Machine Learning Eng Assoc 3 AWS AI Services Flashcards
Artificial Intelligence
Computer systems performing human-like intelligent tasks
Machine Learning
A subset of AI that uses algorithms to learn from data and make predictions
Deep Learning
A subset of machine learning based on artificial neural networks
Natural Language Processing
AI technology that enables machines to understand; interpret; and generate human language
Computer Vision
AI technology that enables machines to interpret and understand visual information from the world
Amazon Comprehend
Fully managed natural language processing service for text analysis
Amazon Translate
Neural machine translation service for language translation
Amazon Transcribe
Automatic speech recognition service for converting speech to text
Amazon Polly
Text-to-speech service that uses deep learning to synthesize natural-sounding speech
Amazon Rekognition
Computer vision service for image and video analysis
Amazon Forecast
Fully managed service that uses machine learning for time-series forecasting
Amazon Lex
Service for building conversational interfaces using voice and text
Amazon Personalize
Machine learning service for creating personalized product recommendations
Amazon Textract
Service that automatically extracts text; handwriting; and data from scanned documents
Amazon Kendra
Intelligent search service powered by machine learning
Amazon Augmented AI (A2I)
Service that makes it easy to build workflows for human review of machine learning predictions
Amazon SageMaker
Fully managed machine learning platform for building; training; and deploying models
Amazon EC2
Elastic Compute Cloud service for scalable computing capacity
AWS Trainium
Custom machine learning chips designed for training deep learning models
AWS Inferentia
Custom machine learning chips designed for high-performance inference
Amazon Bedrock
Fully managed service for building generative AI applications with foundation models
Amazon Q Business
Generative AI-powered assistant for business use cases
Amazon Q Developer
AI-powered coding assistant for software development
Amazon Q Apps
Tool for creating Gen AI-powered apps without coding using natural language
Feature Engineering
Process of selecting; transforming; and creating features to improve model performance
Model Training
Process of teaching a machine learning model to make predictions based on data
Hyperparameter Tuning
Process of finding the optimal set of hyperparameters for a machine learning model
Model Evaluation
Process of assessing the performance and effectiveness of a trained model
Model Deployment
Process of making a trained machine learning model available for use in a production environment
Model Monitoring
Continuous observation and analysis of a deployed model’s performance and behavior
Data Drift
Changes in the statistical properties of the input data over time
Concept Drift
Changes in the relationship between input and output variables in the underlying problem
A/B Testing
Experimental approach to compare two versions of a model or system
CI/CD
Continuous Integration and Continuous Delivery; practices for automating software delivery processes
IAM
Identity and Access Management; AWS service for managing access to AWS resources
Security Group
Virtual firewall for controlling inbound and outbound traffic to AWS resources
Amazon S3
Simple Storage Service; object storage service in AWS
Amazon EFS
Elastic File System; fully managed file storage service for use with AWS cloud services and on-premises resources
Amazon Kinesis
Platform for streaming data on AWS
AWS Glue
Fully managed extract; transform; and load (ETL) service
AWS Lambda
Serverless compute service that runs code in response to events
Amazon DynamoDB
Fully managed NoSQL database service
MLOps
Application of DevOps principles to machine learning workflows
AWS CodePipeline
Fully managed continuous delivery service for automating ML workflows
Spot Instances
Cost-effective option for running fault-tolerant ML training jobs
Auto Scaling
Automatically adjusting compute resources based on ML workload demands
AWS Cost Explorer
Tool for visualizing and managing AWS costs; including ML-related expenses
Right-sizing
Matching instance types and sizes to ML workload requirements for cost optimization
Data Encryption
Process of encoding ML-related data to protect sensitive information
GDPR
General Data Protection Regulation; EU law on data protection and privacy
HIPAA
Health Insurance Portability and Accountability Act; US law for data privacy in healthcare
Version Control
System for tracking and managing changes to ML code; models; and datasets