MetaSGDAdaptedModel<T, TInput, TOutput>

Models & Types · AiDotNet.MetaLearning.Algorithms

Wrapper model for Meta-SGD adapted models that includes the per-parameter optimizer.

Implements: IModel<TInput, TOutput, ModelMetadata<T>>

How It Works

This model wraps an adapted model along with its per-parameter optimizer, allowing for further adaptation or inspection of learned coefficients.

Constructors

Constructor Summary
MetaSGDAdaptedModel(IFullModel<T, TInput, TOutput> model, PerParameterOptimizer<T, TInput, TOutput> optimizer, MetaSGDOptions<T, TInput, TOutput> options) Initializes a new instance of the MetaSGDAdaptedModel.

Properties

Property Summary
ModelMetadata<T> Metadata { get; } Gets the model metadata.
PerParameterOptimizer<T, TInput, TOutput> Optimizer { get; } Gets the per-parameter optimizer (for inspection or further adaptation).

Methods

Method Summary
ModelMetadata<T> GetModelMetadata() Gets the model metadata.
TOutput Predict(TInput input) Makes predictions using the adapted model.
Vector<T> GetParameters() Gets the current model parameters.
void SetParameters(Vector<T> parameters) Sets the model parameters.
void Train(TInput inputs, TOutput targets) Trains the model on the given data.