GoogleCloudMlV1__IntegratedGradientsAttributionArgs

data class GoogleCloudMlV1__IntegratedGradientsAttributionArgs(val numIntegralSteps: Output<Int>? = null) : ConvertibleToJava<GoogleCloudMlV1__IntegratedGradientsAttributionArgs>

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

Constructors

Functions

Link copied to clipboard
open override fun toJava(): GoogleCloudMlV1__IntegratedGradientsAttributionArgs

Properties

Link copied to clipboard
val numIntegralSteps: Output<Int>? = null

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.