Vertex AI v1beta1 API - Class FeatureNoiseSigma.Types.NoiseSigmaForFeature (1.0.0-beta62)

Version latest

• 1.0.0-beta61 (latest)
• 1.0.0-beta60

public sealed class FeatureNoiseSigma.Types.NoiseSigmaForFeature : IMessage<FeatureNoiseSigma.Types.NoiseSigmaForFeature>, IEquatable<FeatureNoiseSigma.Types.NoiseSigmaForFeature>, IDeepCloneable<FeatureNoiseSigma.Types.NoiseSigmaForFeature>, IBufferMessage, IMessage

Reference documentation and code samples for the Vertex AI v1beta1 API class FeatureNoiseSigma.Types.NoiseSigmaForFeature.

Noise sigma for a single feature.

Inheritance

object > FeatureNoiseSigma.Types.NoiseSigmaForFeature

Implements

IMessageFeatureNoiseSigmaTypesNoiseSigmaForFeature, IEquatableFeatureNoiseSigmaTypesNoiseSigmaForFeature, IDeepCloneableFeatureNoiseSigmaTypesNoiseSigmaForFeature, IBufferMessage, IMessage

Inherited Members

object.GetHashCode()

object.GetType()

object.ToString()

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.dll

Constructors

NoiseSigmaForFeature()

public NoiseSigmaForFeature()

NoiseSigmaForFeature(NoiseSigmaForFeature)

public NoiseSigmaForFeature(FeatureNoiseSigma.Types.NoiseSigmaForFeature other)

Parameter
Name	Description
other	FeatureNoiseSigmaTypesNoiseSigmaForFeature

Properties

Name

public string Name { get; set; }

The name of the input feature for which noise sigma is provided. The features are defined in [explanation metadata inputs][google.cloud.aiplatform.v1beta1.ExplanationMetadata.inputs].

Property Value
Type	Description
string

Sigma

public float Sigma { get; set; }

This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma] but represents the noise added to the current feature. Defaults to 0.1.

Property Value
Type	Description
float