TETNPOptions<T, TInput, TOutput>
Options & Configuration · AiDotNet.MetaLearning.Options
Configuration options for Translation-Equivariant Transformer Neural Process (TE-TNP). Extends TNP with relative positional encodings for translation equivariance.
Inheritance: ModelOptions → TETNPOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
For Beginners
TE-TNP predicts functions like TNP but ensures that shifting all inputs by the same amount shifts all outputs correspondingly. This is achieved by using relative distances between points rather than absolute positions in the attention mechanism.
Constructors
| Constructor | Summary |
|---|---|
TETNPOptions(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 EquivarianceRegWeight { get; set; } |
Weight of an optional regularizer on the variance of the refined representations’ norms. |
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 MetaBatchSize { get; set; } |
|
int NumFrequencyBands { get; set; } |
Number of frequency bands for sinusoidal relative positional encoding. |
int NumHeads { get; set; } |
Number of attention heads for the equivariant self-attention. |
int NumMetaIterations { get; set; } |
|
int RepresentationDim { get; set; } |
Gets or sets the representation dimensionality. |
int? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |