public sealed class FeatureNoiseSigma : IMessage<FeatureNoiseSigma>, IEquatable<FeatureNoiseSigma>, IDeepCloneable<FeatureNoiseSigma>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class FeatureNoiseSigma.
Noise sigma by features. Noise sigma represents the standard deviation of the
gaussian kernel that will be used to add noise to interpolated inputs prior
to computing gradients.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-05 UTC."],[[["The `FeatureNoiseSigma` class in the Vertex AI v1beta1 API provides a way to add noise to interpolated inputs before computing gradients, using a Gaussian kernel."],["The class implements several interfaces, including `IMessage`, `IEquatable`, `IDeepCloneable`, and `IBufferMessage`, enabling it to work within the Google Protocol Buffers framework."],["Two versions of the `FeatureNoiseSigma` class are documented, version `1.0.0-beta21` (latest) and `1.0.0-beta20`, representing different releases of the API."],["The primary property of `FeatureNoiseSigma` is `NoiseSigma`, which is a `RepeatedField` of `NoiseSigmaForFeature` types, allowing the specification of noise sigma per feature."],["The `FeatureNoiseSigma` class provides two constructors: a default constructor and a constructor that accepts another `FeatureNoiseSigma` object for creating copies."]]],[]]
