpointing

Gets or sets whether to save model checkpoints.

public bool EnableCheckpointing { get; set; }

Property Value

bool

EvaluationFrequency

Gets or sets how often to evaluate the meta-learner.

public int EvaluationFrequency { get; set; }

Property Value

int

EvaluationTasks

Gets or sets the number of tasks to use for evaluation.

public int EvaluationTasks { get; set; }

Property Value

int

GradientClipThreshold

Gets or sets the maximum gradient norm for gradient clipping.

public double? GradientClipThreshold { get; set; }

Property Value

double?

Default is 10.0.

InitialTemperature

Gets or sets the initial value for the learnable temperature parameter.

public double InitialTemperature { get; set; }

Property Value

double

Default is 1.0.

Remarks

The temperature controls how "soft" or "hard" the distance-based classification is. Lower values make the softmax sharper (more confident predictions).

InnerLearningRate

Gets or sets the learning rate for the inner loop (not used in TADAM).

public double InnerLearningRate { get; set; }

Property Value

double

Default is 0.01.

InnerOptimizer

Gets or sets the optimizer for inner loop updates. Default: null (TADAM uses feed-forward comparison with task conditioning).

public IGradientBasedOptimizer<T, TInput, TOutput>? InnerOptimizer { get; set; }

Property Value

IGradientBasedOptimizer<T, TInput, TOutput>

L2Regularization

Gets or sets the L2 regularization strength.

public double L2Regularization { get; set; }

Property Value

double

Default is 0.0 (no regularization).

LossFunction

Gets or sets the loss function for training. Default: null (uses cross-entropy loss internally).

public ILossFunction<T>? LossFunction { get; set; }

Property Value

ILossFunction<T>

MetaBatchSize

Gets or sets the number of tasks to sample per meta-training iteration.

public int MetaBatchSize { get; set; }

Property Value

int

Default is 4.

MetaModel

Gets or sets the meta-model (feature encoder) to be trained. This is the only required property.

public IFullModel<T, TInput, TOutput> MetaModel { get; set; }

Property Value

IFullModel<T, TInput, TOutput>

Remarks

The meta-model should be a feature encoder that maps inputs to an embedding space. TADAM will apply task conditioning to modulate the extracted features.

For Beginners: This is typically a CNN for images. TADAM will learn to adjust how this encoder works based on each specific task.

MetaOptimizer

Gets or sets the optimizer for network updates. Default: null (uses built-in Adam optimizer with OuterLearningRate).

public IGradientBasedOptimizer<T, TInput, TOutput>? MetaOptimizer { get; set; }

Property Value

IGradientBasedOptimizer<T, TInput, TOutput>

NormalizeEmbeddings

Gets or sets whether to normalize embeddings.

public bool NormalizeEmbeddings { get; set; }

Property Value

bool

Default is true.

NumClasses

Gets or sets the number of output classes.

public int NumClasses { get; set; }

Property Value

int

Default is 5.

NumMetaIterations

Gets or sets the total number of meta-training iterations.

public int NumMetaIterations { get; set; }

Property Value

int

Default is 1000.

OuterLearningRate

Gets or sets the learning rate for the outer loop (encoder training).

public double OuterLearningRate { get; set; }

Property Value

double

Default is 0.001.

RandomSeed

Gets or sets the random seed for reproducibility.

public int? RandomSeed { get; set; }

Property Value

int?

TaskEmbeddingDimension

Gets or sets the dimension of task embeddings.

public int TaskEmbeddingDimension { get; set; }

Property Value

int

Default is 64.

UseAuxiliaryCoTraining

Gets or sets whether to use auxiliary co-training.

public bool UseAuxiliaryCoTraining { get; set; }

Property Value

bool

Default is false.

Remarks

For Beginners: Auxiliary co-training adds an extra classification objective to help learn better features. It can improve performance but adds computational cost.

UseFirstOrder

Gets or sets whether to use first-order approximation.

public bool UseFirstOrder { get; set; }

Property Value

bool

Default is true since TADAM doesn't use gradient-based inner loop.

UseMetricScaling

Gets or sets whether to use metric scaling.

public bool UseMetricScaling { get; set; }

Property Value

bool

Default is true.

Remarks

For Beginners: Metric scaling learns to weight different dimensions of the embedding space differently when computing distances.

UseTaskConditioning

Gets or sets whether to use task conditioning (FiLM layers).

public bool UseTaskConditioning { get; set; }

Property Value

bool

Default is true.

Remarks

For Beginners: Task conditioning adjusts the feature encoder based on what task is being solved. This helps the network adapt its representation.

Methods

Clone()

Creates a deep copy of the TADAM options.

public IMetaLearnerOptions<T> Clone()

Returns

IMetaLearnerOptions<T>

A new TADAMOptions instance with the same configuration.

IsValid()

Validates that all TADAM configuration options are properly set.

public bool IsValid()

Returns

bool

True if the configuration is valid; otherwise, false.