Class: Google::Cloud::AIPlatform::V1::FeatureNoiseSigma

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/aiplatform/v1/explanation.rb

Overview

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.

Defined Under Namespace

Classes: NoiseSigmaForFeature

Instance Attribute Summary collapse

Instance Attribute Details

#noise_sigma ⇒ ::Array<::Google::Cloud::AIPlatform::V1::FeatureNoiseSigma::NoiseSigmaForFeature>

Returns Noise sigma per feature. No noise is added to features that are not set.

Returns:



369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 369

class FeatureNoiseSigma
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Noise sigma for a single feature.
  # @!attribute [rw] name
  #   @return [::String]
  #     The name of the input feature for which noise sigma is provided. The
  #     features are defined in
  #     {::Google::Cloud::AIPlatform::V1::ExplanationMetadata#inputs explanation metadata inputs}.
  # @!attribute [rw] sigma
  #   @return [::Float]
  #     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 {::Google::Cloud::AIPlatform::V1::SmoothGradConfig#noise_sigma noise_sigma} but represents the
  #     noise added to the current feature. Defaults to 0.1.
  class NoiseSigmaForFeature
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end