Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
You are part of a team managing a machine learning model deployed to a Vertex AI endpoint. To automate the model training process, you have created a Vertex AI pipeline, which is triggered by a Cloud Function. Your goal is to ensure that the model remains up-to-date with the latest data while keeping retraining costs as low as possible. Given these requirements, how should you configure the retraining process?
Explanation:
The correct answer is D: Enable model monitoring on the Vertex AI endpoint. Configure Pub/Sub to call the Cloud Function when feature drift is detected. This approach ensures that the model stays relevant to evolving data patterns, prioritizing model accuracy by retraining only when necessary. This helps in minimizing retraining costs by avoiding unnecessary retraining sessions. Options A, B, and C either do not directly address feature drift or may lead to unnecessary retraining.