NPAlgorithm<T, TInput, TOutput>

Models & Types · AiDotNet.MetaLearning.Algorithms

Implementation of Neural Process (NP) (Garnelo et al., 2018). Extends CNP with a latent variable z for modeling uncertainty and function correlations.

Inheritance: ModelBase<T, TInput, TOutput> → MetaLearnerBase<T, TInput, TOutput> → NeuralProcessBase<T, TInput, TOutput> → NPAlgorithm<T, TInput, TOutput>

Implements: IGeneratedParameterRegistrar<T>

How It Works

Algorithm:

Constructors

Constructor Summary
NPAlgorithm(NPOptions<T, TInput, TOutput> options)

Properties

Property Summary
MetaLearningAlgorithmType AlgorithmType { get; }

Methods

Method Summary
IModel<TInput, TOutput, ModelMetadata<T>> Adapt(IMetaLearningTask<T, TInput, TOutput> task)
T MetaTrain(TaskBatch<T, TInput, TOutput> taskBatch)