Class UncertaintyStats<T>

Namespace

AiDotNet.Models

Assembly

AiDotNet.dll

Represents uncertainty-quantification diagnostics aggregated over a dataset.

public sealed class UncertaintyStats<T>

Type Parameters

T

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

Inheritance

object

UncertaintyStats<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

This container is designed to integrate with the existing AiDotNet evaluation pipeline by living alongside ErrorStats<T> and PredictionStats<T> within DataSetStats<T, TInput, TOutput>.

For Beginners: This stores summary uncertainty metrics (like average entropy) for an entire dataset, similar to how accuracy or error metrics summarize model quality.

Properties

Metrics

Gets a dictionary of aggregate uncertainty metrics for the dataset.

public Dictionary<string, T> Metrics { get; }

Property Value

Dictionary<string, T>

Remarks

Keys are stable so consumers do not have to branch on missing keys. When a metric is not computable, it should be populated with a sensible default (typically 0).

Methods

Empty()

Creates an empty UncertaintyStats<T> instance.

public static UncertaintyStats<T> Empty()

Returns

UncertaintyStats<T>