What must a custom container include to serve a model?

The model artifact and the serving code

What is the purpose of A/B testing in model serving?

To compare the performance of two model versions by splitting traffic

To replace a model with a completely new one

To train two models simultaneously

What is the primary purpose of Model Garden in Vertex AI?

To discover and deploy pre-trained foundation models

To store trained model artifacts

What is a prebuilt container in the context of model serving?

A container that is stored in a private registry

A container image that you must build from scratch for each model

A container that only works with TensorFlow models

A container image provided by Google that includes a serving framework and dependencies

A financial services company needs to run credit risk predictions for a portfolio of 500,000 loan applications. The results are used for regulatory reporting and are not needed in real time. The model is a TensorFlow model. What is the most efficient way to generate these predictions?

Use Vertex AI Batch Prediction with the prebuilt TensorFlow container.

Deploy the model to Vertex AI Prediction and send each application as a separate online request.

Use Cloud Run to process the batch by invoking the model in a loop.

Export the model to BigQuery ML and run a query.

Google CloudProfessional Machine Learning Engineer

Domain 4Objective 1

Serving Models PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 4)

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 16–20

16foundation · easy
What must a custom container include to serve a model?
Select an answer first
17foundation · easy
What is the purpose of A/B testing in model serving?
Select an answer first
18foundation · easy
What is the primary purpose of Model Garden in Vertex AI?
Select an answer first
19foundation · easy
What is a prebuilt container in the context of model serving?
Select an answer first
20application · medium
A financial services company needs to run credit risk predictions for a portfolio of 500,000 loan applications. The results are used for regulatory reporting and are not needed in real time. The model is a TensorFlow model. What is the most efficient way to generate these predictions?
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.