Google Cloud Professional Machine Learning Engineer — Question 20

You have deployed multiple versions of an image classification model on AI Platform. You want to monitor the performance of the model versions over time. How should you perform this comparison?

Answer options

• A. Compare the loss performance for each model on a held-out dataset.
• B. Compare the loss performance for each model on the validation data.
• C. Compare the receiver operating characteristic (ROC) curve for each model using the What-If Tool.
• D. Compare the mean average precision across the models using the Continuous Evaluation feature.

Correct answer: D

Explanation

The correct answer is D, as the Continuous Evaluation feature is specifically designed to compare model performance metrics like mean average precision over time. Options A and B focus on loss performance metrics, which do not provide a comprehensive view of model effectiveness, while option C, although useful, does not focus on the average precision metric that is crucial for model comparison in this context.