Class: Google::Cloud::AIPlatform::V1::ExplanationParameters

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

Overview

Parameters to configure explaining for Model's predictions.

Instance Attribute Summary collapse

Instance Attribute Details

#examples ⇒ ::Google::Cloud::AIPlatform::V1::Examples

Returns Example-based explanations that returns the nearest neighbors from the provided dataset.

Returns:



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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

#integrated_gradients_attribution ⇒ ::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution

Returns An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365.

Returns:



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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

#output_indices ⇒ ::Google::Protobuf::ListValue

Returns If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining.

If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.

Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

Returns:

  • (::Google::Protobuf::ListValue) —

    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining.

    If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.

    Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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

#sampled_shapley_attribution ⇒ ::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution

Returns An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

Returns:



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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

#top_k ⇒ ::Integer

Returns If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.

Returns:

  • (::Integer) —

    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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

#xrai_attribution ⇒ ::Google::Cloud::AIPlatform::V1::XraiAttribution

Returns An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825

XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

Returns:

  • (::Google::Cloud::AIPlatform::V1::XraiAttribution) —

    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825

    XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.



280
281
282
283
 
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 280

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