ml  v1
Properties | List of all members
Google.Apis.CloudMachineLearningEngine.v1.Data.GoogleCloudMlV1IntegratedGradientsAttribution Class Reference

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...

Inheritance diagram for Google.Apis.CloudMachineLearningEngine.v1.Data.GoogleCloudMlV1IntegratedGradientsAttribution:
Google::Apis::Requests::IDirectResponseSchema

Properties

virtual System.Nullable< int > NumIntegralSteps [get, set]
 Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. More...
 
virtual string ETag [get, set]
 The ETag of the item. More...
 
- Properties inherited from Google::Apis::Requests::IDirectResponseSchema
string ETag
 

Detailed Description

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

Property Documentation

◆ ETag

virtual string Google.Apis.CloudMachineLearningEngine.v1.Data.GoogleCloudMlV1IntegratedGradientsAttribution.ETag
getset

The ETag of the item.

◆ NumIntegralSteps

virtual System.Nullable<int> Google.Apis.CloudMachineLearningEngine.v1.Data.GoogleCloudMlV1IntegratedGradientsAttribution.NumIntegralSteps
getset

Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.


The documentation for this class was generated from the following file: