PerformancePlateauCriterion<T>
Models & Types · AiDotNet.ActiveLearning.StoppingCriteria
Stopping criterion based on performance plateau detection.
Implements: IStoppingCriterion<T>
For Beginners
This criterion stops learning when the model’s performance (accuracy or validation score) stops improving significantly. Adding more labeled data at this point is unlikely to help.
How It Works
How It Works:
Key Parameters:
Reference: Early stopping is a common regularization technique in deep learning.
Constructors
| Constructor | Summary |
|---|---|
PerformancePlateauCriterion() |
Initializes a new PerformancePlateau criterion with default parameters. |
PerformancePlateauCriterion(int windowSize, int patience, double minImprovement, bool useValidation) |
Initializes a new PerformancePlateau criterion with specified parameters. |
Properties
| Property | Summary |
|---|---|
string Description { get; } |
|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
T GetProgress(ActiveLearningContext<T> context) |
|
bool ShouldStop(ActiveLearningContext<T> context) |
|
void Reset() |