Message holding configuration options for explaining model predictions. There are two feature attribution methods supported for TensorFlow models: integrated gradients and sampled Shapley. Learn more about feature attributions. More...
Properties | |
| virtual GoogleCloudMlV1IntegratedGradientsAttribution | IntegratedGradientsAttribution [get, set] |
| Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: http://proceedings.mlr.press/v70/sundararajan17a.html More... | |
| virtual GoogleCloudMlV1SampledShapleyAttribution | SampledShapleyAttribution [get, set] |
| 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. More... | |
| virtual GoogleCloudMlV1XraiAttribution | XraiAttribution [get, set] |
| Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs. More... | |
| virtual string | ETag [get, set] |
| The ETag of the item. More... | |
 Properties inherited from Google::Apis::Requests::IDirectResponseSchema | |
| string | ETag |
Detailed Description
Message holding configuration options for explaining model predictions. There are two feature attribution methods supported for TensorFlow models: integrated gradients and sampled Shapley. Learn more about feature attributions.
Property Documentation
◆ ETag
|
getset |
The ETag of the item.
◆ IntegratedGradientsAttribution
|
getset |
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: http://proceedings.mlr.press/v70/sundararajan17a.html
◆ SampledShapleyAttribution
|
getset |
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.
◆ XraiAttribution
|
getset |
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
The documentation for this class was generated from the following file:
- Google.Apis.CloudMachineLearningEngine.v1.cs
