All Modules Google Cloud Platform Big Data and Machine Learning Fundamentals Quiz Answers
Table of Contents
Google Cloud Platform Big Data and Machine Learning Fundamentals Module 02 Quiz Answers
Q1: Which Google hardware innovation tailors architecture to meet the computation needs on a domain, such as the matrix multiplication in machine learning?
Answer: TPUs (Tensor Processing Units)
TPUs are custom-built hardware designed by Google to accelerate machine learning tasks, especially for operations like matrix multiplication in deep learning.
Q2: Which data storage class is best for storing data that needs to be accessed less than once a year, such as online backups and disaster recovery?
Answer: Archive storage
Archive storage is the most cost-effective class for data that is accessed infrequently, less than once a year, such as for backups and disaster recovery.
Q3: Compute Engine, Google Kubernetes Engine, App Engine, and Cloud Functions represent which type of services?
Answer: Compute
These services provide various compute capabilities, from VMs to serverless computing, to support a wide range of application needs.
Q4: Cloud Storage, Bigtable, Cloud SQL, Spanner, and Firestore represent which type of services?
Answer: Database and storage
These services provide scalable storage and database solutions for structured and unstructured data.
Q5: Pub/Sub, Dataflow, Dataproc, and Cloud Data Fusion align to which stage of the data-to-AI workflow?
Answer: Ingestion and process
These services help ingest, process, and transform data in preparation for storage or analysis.
Q6: AutoML, Vertex AI Workbench, and TensorFlow align to which stage of the data-to-AI workflow?
Answer: Machine learning
These tools and platforms are designed for developing, training, and deploying machine learning models.
Google Cloud Platform Big Data and Machine Learning Fundamentals Module 03 Quiz Answers
Q1: Select the correct streaming data workflow.
Answer: Ingest the streaming data, process the data, and visualize the results.
In a streaming data workflow, data is first ingested from the source, processed to extract insights or transform the data, and finally visualized for analysis or monitoring.
Q2: Which Google Cloud product is a distributed messaging service that is designed to ingest messages from multiple device streams such as gaming events, IoT devices, and application streams?
Answer: Pub/Sub
Pub/Sub is a distributed messaging service designed for real-time event ingestion and delivery from multiple sources, such as IoT devices or applications.
Q3: Which Google Cloud product acts as an execution engine to process and implement data processing pipelines?
Answer: Dataflow
Dataflow is a fully managed service for stream and batch processing that uses Apache Beam as its programming model for building and executing data pipelines.
Q4: When you build scalable and reliable pipelines, data often needs to be processed in near-real time, as soon as it reaches the system. Which type of challenge might this present to data engineers?
Answer: Velocity
Velocity refers to the speed at which data is generated and processed. Near-real-time data processing requires handling high-velocity data streams efficiently.
Q5: Due to several data types and sources, big data often has many data dimensions. This can introduce data inconsistencies and uncertainties. Which type of challenge might this present to data engineers?
Answer: Variety
Variety refers to the diversity of data types and sources, which can lead to inconsistencies and complexities in data integration and processing.
Google Cloud Platform Big Data and Machine Learning Fundamentals Module 04 Quiz Answers
Q1: BigQuery is a fully managed data warehouse. What does “fully managed” refer to?
Answer: BigQuery manages the underlying structure for you.
Fully managed means that BigQuery handles the infrastructure, including scaling, maintenance, and performance optimization, without user intervention.
Q2: Which two services does BigQuery provide?
Answer: Storage and compute
BigQuery offers both storage for data and compute resources to process and analyze that data.
Q3: Which pattern describes source data that is moved into a BigQuery table in a single operation?
Answer: Batch load
Batch loading refers to moving large amounts of data into BigQuery in one operation.
Q4: Which BigQuery feature leverages geography data types and standard SQL geography functions to analyze a data set?
Answer: Geospatial analysis
Geospatial analysis uses geography data types and SQL functions to analyze spatial and geographic data.
Q5: Data has been loaded into BigQuery, and the features have been selected and preprocessed. What should happen next when you use BigQuery ML to develop a machine learning model?
Answer: Create the ML model inside BigQuery.
The next step is to create the machine learning model directly within BigQuery using BigQuery ML.
Q6: In a supervised machine learning model, what provides historical data that can be used to predict future data?
Answer: Labels
Labels are the output values in supervised learning that the model learns to predict.
Q7: You want to use machine learning to group random photos into similar groups. Which should you use?
Answer: Unsupervised learning, cluster analysis
Cluster analysis is an unsupervised learning method used to group similar data points.
Q8: You want to use machine learning to identify whether an email is spam. Which should you use?
Answer: Supervised learning, logistic regression
Logistic regression is a supervised learning method commonly used for binary classification tasks, like identifying spam emails.
Google Cloud Platform Big Data and Machine Learning Fundamentals Module 05 Quiz Answers
Q1: A video production company wants to use machine learning to categorize event footage but does not want to train its own ML model. Which option can help you get started?
Answer: Pre-built APIs
Pre-built APIs, such as Google Cloud’s Vision API, provide ready-to-use machine learning models for common tasks like image and video categorization without requiring training.
Q2: Your company has a lot of data, and you want to train your own machine model to see what insights ML can provide. Due to resource constraints, you require a codeless solution. Which option is best?
Answer: AutoML
AutoML allows you to train custom machine learning models without writing code, making it ideal for teams with limited development resources.
Q3: You work for a global hotel chain that has recently loaded some guest data into BigQuery. You have experience writing SQL and want to leverage machine learning to help predict guest trends for the next few months. Which option is best?
Answer: BigQuery ML
BigQuery ML allows users to create and execute machine learning models using SQL, leveraging their existing SQL skills for predictive analytics.
Q4: Which Google Cloud product lets users create, deploy, and manage machine learning models in one unified platform?
Answer: Vertex AI
Vertex AI provides a comprehensive platform for managing the entire machine learning lifecycle, from model development to deployment and monitoring.
Q5: Which code-based solution offered with Vertex AI gives data scientists full control over the development environment and process?
Answer: Custom training
Custom training in Vertex AI enables data scientists to have complete control over the development and training of machine learning models, allowing for fine-tuning and custom configurations.
Google Cloud Platform Big Data and Machine Learning Fundamentals Module 06 Quiz Answers
Q1: Select the correct machine learning workflow.
Answer: Data preparation, model training, model serving
This sequence represents the typical steps in a machine learning project: preparing data, training the model, and then deploying it for use.
Q2: Which stage of the machine learning workflow includes feature engineering?
Answer: Data preparation
Feature engineering, where raw data is transformed into features that improve model performance, is part of data preparation.
Q3: Which stage of the machine learning workflow includes model evaluation?
Answer: Model training
Model evaluation happens during the model training phase to assess how well the model performs and to refine it as needed.
Q4: A hospital uses Google’s machine learning technology to help pre-diagnose cancer by feeding historical patient medical data to the model. The goal is to identify as many potential cases as possible. Which metric should the model focus on?
Answer: Recall
Recall focuses on correctly identifying all relevant cases (true positives), which is crucial in scenarios like cancer diagnosis, where missing a positive case could have severe consequences.
Q5: A farm uses Google’s machine learning technology to detect defective apples in their crop, such as those that are irregular in size or have scratches. The goal is to identify only the apples that are actually bad so that no good apples are wasted. Which metric should the model focus on?
Answer: Precision
Precision emphasizes minimizing false positives, ensuring only defective apples are removed, reducing waste of good apples.
Q6: Which Vertex AI tool automates, monitors, and governs machine learning systems by orchestrating the workflow in a serverless manner?
Answer: Vertex AI Pipelines
Vertex AI Pipelines automates and manages machine learning workflows, enabling users to build and deploy pipelines efficiently.
More Related Quiz Answers >>
The 3D Printing Revolution Coursera Quiz Answers
3D Printing Applications Coursera Quiz Answers
3D Printing Software Coursera Quiz Answers
3D Printing Hardware Coursera Quiz Answers
