A healthcare company wants to build a model that classifies medical notes into categories. They have a small labeled dataset (500 examples) and need the model to understand medical terminology. They also have strict data residency requirements, so the data must stay in a specific region. Which approach should they take?

Train a custom LSTM model from scratch on the small dataset.

Use Vertex AI AutoML for text classification with the small dataset.

Fine-tune a foundational model from Model Garden in the required region.

Use a pre-trained model from Model Garden without fine-tuning.

What is the primary purpose of fine-tuning a foundational model?

To convert the model to a different framework

To adapt a pre-trained model to a specific domain or task using a smaller dataset

To compress the model to reduce its size

To train a model from scratch on a new dataset

A team is running a hyperparameter tuning job on Vertex AI. They notice that the tuning job is taking too long and consuming too many resources. They want to speed it up without sacrificing too much model quality. What should they do?

Disable early stopping to let all trials run fully.

Increase the number of trials to explore more.

Use a larger machine type for each trial.

Reduce the number of trials and use early stopping.

A marketing team wants to build a churn prediction model using a tabular dataset with 50 features and 1 million rows. They have limited ML expertise and want to minimize manual effort. They also need to understand which features are most important for the model. Which approach should they take?

Use Vertex AI Feature Store to train a model directly on the feature store data.

Use Vertex AI custom training with a pre-built PyTorch container and manual hyperparameter tuning.

Use Vertex AI AutoML for tabular data to train a model and inspect feature importance.

Use Vertex AI Tabular Workflows to run a custom XGBoost training script.

A training job on Vertex AI is failing with an error that the training data contains NaN values. The team has verified that the source data is clean. What is the most likely cause?

The model architecture is incorrect.

The hyperparameters are set too high.

The training job is running out of memory.

The data preprocessing code is introducing NaN values.

Google CloudProfessional Machine Learning Engineer

Domain 3Objective 2

Training Models PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 3)

Part of the Scaling prototypes into ML models domain, which accounts for ~21% of the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam.

31questions here

7free pages

8concepts

~21%of the exam

Questions 11–15

11application · medium
A healthcare company wants to build a model that classifies medical notes into categories. They have a small labeled dataset (500 examples) and need the model to understand medical terminology. They also have strict data residency requirements, so the data must stay in a specific region. Which approach should they take?
Select an answer first
12foundation · easy
What is the primary purpose of fine-tuning a foundational model?
Select an answer first
13expert · medium
A team is running a hyperparameter tuning job on Vertex AI. They notice that the tuning job is taking too long and consuming too many resources. They want to speed it up without sacrificing too much model quality. What should they do?
Select an answer first
14application · medium
A marketing team wants to build a churn prediction model using a tabular dataset with 50 features and 1 million rows. They have limited ML expertise and want to minimize manual effort. They also need to understand which features are most important for the model. Which approach should they take?
Select an answer first
15expert · medium
A training job on Vertex AI is failing with an error that the training data contains NaN values. The team has verified that the source data is clean. What is the most likely cause?
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.