support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
CrowdStrike
Anthropic
All Vendors
  1. Home
  2. Exams
  3. Google
  4. PROFESSIONAL MACHINE LEARNING ENGINEER

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps
Professional Machine Learning Engineer Questions 176–180 (page: 37)

Updated On: 25-Oct-2026
Page 37 of 82
PDF with 402 Questions

You lead a data science team at a large international corporation. Most of the models your team trains are large-scale models using high-level TensorFlow APIs on AI Platform with GPUs. Your team usually takes a few weeks or months to iterate on a new version of a model. You were recently asked to review your team’s spending. How should you reduce your Google Cloud compute costs without impacting the model’s performance?

  1. Use AI Platform to run distributed training jobs with checkpoints.
  2. Use AI Platform to run distributed training jobs without checkpoints.
  3. Migrate to training with Kuberflow on Google Kubernetes Engine, and use preemptible VMs with checkpoints.
  4. Migrate to training with Kuberflow on Google Kubernetes Engine, and use preemptible VMs without checkpoints.

Answer(s): C



You are developing an ML model using a dataset with categorical input variables. You have randomly split half of the data into training and test sets. After applying one-hot encoding on the categorical variables in the training set, you discover that one categorical variable is missing from the test set.
What should you do?

  1. Use sparse representation in the test set.
  2. Randomly redistribute the data, with 70% for the training set and 30% for the test set
  3. Apply one-hot encoding on the categorical variables in the test data
  4. Collect more data representing all categories

Answer(s): C



You work for a bank with strict data governance requirements. You recently implemented a custom model to detect fraudulent transactions. You want your training code to download internal data by using an API endpoint hosted in your project’s network. You need the data to be accessed in the most secure way, while mitigating the risk of data exfiltration.
What should you do?

  1. Enable VPC Service Controls for peerings, and add Vertex AI to a service perimeter.
  2. Create a Cloud Run endpoint as a proxy to the data. Use Identity and Access Management (IAM) authentication to secure access to the endpoint from the training job.
  3. Configure VPC Peering with Vertex AI, and specify the network of the training job.
  4. Download the data to a Cloud Storage bucket before calling the training job.

Answer(s): A



You work for a retail company. You have a managed tabular dataset in Gemini Enterprise Agent Platform that contains regional sales data for each item across stores. The dataset includes several features, such as store name, items sold, and sale timestamp. You want to use the data to train a classification model that predicts whether an item will sell out in each store in the coming week. You need to split the data between the training, validation, and test sets.
What approach should you use to split the data?

  1. Manually split the data, using the store name feature to assign stores to each set.
  2. Use the default data split settings.
  3. Chronologically split the data and specify the sales timestamp feature as the time variable.
  4. Randomly split the data, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set.

Answer(s): C



You work for a large manufacturing company that uses thousands of sensors across its production lines. These sensors generate petabytes of operational data monthly. You have deployed an early warning detection model on an Agent Platform endpoint that predicts potential equipment failures. You need to monitor for data end concept drift for this model in near reel-time. You must ensure that the solution is cost-effective given the massive volume of incoming prediction requests.
What should you do?

  1. Configure the endpoint to log all traffic in BigQuery. Schedule a daily notebook execution in Agent Platform Workbench to run a custom PyTorch job that analyzes drift in the previous day's data.
  2. Configure a Model Monitoring job for the endpoint. Set the sample_rate to a fraction of the traffic and one hour monitoring_frequency.
  3. Create an additional Agent Platform endpoint. Deploy the model to the new endpoint. Enable a Model Monitoring job with full data logging on the endpoint that serves requests related to critical machinery.
  4. Use Cloud Run functions to trigger the Model Monitoring job only during peak production hours identified in your historical BigQuery data.

Answer(s): B

Explanation:

Model Monitoring is designed to detect feature distribution changes and model-related drift in production. Sampling only a fraction of prediction traffic substantially reduces logging and monitoring costs for very high-volume endpoints, while a one-hour monitoring frequency provides near-real-time detection. Google Cloud specifically supports configurable prediction sampling rates for cost efficiency and monitoring frequencies as low as one hour.


Reference:

https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/model-monitoring/overview https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/model-monitoring/using-mod el-monitoring



  PDF
Viewing page 37 of 82
Viewing questions 181 - 185 out of 402 questions


Post your Comments and Discuss Google PROFESSIONAL MACHINE LEARNING ENGINEER exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!