Building models given the task considering cost, complexity, latency, and scalability.
7 practice questions under this official exam objective (PMLE), each with the answer key, an option-by-option explanation and instant feedback.
Questions under this objective
7 total · page 1 of 1Minimizing Overhead for BigQuery Batch Predictions with TensorFlow Models
To minimize computational overhead for batch predictions on BigQuery data, export your TensorFlow model to BigQuery ML. This allows direct SQL-based i
Using Pre-built Kubeflow Components for BigQuery Integration
To easily integrate BigQuery results into a Kubeflow pipeline, use the pre-built BigQuery Query Component loaded by URL rather than writing custom scr
Preventing Data Leakage in Time-Series Models via Temporal Splitting
This question addresses data leakage in time-series forecasting where random splitting inflates test accuracy. The correct approach is to use a tempor
Serving Predictions via Firebase Cloud Messaging for Scale
Learn how to serve ML predictions to millions of users using Firebase Cloud Messaging (FCM) instead of Pub/Sub to avoid quota limits and ensure person
Choosing Batch vs Online ML Inference for Daily Aggregated Data
Learn how to select the right ML serving pattern for aggregated data. The correct solution uses AI Platform batch prediction for daily jobs with minim
Customer Segmentation with BigQuery ML K-Means
Learn how to efficiently segment customers with unknown group counts using BigQuery ML's automatic k-means clustering capabilities.
Using Custom Containers for Distributed Training on Google Cloud
Learn how to train custom neural networks with unsupported dependencies and large-scale data using custom containers and distributed training on Googl