AI-900 Question 139
Select 4You are tasked with deploying a machine learning model using Azure Machine Learning. The model needs to be available for real-time predictions, and you also want to monitor its performance after deployment. Which of the following Azure Machine Learning capabilities can help you achieve this?
- A
Azure Machine Learning endpoints
- B
Azure Blob Storage for model storage
- C
Azure Machine Learning model registry
- D
Azure Monitor integration for telemetry and logging
- E
Azure Kubernetes Service (AKS) for scalable deployment
Show answer and explanation
Correct answers: A, C, D, E
Explanation
To deploy and monitor a machine learning model in Azure Machine Learning, you can use Azure Machine Learning endpoints for real-time predictions, the model registry for managing model versions, Azure Monitor integration for performance monitoring, and Azure Kubernetes Service (AKS) for scalable deployment. Azure Blob Storage is not directly involved in deployment or monitoring but can be used for storing model files.
- A. Correct.
Azure Machine Learning endpoints allow you to deploy models and make them available for real-time predictions. This is essential for your scenario.
- B. Incorrect.
Azure Blob Storage is primarily used for storing data and artifacts. While it can store models, it does not directly support deployment or monitoring capabilities.
- C. Correct.
Azure Machine Learning model registry is used to manage and version models. It helps in tracking the model lifecycle, which is crucial for deployment and monitoring setups.
- D. Correct.
Azure Monitor integration provides telemetry and logging capabilities, which are necessary for monitoring the performance of deployed models.
- E. Correct.
Azure Kubernetes Service (AKS) is a scalable compute environment that supports deploying machine learning models for real-time predictions. It is a suitable choice for scalable deployments.