iTAMLOptions<T, TInput, TOutput>
Options & Configuration · AiDotNet.MetaLearning.Options
Configuration options for the iTAML (incremental Task-Agnostic Meta-Learning) algorithm.
Inheritance: ModelOptions → iTAMLOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
How It Works
iTAML (Rajasegaran et al., 2020) prevents catastrophic forgetting by maintaining an EMA teacher model and applying knowledge distillation between teacher and student predictions. Task-balanced gradient weighting normalizes gradient magnitudes across tasks to prevent any single task from dominating the meta-update.
Constructors
| Constructor | Summary |
|---|---|
iTAMLOptions(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 EtaDecay { get; set; } |
beta in the paper’s meta-update weight eta = exp(-beta * t / T), where t / T is training progress (meta-iteration over NumMetaIterations). |
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 NumMetaIterations { get; set; } |
|
int? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |