nerdexam
Microsoft

DP-100 · Question #414

You create an Azure Machine Learning workspace. You train an MLflow-formatted regression model by using tabular structured data. You must use a Responsible AI dashboard to access the model. You need…

The correct answer is B. Register the model with the workspace. Before generating a Responsible AI dashboard in Azure ML studio, the model must be registered in the workspace because the dashboard pipeline requires a registered model as input.

Train and deploy models

Question

You create an Azure Machine Learning workspace. You train an MLflow-formatted regression model by using tabular structured data. You must use a Responsible AI dashboard to access the model. You need to use the Azure Machine Learning studio UI to generate the Responsible AI dashboard. What should you do first?

Options

  • ADeploy the model to a managed online endpoint.
  • BRegister the model with the workspace.
  • CCreate the model explanations.
  • DConvert the model from the MLflow format to a custom format.

How the community answered

(28 responses)
  • A
    7% (2)
  • B
    89% (25)
  • D
    4% (1)

Why each option

Before generating a Responsible AI dashboard in Azure ML studio, the model must be registered in the workspace because the dashboard pipeline requires a registered model as input.

ADeploy the model to a managed online endpoint.

Deploying to a managed online endpoint is not required to generate a Responsible AI dashboard; the dashboard operates on the registered model, not a live endpoint.

BRegister the model with the workspace.Correct

The Responsible AI dashboard in Azure ML studio is generated by submitting a pipeline job that takes a registered model as a required input. Without registering the model first, the studio UI cannot reference it when configuring the dashboard components such as error analysis, model explanations, or fairness assessment. Registration is therefore the mandatory prerequisite step.

CCreate the model explanations.

Model explanations are one of the outputs generated by the Responsible AI dashboard pipeline, not a prerequisite for creating the dashboard.

DConvert the model from the MLflow format to a custom format.

MLflow-formatted models are natively supported by the Responsible AI dashboard and do not need to be converted to a custom format.

Concept tested: Responsible AI dashboard prerequisites in Azure ML

Source: https://learn.microsoft.com/en-us/azure/machine-learning/how-to-responsible-ai-dashboard

Topics

#Model Registration#Azure Machine Learning Studio#Responsible AI#MLflow

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full DP-100 Practice