Microsoft · AI-300
Monitoring and retraining
AI-300 · Lesson 8 of 15 · 47:52
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AI-300 exam (Microsoft Certified: Machine Learning Operations Engineer Associate). In this lesson: model monitoring signals (data drift, prediction drift, data quality, model performance), production data collection, schedules, reference data, and alerts, and Event Grid events that start retraining. Includes three original practice questions.
Preview the topics
- A model on a managed online endpoint must be monitored for data drift, but no production data reaches the workspace. What should the team turn on first?
- A team sets up a prediction drift signal for a churn model. Which reference data does Microsoft recommend for this signal?
- A model must be retrained automatically, but only when its monitor detects drift. Which design fits?