CNAPOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for the Conditional Neural Adaptive Processes (CNAP) algorithm.

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

Implements: IMetaLearnerOptions<T>

For Beginners

CNAP learns to understand tasks from examples:

  1. It encodes examples (context points) into a task representation
  2. It uses this representation to generate task-specific fast weights
  3. The fast weights modify the base model to work well on that specific task

This is like having a teacher who can quickly understand what kind of problem you’re working on and adjust their teaching style accordingly.

How It Works

CNAP extends Neural Processes by conditioning on task-specific context points and learning to produce fast adaptation weights for each task. This enables effective few-shot learning through learned task representations.

Key Components:

  • Encoder: Processes context points into task representations
  • Adaptation Network: Generates task-specific fast weights from representations
  • Base Model: The neural network that gets modified by fast weights

Constructors

Constructor Summary
CNAPOptions(IFullModel<T, TInput, TOutput> metaModel) Initializes a new instance of the CNAPOptions class with the required meta-model.

Properties

Property Summary
FastWeightApplicationMode FastWeightMode { get; set; } Gets or sets how fast weights are applied to the model.
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Gets or sets the episodic data loader for sampling tasks.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } Gets or sets the meta-model to be trained.
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 meta-model’s default loss.
bool EnableCheckpointing { get; set; } Gets or sets whether to save checkpoints during training.
bool NormalizeFastWeights { get; set; } Gets or sets whether to normalize fast weights.
bool PredictUncertainty { get; set; } Gets or sets whether to predict uncertainty along with predictions.
bool UseAttention { get; set; } Gets or sets whether to use attention for aggregating context points.
bool UseFirstOrder { get; set; } Gets or sets whether to use first-order approximation.
bool UseLayerNorm { get; set; } Gets or sets whether to use layer normalization in networks.
double DropoutRate { get; set; } Gets or sets the dropout rate for regularization.
double FastWeightRegularization { get; set; } Gets or sets the regularization weight for fast weights.
double FastWeightScale { get; set; } Gets or sets the scale factor for fast weights.
double InnerLearningRate { get; set; } Gets or sets the learning rate for the inner loop (task adaptation).
double OuterLearningRate { get; set; } Gets or sets the learning rate for the outer loop (meta-update).
double UncertaintyWeight { get; set; } Gets or sets the weight for uncertainty loss when predicting uncertainty.
double? GradientClipThreshold { get; set; } Gets or sets the maximum gradient norm for gradient clipping.
int AdaptationNetworkLayers { get; set; } Gets or sets the number of layers in the adaptation network.
int AdaptationSteps { get; set; } Gets or sets the number of gradient steps to take during inner loop adaptation.
int CheckpointFrequency { get; set; } Gets or sets how often to save checkpoints.
int ContextSize { get; set; } Gets or sets the number of context points to use for encoding (support set size).
int EncoderLayers { get; set; } Gets or sets the number of layers in the encoder network.
int EvaluationFrequency { get; set; } Gets or sets how often to evaluate during meta-training.
int EvaluationTasks { get; set; } Gets or sets the number of tasks to use for evaluation.
int HiddenDimension { get; set; } Gets or sets the hidden dimension for the encoder and adaptation networks.
int MetaBatchSize { get; set; } Gets or sets the number of tasks to sample per meta-training iteration.
int NumAttentionHeads { get; set; } Gets or sets the number of attention heads when using attention.
int NumMetaIterations { get; set; } Gets or sets the total number of meta-training iterations to perform.
int RepresentationDimension { get; set; } Gets or sets the dimension of the task representation vector.
int? RandomSeed { get; set; } Gets or sets the random seed for reproducibility.

Methods

Method Summary
IMetaLearnerOptions<T> Clone() Creates a deep copy of the CNAP options.
bool IsValid() Validates that all CNAP configuration options are properly set.