TaskCondHyperNetOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for Task-Conditioned HyperNetwork.

Inheritance: ModelOptions → TaskCondHyperNetOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

How It Works

A hypernetwork generates task-specific parameter deltas conditioned on a task embedding derived from support-set gradient statistics. The hypernetwork is a 2-layer MLP: embedding → hidden → parameter delta, added to the meta-initialization.

Constructors

Constructor Summary
TaskCondHyperNetOptions(IFullModel<T, TInput, TOutput> metaModel) Creates options for meta-learning metaModel, with the default settings.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Episodic data loader that supplies the meta-training tasks; null when tasks are passed to training directly.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } The model whose parameters the meta-learner trains to adapt quickly to new tasks.
IGradientBasedOptimizer<T, TInput, TOutput> InnerOptimizer { get; set; } Optimizer for task adaptation.
IGradientBasedOptimizer<T, TInput, TOutput> MetaOptimizer { get; set; } Optimizer for the meta-update.
ILossFunction<T> LossFunction { get; set; } Loss function for meta-training; null uses the default multi-class classification loss.
bool EnableCheckpointing { get; set; }
bool UseFirstOrder { get; set; } Whether to use the first-order approximation of the meta-gradient.
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int ChunkSize { get; set; } Chunk size for chunked hypernetwork output (generates parameters in chunks to reduce hypernetwork size).
int EmbeddingDim { get; set; } Dimension of the task embedding derived from gradient statistics.
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int HyperHiddenDim { get; set; } Hidden dimension of the hypernetwork MLP.
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; }

Methods

Method Summary
IMetaLearnerOptions<T> Clone()
bool IsValid()