pulumi-google-native-kotlin/com.pulumi.googlenative.ml.v1.kotlin.outputs/GoogleCloudMlV1__ExplanationConfigResponse

GoogleCloudMlV1__ExplanationConfigResponse

data class GoogleCloudMlV1__ExplanationConfigResponse(val integratedGradientsAttribution: GoogleCloudMlV1__IntegratedGradientsAttributionResponse, val sampledShapleyAttribution: GoogleCloudMlV1__SampledShapleyAttributionResponse, val xraiAttribution: GoogleCloudMlV1__XraiAttributionResponse)

Message holding configuration options for explaining model predictions. There are three feature attribution methods supported for TensorFlow models: integrated gradients, sampled Shapley, and XRAI. /ai-platform/prediction/docs/ai-explanations/overview

Constructors

fun GoogleCloudMlV1__ExplanationConfigResponse(integratedGradientsAttribution: GoogleCloudMlV1__IntegratedGradientsAttributionResponse, sampledShapleyAttribution: GoogleCloudMlV1__SampledShapleyAttributionResponse, xraiAttribution: GoogleCloudMlV1__XraiAttributionResponse)

Types

Companion

object Companion

Properties

integratedGradientsAttribution

val integratedGradientsAttribution: GoogleCloudMlV1__IntegratedGradientsAttributionResponse

Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

sampledShapleyAttribution

val sampledShapleyAttribution: GoogleCloudMlV1__SampledShapleyAttributionResponse

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

val xraiAttribution: GoogleCloudMlV1__XraiAttributionResponse

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.