Class GoogleCloudAiplatformV1ExplanationParameters

Parameters to configure explaining for Model's predictions.

Inheritance
object
GoogleCloudAiplatformV1ExplanationParameters
Implements
Inherited Members
Namespace: Google.Apis.Aiplatform.v1.Data
Assembly: Google.Apis.Aiplatform.v1.dll
Syntax
public class GoogleCloudAiplatformV1ExplanationParameters : IDirectResponseSchema

Properties

ETag

The ETag of the item.

Declaration
public virtual string ETag { get; set; }
Property Value
Type Description
string

Examples

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

Declaration
[JsonProperty("examples")]
public virtual GoogleCloudAiplatformV1Examples Examples { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1Examples

IntegratedGradientsAttribution

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

Declaration
[JsonProperty("integratedGradientsAttribution")]
public virtual GoogleCloudAiplatformV1IntegratedGradientsAttribution IntegratedGradientsAttribution { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1IntegratedGradientsAttribution

OutputIndices

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).

Declaration
[JsonProperty("outputIndices")]
public virtual IList<object> OutputIndices { get; set; }
Property Value
Type Description
IList<object>

SampledShapleyAttribution

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.

Declaration
[JsonProperty("sampledShapleyAttribution")]
public virtual GoogleCloudAiplatformV1SampledShapleyAttribution SampledShapleyAttribution { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1SampledShapleyAttribution

TopK

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.

Declaration
[JsonProperty("topK")]
public virtual int? TopK { get; set; }
Property Value
Type Description
int?

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.

Declaration
[JsonProperty("xraiAttribution")]
public virtual GoogleCloudAiplatformV1XraiAttribution XraiAttribution { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1XraiAttribution

Implements