ActiveLearningOptions

Options & Configuration ยท AiDotNet.Models.Options

Represents configuration options for active learning.

Inheritance: ModelOptions โ†’ ActiveLearningOptions

For Beginners

Active learning helps when labeling data is expensive or time-consuming. Instead of randomly selecting samples to label, active learning intelligently picks the samples that would be most helpful for training the model. This can dramatically reduce the number of labels needed while achieving similar or better performance.

How It Works

Typical Usage:

How to Choose a Strategy:

Constructors

Constructor Summary
ActiveLearningOptions()

Properties

Property Summary
ActiveLearningStrategyType Strategy { get; set; } Gets or sets the active learning strategy to use.
bool NormalizeScores { get; set; } Gets or sets whether to normalize informativeness scores before selection.
bool UseBatchDiversity { get; set; } Gets or sets whether to consider diversity when selecting multiple samples in a batch.
double DensityBeta { get; set; } Gets or sets the beta parameter for DensityWeightedSampling.
double DiversityWeight { get; set; } Gets or sets the weight for diversity component in hybrid strategies.
double DropoutRate { get; set; } Gets or sets the dropout rate for Monte Carlo Dropout in BALD/BatchBALD.
int BatchSize { get; set; } Gets or sets the number of samples to select in each active learning iteration.
int CommitteeSize { get; set; } Gets or sets the number of committee members for QueryByCommittee strategy.
int MinimumPoolSize { get; set; } Gets or sets the minimum number of samples required in the unlabeled pool.
int NumClusters { get; set; } Gets or sets the number of clusters for diversity-based methods.
int NumMcSamples { get; set; } Gets or sets the number of Monte Carlo samples for BALD strategy.
int NumNeighbors { get; set; } Gets or sets the number of nearest neighbors for density estimation.
string UncertaintyMeasure { get; set; } Gets or sets the uncertainty measure for UncertaintySampling strategy.