LeastConfidenceSampling<T>

Models & Types · AiDotNet.ActiveLearning

Implements least confidence sampling for active learning sample selection.

Implements: IActiveLearningStrategy<T>

For Beginners

Least confidence sampling selects samples where the model’s top prediction has the lowest probability. This is the simplest uncertainty measure, focusing on how confident the model is in its best guess.

How It Works

Formula: LC(x) = 1 - max P(y|x)

Interpretation:

Advantages:

Complexity: O(n × c) where n=pool size, c=number of classes.

Reference: Lewis, D.D. & Catlett, J. (1994). “Heterogeneous uncertainty sampling for supervised learning.”

Constructors

Constructor Summary
LeastConfidenceSampling() Initializes a new instance of the LeastConfidenceSampling class.

Properties

Property Summary
bool UseBatchDiversity { get; set; }
string Name { get; }

Methods

Method Summary
Dictionary<string, T> GetSelectionStatistics()
Vector<T> ComputeInformativenessScores(IFullModel<T, Tensor<T>, Tensor<T>> model, Tensor<T> unlabeledPool)
int[] SelectSamples(IFullModel<T, Tensor<T>, Tensor<T>> model, Tensor<T> unlabeledPool, int batchSize)