RecurrentHyperNetOptions<T, TInput, TOutput>
Options & Configuration ยท AiDotNet.MetaLearning.Options
Configuration options for Recurrent HyperNetwork meta-learning.
Inheritance: ModelOptions โ RecurrentHyperNetOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
How It Works
A GRU-like recurrent cell processes gradient information at each adaptation step, maintaining hidden state that captures the optimization trajectory. The recurrent output modulates per-parameter learning rates, enabling adaptive step sizes that evolve through the inner loop.
Constructors
| Constructor | Summary |
|---|---|
RecurrentHyperNetOptions(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 multi-class classification loss. |
bool EnableCheckpointing { get; set; } |
|
bool UseFirstOrder { get; set; } |
Whether to use the first-order approximation of the meta-gradient. |
double CellRegWeight { get; set; } |
L2 regularization weight on recurrent cell state magnitude to prevent unbounded hidden state growth. |
double ForgetBias { get; set; } |
Initial forget gate bias. |
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 HiddenStateDim { get; set; } |
Dimension of the GRU hidden state. |
int InputDim { get; set; } |
Gradient compression dimension for feeding into the recurrent cell. |
int MetaBatchSize { get; set; } |
|
int NumMetaIterations { get; set; } |
|
int? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |