HyperNeRFMetaOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for HyperNeRF Meta-learning.

Inheritance: ModelOptions โ†’ HyperNeRFMetaOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

How It Works

Combines hypernetwork conditioning with NeRF-style positional encoding. Each parameter index is positionally encoded using sinusoidal frequencies, and combined with a task latent code to produce per-parameter learning rate modulation. This gives the hypernetwork structural awareness of parameter positions within the network.

Constructors

Constructor Summary
HyperNeRFMetaOptions(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; } Must stay null: this algorithm takes no plain gradient inner step (it adapts without one, or by its own update rule), so a supplied optimizer is rejected when the learner is built.
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 regression loss.
bool EnableCheckpointing { get; set; }
bool UseFirstOrder { get; set; } Whether to use the first-order approximation of the meta-gradient.
double ConditioningRegWeight { get; set; } L2 regularization weight on the conditioning MLP weights to prevent overfitting the hypernetwork.
double ConditioningStrength { get; set; } Strength of frequency-based conditioning modulation.
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int LatentDim { get; set; } Dimension of the task-specific latent code derived from gradient statistics.
int MetaBatchSize { get; set; }
int NumFrequencyBands { get; set; } Number of sinusoidal frequency bands for positional encoding of parameter indices.
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; }

Methods

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