Microsoft · AI-300
Assets and registries
AI-300 · Lesson 2 of 15 · 8:30
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: versioned data assets (uri_file, uri_folder, mltable), curated and custom environments, components with typed inputs and outputs, and registries that share assets across workspaces, subscriptions, and regions. Includes three original practice questions.
Preview the topics
- A training script installs its packages with pip at every run, and two runs a month apart got different versions. Every run must use exactly the same packages. What should the team do?
- The same data preparation code is copied into five pipelines, and every fix must now be made five times. What should the team create?
- A model is approved in a development workspace. The production workspace is in another subscription and another region, and must deploy the exact same version. What should the team use?