Azure Machine Learning Quiz

Name the functions that the scoring script for a real-time service must implement

• init()

• run()

• main()

• script()

You want to try every possible combination of a set of specified discrete values in a hyper-parameter tuning experiment. Which kind of sampling should you use?

• Random Sampling

• Bayesian Sampling

• Gaussian Sampling

• Grid Sampling

Jolly uses Azure ML SDK v2 to write code for an experiment. How can she record metrics from each run of the experiment and be able to retrieve them easily from each run?

• Use the log methods of the ScriptRunConfig class to record the named metrics

• Use the log methods of the Run class to record named metrics

• Use mlflow.log_metric() function

• Use mlflow.log_param() function

You want to use automated machine learning to find the model with the best AUC_weighted metric. Name the parameter of the AutoMLConfig object that you must set from the following options.

• metric = 'AUC_weighted'

• primary_metric = 'AUC_weighted'

• primary_metric ='ROC_AUC'

• primary_metric = 'AUC'

How do you determine the influence of each feature on the predicted label while training an Azure ML model ?

• Use Explain Model option

• Use Feature Importance tab

• Use Notebooks and run python script to get feature importance

• Use mlflow

Which Azure service is commonly used for building and deploying machine learning models?

• Azure Data Lake Storage

• Azure Synapse Analytics

• Azure Machine Learning

• Azure Databricks

Which Azure service provides a scalable and collaborative environment for big data analytics and machine learning?

• Azure SQL Database

• Azure Cosmos DB

• Azure Databricks

• 
  Azure Blob Storage

In Azure Machine Learning, what is a Workspace?

• A folder to store code and data

• A cloud-based environment to manage machine learning assets

• A visualization tool for machine learning models

• A database for storing trained models

Which of the following is NOT a feature of Azure Machine Learning service?

• Automated machine learning

• 
  Hyperparameter tuning

• Real-time streaming analytics

• Model deployment

What is the purpose of an Experiment in Azure Machine Learning?

• To deploy machine learning models

• To create visualizations of data

• To track and log model training runs

• To manage data pipelines