IGradientBatchStrategy<T, TInput, TOutput>

Interfaces · AiDotNet.ActiveLearning.Interfaces

Interface for gradient-based batch selection (e.g., BADGE).

Implements: IBatchStrategy<T, TInput, TOutput>

Known implementations: GradientBatchStrategy<T, TInput, TOutput>

For Beginners

BADGE (Batch Active learning by Diverse Gradient Embeddings) uses gradient embeddings to represent samples, then selects a diverse set using k-means++.

Methods

Method Summary
Matrix<T> ComputeGradientEmbeddings(IFullModel<T, TInput, TOutput> model, IDataset<T, TInput, TOutput> samples) Computes gradient embeddings for samples.
int[] KMeansPlusPlusSelection(Matrix<T> embeddings, int batchSize) Selects samples using k-means++ initialization on gradient embeddings.