Exam AI-100 topic 4 question 22 discussion

B. No Writing a custom scoring script for the deployed AI models in Azure Machine Learning Studio does not directly address the goal of monitoring the compute performance of the models. A custom scoring script is typically used to define the logic for scoring or making predictions using the deployed models. It allows you to customize the way the models process input data and produce output. While you can include logging or performance tracking code within the custom scoring script, it does not provide comprehensive monitoring capabilities for compute performance. To monitor the compute performance of the deployed models, you would need to utilize other monitoring mechanisms, such as Azure Monitor. Azure Monitor provides comprehensive monitoring and diagnostics capabilities for Azure resources, including Azure Machine Learning. It allows you to track and analyze various performance metrics, such as CPU and memory usage, request latency, and resource utilization.

It should be a) Yes (https://docs.microsoft.com/en-us/azure/machine-learning/how-to-enable-data-collection). The scoring file should be edited.