IUncertaintyEstimator<T>
Interfaces · AiDotNet.UncertaintyQuantification.Interfaces
Defines the contract for models that can estimate prediction uncertainty.
Known implementations: BayesianNeuralNetwork<T>, DeepEnsemble<T>, MCDropoutNeuralNetwork<T>
For Beginners
Uncertainty estimation helps you understand how confident a model is in its predictions.
Think of it like a weather forecast that not only predicts rain but also tells you how sure it is:
- “90% chance of rain” shows high confidence
- “50% chance of rain” shows high uncertainty
This interface is for models that can provide both a prediction and an estimate of how uncertain that prediction is. This is crucial for safety-critical applications like medical diagnosis or autonomous vehicles.
Methods
| Method | Summary |
|---|---|
Tensor<T> EstimateAleatoricUncertainty(Tensor<T> input) |
Estimates aleatoric uncertainty (data noise) for the given input. |
Tensor<T> EstimateEpistemicUncertainty(Tensor<T> input) |
Estimates epistemic uncertainty (model uncertainty) for the given input. |
UncertaintyPredictionResult<T, Tensor<T>> PredictWithUncertainty(Tensor<T> input) |
Predicts output with uncertainty estimates for a single input. |