Interface ExplanationParametersOrBuilder (1.15.0)

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

.google.cloud.vertexai.v1.Examples examples = 7;

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

.google.cloud.vertexai.v1.Examples examples = 7;

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

.google.cloud.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

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

.google.cloud.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

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).

.google.protobuf.ListValue output_indices = 5;

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).

.google.protobuf.ListValue output_indices = 5;

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.

.google.cloud.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

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.

.google.cloud.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

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.

int32 top_k = 4;

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.

.google.cloud.vertexai.v1.XraiAttribution xrai_attribution = 3;

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.

.google.cloud.vertexai.v1.XraiAttribution xrai_attribution = 3;

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

.google.cloud.vertexai.v1.Examples examples = 7;

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

.google.cloud.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

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).

.google.protobuf.ListValue output_indices = 5;

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.

.google.cloud.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

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.

.google.cloud.vertexai.v1.XraiAttribution xrai_attribution = 3;