Class Google::Cloud::AIPlatform::V1::SmoothGradConfig (v0.1.0)

Stay organized with collections Save and categorize content based on your preferences.

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

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#feature_noise_sigma

def feature_noise_sigma() -> ::Google::Cloud::AIPlatform::V1::FeatureNoiseSigma
Returns

#feature_noise_sigma=

def feature_noise_sigma=(value) -> ::Google::Cloud::AIPlatform::V1::FeatureNoiseSigma
Parameter
Returns

#noise_sigma

def noise_sigma() -> ::Float
Returns
  • (::Float) — This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization.

    For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.

    If the distribution is different per feature, set feature_noise_sigma instead for each feature.

#noise_sigma=

def noise_sigma=(value) -> ::Float
Parameter
  • value (::Float) — This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization.

    For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.

    If the distribution is different per feature, set feature_noise_sigma instead for each feature.

Returns
  • (::Float) — This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization.

    For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.

    If the distribution is different per feature, set feature_noise_sigma instead for each feature.

#noisy_sample_count

def noisy_sample_count() -> ::Integer
Returns
  • (::Integer) — The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.

#noisy_sample_count=

def noisy_sample_count=(value) -> ::Integer
Parameter
  • value (::Integer) — The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
Returns
  • (::Integer) — The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.