12. Machine Learning Flashcards
What is the primary purpose of AWS Machine Learning services?
To enable developers and data scientists to build, train, and deploy machine learning models at scale.
True or False: AWS SageMaker is a fully managed service for machine learning.
True
Fill in the blank: AWS _____ allows for the creation of Jupyter notebooks for data exploration and model building.
SageMaker
What is the function of AWS Glue in data engineering?
To prepare and transform data for analytics and machine learning.
Which AWS service provides a data lake solution?
AWS Lake Formation
What is the role of Amazon S3 in machine learning workflows?
To store and retrieve large datasets used for training machine learning models.
List one use case for Amazon Rekognition.
Image and video analysis for facial recognition.
What does the term ‘hyperparameter tuning’ refer to in machine learning?
The process of optimizing the parameters that govern the training process of a model.
True or False: Amazon Comprehend provides natural language processing capabilities.
True
What is the purpose of the Amazon SageMaker Model Registry?
To store and manage different versions of machine learning models.
Which AWS service is used for deploying machine learning models as APIs?
Amazon SageMaker
What is the significance of using Amazon Redshift in data engineering?
It is a fully managed data warehouse service that allows for complex queries and analytics.
Multiple Choice: Which of the following is NOT a feature of AWS SageMaker?
A) Built-in algorithms
B) Real-time predictions
C) Manual model deployment
D) Jupyter notebook support
C) Manual model deployment
Fill in the blank: AWS _____ is used for building, training, and deploying machine learning models quickly.
SageMaker
What type of data can Amazon Polly convert into speech?
Text data
True or False: Amazon Forecast is used for time series forecasting.
True
What is the main advantage of using Amazon SageMaker Ground Truth?
To create labeled datasets efficiently using human labeling and automation.
Which service helps in detecting anomalies in time series data?
Amazon Lookout for Metrics
What is the purpose of Amazon Personalize?
To provide personalized recommendations to users.
What does the term ‘training data’ refer to?
Data used to train a machine learning model.
Multiple Choice: Which AWS service is specifically designed for visual search and image recognition?
A) Amazon Rekognition
B) Amazon Polly
C) Amazon Lex
D) AWS Glue
A) Amazon Rekognition
What is the role of AWS Lambda in a machine learning pipeline?
To run code in response to events without provisioning servers.
True or False: Amazon Lex is used for building conversational interfaces.
True
What is the purpose of feature engineering?
To select, modify, or create features that improve model performance.
Fill in the blank: The _____ is the model’s ability to generalize to new, unseen data.
generalization
What is a confusion matrix used for?
To evaluate the performance of a classification model.
What does the acronym ‘ETL’ stand for in data engineering?
Extract, Transform, Load
Multiple Choice: Which service provides managed Hadoop and Spark?
A) Amazon EMR
B) Amazon S3
C) Amazon RDS
D) AWS Glue
A) Amazon EMR
What is the significance of model evaluation?
To assess how well a model performs on unseen data.
True or False: AWS Data Pipeline is used for data orchestration.
True
What is the purpose of Amazon SageMaker Autopilot?
To automate the process of building machine learning models.
What type of model is used for predicting continuous outcomes?
Regression model
Fill in the blank: AWS _____ provides tools for natural language understanding.
Comprehend
What is the role of Amazon Kinesis in data engineering?
To collect, process, and analyze real-time streaming data.
Multiple Choice: Which AWS service is a serverless data warehouse?
A) Amazon Redshift
B) Amazon Athena
C) Amazon RDS
D) AWS Glue
B) Amazon Athena
What is a ROC curve used for?
To evaluate the trade-off between true positive rate and false positive rate.
True or False: Amazon SageMaker can only be used for supervised learning.
False
What is the main function of Amazon Translate?
To provide language translation services.
Fill in the blank: The _____ is the set of rules that a machine learning model follows to make predictions.
algorithm
What is the purpose of the Amazon SageMaker debugger?
To provide insights into the training process of machine learning models.
What type of learning is used when the model learns from labeled data?
Supervised learning
Multiple Choice: Which of the following is a key benefit of using AWS for machine learning?
A) Scalability
B) Manual resource management
C) High latency
D) Limited data access
A) Scalability
What is Amazon SageMaker’s role in model deployment?
It provides capabilities for deploying models to production environments.
True or False: AWS provides tools for both data preparation and model training.
True
What does ‘overfitting’ refer to in machine learning?
When a model learns the training data too well and performs poorly on unseen data.
Fill in the blank: The process of splitting data into training and testing sets is known as _____.
data splitting
What is the significance of data normalization?
To scale features to a similar range for better model performance.
Multiple Choice: Which AWS service is best for real-time analytics?
A) Amazon Redshift
B) AWS Glue
C) Amazon Kinesis
D) Amazon S3
C) Amazon Kinesis
What is the purpose of Amazon SageMaker Pipelines?
To create, automate, and manage machine learning workflows.
True or False: Amazon Lex can be used to create chatbots.
True
What is the role of feature selection in machine learning?
To identify the most relevant features for model training.
Fill in the blank: The _____ is a measure of how well a model performs on a given dataset.
accuracy
What is a decision tree in machine learning?
A model that makes decisions based on a series of questions.
What is the main function of Amazon SageMaker Neo?
To optimize machine learning models for deployment on various platforms.
Multiple Choice: Which of the following is a type of unsupervised learning?
A) Classification
B) Clustering
C) Regression
D) Time series forecasting
B) Clustering
What is the purpose of Amazon SageMaker Clarify?
To detect and mitigate bias in machine learning models.
True or False: AWS supports only deep learning frameworks for machine learning.
False
What is an ensemble model?
A model that combines predictions from multiple models to improve accuracy.
Fill in the blank: The process of adjusting model parameters based on training data is known as _____.
training
What does ‘data drift’ refer to?
Changes in data distribution over time that can affect model performance.
What is the primary function of AWS Data Wrangler?
To simplify the process of data preparation for machine learning.
Multiple Choice: Which of the following AWS services is used for data transformation?
A) Amazon SageMaker
B) AWS Glue
C) Amazon Comprehend
D) Amazon Rekognition
B) AWS Glue
True or False: Amazon Forecast is based on machine learning algorithms.
True
What is the significance of a validation set?
To tune model hyperparameters and avoid overfitting.
Fill in the blank: A _____ is a function that maps inputs to outputs in a machine learning model.
predictor
What is the purpose of Amazon Lookout for Equipment?
To monitor equipment for anomalies and predict failures.
Multiple Choice: Which AWS service is primarily used for building serverless applications?
A) AWS Lambda
B) Amazon S3
C) Amazon EC2
D) Amazon RDS
A) AWS Lambda
What is the main advantage of using a cloud-based machine learning platform?
Flexibility and scalability without the need for physical infrastructure.
