What is the purpose of postprocessing in a serving pipeline?

To transform input data for the model

To transform the model's raw output into a final prediction

In Vertex AI, how is A/B testing typically implemented?

By creating two separate endpoints

By deploying models to different regions

By configuring traffic split percentages on an endpoint

When would you use a custom container for model serving?

When you want to avoid building any container image

When you only need to serve a TensorFlow model

When you need to use a framework not supported by prebuilt containers

When you want to use a fully managed serving service

Which of the following is an example of preprocessing?

Applying a threshold to a probability to produce a class label

Converting the model output to JSON

Normalizing numeric features to have zero mean and unit variance

Google CloudProfessional Machine Learning Engineer

Domain 4Objective 1

Serving Models PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 5)

Part of the Serving and scaling models domain, which accounts for ~20% of the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam.

40questions here

8free pages

13concepts

~20%of the exam

Questions 21–25

21foundation · easy
What is the purpose of postprocessing in a serving pipeline?
Select an answer first
22foundation · easy
In Vertex AI, how is A/B testing typically implemented?
Select an answer first
23foundation · easy
When would you use a custom container for model serving?
Select an answer first
24foundation · easy
Which of the following is an example of preprocessing?
Select an answer first
25foundation · easy
Which of the following frameworks is supported by prebuilt containers for model serving?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to PROFESSIONAL-MACHINE-LEARNING-ENGINEER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Google Cloud. “PROFESSIONAL-MACHINE-LEARNING-ENGINEER” is a trademark of its owner, used for identification only.