AWS Machine Learning Services

This article discusses AWS Machine Learning Services in the context of the AWS Certified Cloud Practitioner Exam. Services in this category come up regularly in questions and are usually high level.

AWS Rekognition

Add image and video analysis to your applications.

Identify objects, people, text, scenes, and activities in images and videos.

Processes videos stored in an Amazon S3 bucket.

Publish completion status to Amazon SNS Topic.

Amazon Transcribe

Add speech to text capabilities to applications.

Recorded speech can be converted to text before it can be used in applications.

Uses a deep learning process called automatic speech recognition (ASR) to convert speech to text quickly and accurately.

Amazon Translate

Neural machine translation service that delivers fast, high-quality, and affordable language translation.

Uses deep learning models to deliver more accurate and more natural sounding translation.

Localize content such as websites and applications for your diverse users.

Amazon Textract

Automatically extract printed text, handwriting, and data from any document.

Features:

• Optical character recognition (OCR).
• Identifies relationships, structure, and text.
• Uses AI to extract text and structured data.
• Recognizes handwriting as well as printed text.
• Can extract from documents such as PDFs, images, forms, and tables.
• Understands context. For example know what data to extract from a receipt or invoice.

Amazon SageMaker

Helps data scientists and developers to prepare, build, train, and deploy high-quality machine learning (ML) models.

ML development activities including:

• Data preparation.
• Feature engineering.
• Statistical bias detection.
• Auto-ML.
• Training and tuning.
• Hosting.
• Monitoring.
• Workflows.

Amazon Comprehend

Natural-language processing (NLP) service.

Uses machine learning to uncover information in unstructured data.

Can identify critical elements in data, including references to language, people, and places, and the text files can be categorized by relevant topics.

In real time, you can automatically and accurately detect customer sentiment in your content.

Amazon Lex

Conversational AI for Chatbots.

Build conversational interfaces into any application using voice and text.

Build bots to increase contact center productivity, automate simple tasks, and drive operational efficiencies across the enterprise.

Amazon Polly

Turns text into lifelike speech.

Create applications that talk and build entirely new categories of speech-enabled products.

Text-to-Speech (TTS) service uses advanced deep learning technologies to synthesize natural sounding human speech.

Amazon Forecast

Time-series forecasting service.

Uses ML and is built for business metrics analysis.

Amazon DevOps Guru

Cloud operations service for improving application operational performance and availability.

Detect behaviors that deviate from normal operating patterns.

Benefits:

• Automatically detect operational issues.
• Resolve issues with ML-powered insights.
• Elastically scale operational analytics.
• Uses ML to reduce alarm noise.