Class UncertaintyPredictionResult<T, TOutput>

Namespace

AiDotNet.Models.Results

Assembly

AiDotNet.dll

Represents a prediction result augmented with uncertainty information.

public sealed class UncertaintyPredictionResult<T, TOutput>

Type Parameters

T

The numeric type used for uncertainty computations (e.g., float, double).

TOutput

The model's output type (e.g., Tensor<T>).

Inheritance

object

UncertaintyPredictionResult<T, TOutput>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

This type is returned by the facade method AiModelResult.PredictWithUncertainty(...).

For Beginners: This lets you ask the model both: - "What is the prediction?" - "How uncertain is that prediction?"

Constructors

UncertaintyPredictionResult(UncertaintyQuantificationMethod, TOutput, TOutput?, IReadOnlyDictionary<string, Tensor<T>>, RegressionConformalInterval<TOutput>?, ClassificationConformalPredictionSet?)

Initializes a new instance of the UncertaintyPredictionResult<T, TOutput> class.

public UncertaintyPredictionResult(UncertaintyQuantificationMethod methodUsed, TOutput prediction, TOutput? variance, IReadOnlyDictionary<string, Tensor<T>> metrics, RegressionConformalInterval<TOutput>? regressionInterval = null, ClassificationConformalPredictionSet? classificationSet = null)

Parameters

methodUsed UncertaintyQuantificationMethod

prediction TOutput

variance TOutput

metrics IReadOnlyDictionary<string, Tensor<T>>

regressionInterval RegressionConformalInterval<TOutput>

classificationSet ClassificationConformalPredictionSet

Properties

ClassificationSet

Gets an optional conformal classification prediction set, when configured and supported.

public ClassificationConformalPredictionSet? ClassificationSet { get; }

Property Value

ClassificationConformalPredictionSet

MethodUsed

Gets the uncertainty method that was used to produce this result.

public UncertaintyQuantificationMethod MethodUsed { get; }

Property Value

UncertaintyQuantificationMethod

Metrics

Gets additional uncertainty diagnostics.

public IReadOnlyDictionary<string, Tensor<T>> Metrics { get; }

Property Value

IReadOnlyDictionary<string, Tensor<T>>

Remarks

Keys are stable so downstream consumers do not need to branch on missing keys.

Prediction

Gets the point prediction (mean / expected prediction).

public TOutput Prediction { get; }

Property Value

TOutput

RegressionInterval

Gets an optional conformal regression interval, when configured and supported.

public RegressionConformalInterval<TOutput>? RegressionInterval { get; }

Property Value

RegressionConformalInterval<TOutput>

Variance

Gets the per-output predictive variance (when available).

public TOutput? Variance { get; }

Property Value

TOutput