AWS Machine Learning - Quick Notes

The following is the summary of the various features/capabilities of Rekognition:

Is a service that is used for Image and Video analysis without any machine learning expertise
Can identify labels (objects, concepts, people, scenes, and activities) and text
Can detect inappropriate content
Provides highly accurate facial analysis, face comparison, and face search capabilities that can be used for a wide variety of use-cases, including user verification, cataloging, people counting, public safety, etc
Provides a simple, easy-to-use API that can quickly analyze any image or video file that is stored in S3

The following is the summary of the various features/capabilities of Transcribe:

Is an Automatic Speech Recognition service that uses machine learning models to convert audio to text
Can transcribe media in real-time (streaming) or can transcribe media files located in S3 (batching)
Support for automatic Personally Identifiable Information (PII) content redaction
Support for automatic language identification for multi-language audio

The following is the summary of the various features/capabilities of Polly:

Is a Text-to-Speech service that converts text into lifelike speech
Useful for developing applications that increase engagement and accessibility
Supports multiple languages and includes a variety of lifelike voices, so that one can build speech-enabled applications that work in multiple locations
Support for Pronunciation Lexicons that enables one to customize the pronunciation of words
Use lexicons for fully expanding abbreviations (ex: Amazon Web Services for AWS)
Allows the use of Speech Synthesis Markup Language (SSML) for additional control, such as, emphasizing specific words or phrases, using phonetic pronunciation, whispering, using the Newscaster speaking style, etc

The following is the summary of the various features/capabilities of Translate:

Is a Text Translation service that translates content from a source language to a target language
Helps in localization of content for websites
In a batch job, one can translate files from one or more source languages to one or more target languages

The following is the summary of the various features/capabilities of Comprehend:

Uses Natural Language Processing (NLP) to extract insights about the content of documents
Develops insights by recognizing entities, key phrases, language, sentiments, and other common elements in a document
Support for automatic organization of a collection of documents by topic

The following is the summary of the various features/capabilities of SageMaker:

Is a fully managed Machine Learning service that enables data scientists and developers to quickly build and train machine learning models, and then deploy them into a production-ready hosted environment
SageMaker Autopilot is a feature-set that automates key tasks of an automatic machine learning (AutoML) process. It explores the data, selects the algorithms relevant to the problem type, and prepares the data to facilitate model training and tuning
SageMaker JumpStart provides pretrained, open-source models for a wide range of problem types to help one get started with machine learning. One can incrementally train and tune these models before deployment

The following is the summary of the various features/capabilities of Forecast:

Is a fully managed service that uses statistical and machine learning algorithms to deliver highly accurate future time-series forecasts based on historical data
Time-series forecasting is useful in multiple fields, including retail, finance, logistics, and healthcare
Can also be used to predict domain-specific metrics, such as, inventory, workforce, web traffic, server capacity, and finances

The following is the summary of the various features/capabilities of Kendra:

Is an intelligent Document Search service that uses Natural Language Processing and advanced Machine Learning algorithms to return specific answers to search questions from data
Uses its semantic and contextual understanding capabilities to decide whether a document is relevant to a search query
Support for incremental learning from user interactions and feedback to promote preferred results

The following is the summary of the various features/capabilities of Personalize:

Is a fully managed Personalized Recommendation service that uses data to generate item recommendations for users
Allows one to build applications for real-time personalized recommendations
Used by amazon.com
Generates recommendations primarily based on item interaction data, which comes from users interacting with items in a product catalog

The following is the summary of the various features/capabilities of Textract: