Class: Google::Cloud::AIPlatform::V1::SmoothGradConfig

Inherits:

Object

• Object
• Google::Cloud::AIPlatform::V1::SmoothGradConfig

Extended by:

Protobuf::MessageExts::ClassMethods

Includes:

Protobuf::MessageExts

Defined in:

proto_docs/google/cloud/aiplatform/v1/explanation.rb

Overview

Config for SmoothGrad approximation of gradients.

When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

Instance Attribute Summary

• #feature_noise_sigma ⇒ ::Google::Cloud::AIPlatform::V1::FeatureNoiseSigma

  This is similar to noise_sigma, but provides additional flexibility.

• #noise_sigma ⇒ ::Float

  This is a single float value and will be used to add noise to all the features.

• #noisy_sample_count ⇒ ::Integer

  The number of gradient samples to use for approximation.

Instance Attribute Details

#feature_noise_sigma ⇒ ::Google::Cloud::AIPlatform::V1::FeatureNoiseSigma

# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 413

class SmoothGradConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#noise_sigma ⇒ ::Float

# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 413

class SmoothGradConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#noisy_sample_count ⇒ ::Integer

# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 413

class SmoothGradConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end