Hands-On Artificial Intelligence on Amazon Web Services电子书

About Packt

Why subscribe?

Contributors

About the authors

About the reviewer

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Section 1: Introduction and Anatomy of a Modern AI Application

Introduction to Artificial Intelligence on Amazon Web Services

Technical requirements

What is AI?

Applications of AI

Autonomous vehicles

AI in medical care

Personalized predictive keyboards

Why use Amazon Web Services for AI?

Overview of AWS AI offerings

Hands-on with AWS services

Creating your AWS account

Navigating through the AWS Management Console

Finding AWS services

Choosing the AWS region

Test driving the Amazon Rekognition service

Working with S3

Identity and Access Management

Getting familiar with the AWS CLI

Installing Python

Installing Python on macOS

Installing Python on Linux

Installing Python on Microsoft Windows

Windows 10

Earlier Windows versions

Installing the AWS CLI

Configuring the AWS CLI

Invoking the Rekognition service using the AWS CLI

Using Python for AI applications

Setting up a Python development environment

Setting up a Python virtual environment with Pipenv

Creating your first Python virtual environment

First project with the AWS SDK

Summary

References

Anatomy of a Modern AI Application

Technical requirements

Understanding the success factors of artificial intelligence applications

Understanding the architecture design principles for AI applications

Understanding the architecture of modern AI applications

Creation of custom AI capabilities

Working with a hands-on AI application architecture

Object detector architecture

Component interactions of the Object Detector

Creating the base project structure

Developing an AI application locally using AWS Chalice

Developing a demo application web user interface

Deploying AI application backends to AWS via Chalice

Deploying a static website via AWS S3

Summary

Further reading

Section 2: Building Applications with AWS AI Services

Detecting and Translating Text with Amazon Rekognition and Translate

Making the world smaller

Understanding the architecture of Pictorial Translator

Component interactions of Pictorial Translator

Setting up the project structure

Implementing services

Recognition service – text detection

Translation service – translating text

Storage service – uploading files

A recommendation on unit testing

Implementing RESTful endpoints

Translate the image text endpoint

Upload the image endpoint

Implementing the web user interface

index.html

scripts.js

Deploying Pictorial Translator to AWS

Discussing project enhancement ideas

Summary

Further reading

Performing Speech-to-Text and Vice Versa with Amazon Transcribe and Polly

Technical requirements

Technologies from science fiction

Understanding the architecture of Universal Translator

Component interactions of Universal Translator

Setting up the project structure

Implementing services

Transcription service – speech-to-text

Translation Service – translating text

Speech Service – text-to-speech

Storage Service – uploading and retrieving a file

Implementing RESTful endpoints

Translate recording endpoint

Synthesize speech endpoint

Upload recording Endpoint

Implementing the Web User Interface

index.html

scripts.js

Deploying the Universal Translator to AWS

Discussing the project enhancement ideas

Summary

References

Extracting Information from Text with Amazon Comprehend

Technical requirements

Working with your Artificial Intelligence coworker

Understanding the Contact Organizer architecture

Component interactions in Contact Organizer

Setting up the project structure

Implementing services

Recognition Service – text detection

Extraction Service – contact information extraction

Contact Store – save and retrieve contacts

Storage Service – uploading and retrieving a file

Implementing RESTful endpoints

Extract Image Information endpoint

Save contact and get all contacts endpoints

Upload image endpoint

Implementing the web user interface

Index.html

scripts.js

Deploying the Contact Organizer to AWS

Discussing the project enhancement ideas

Summary

Further reading

Building a Voice Chatbot with Amazon Lex

Understanding the friendly human-computer interface

Contact assistant architecture

Understanding the Amazon Lex development paradigm

Setting up the contact assistant bot

The LookupPhoneNumberByName intent

Sample utterances and slots for LookupPhoneNumberByName

Confirmation prompt and response for LookupPhoneNumberByName

Fulfillment for LookupPhoneNumberByName using AWS Lambda

DynamoDB IAM role for LookupPhoneNumberByName

Fulfillment lambda function for LookupPhoneNumberByName

Amazon Lex helper functions

The intent fulfillment for LookupPhoneNumberByName

Test conversations for LookupPhoneNumberByName

The MakePhoneCallByName intent

Sample utterances and lambda initialization/validation for MakePhoneCallByName

Slots and confirmation prompt for MakePhoneCallByName

Fulfillment and response for MakePhoneCallByName

Test conversations for MakePhoneCallByName

Deploying the contact assistant bot

Integrating the contact assistant into applications

Intelligent assistant service implementation

Contact assistant RESTful endpoint

Summary

Further reading

Section 3: Training Machine Learning Models with Amazon SageMaker

Working with Amazon SageMaker

Technical requirements

Preprocessing big data through Spark EMR

Conducting training in Amazon SageMaker

Learning how Object2Vec Works

Training the Object2Vec algorithm

Deploying the trained Object2Vec and running inference

Running hyperparameter optimization (HPO)

Understanding the SageMaker experimentation service

Bring your own model – SageMaker, MXNet, and Gluon

Bring your own container – R model

Summary

Further reading

Creating Machine Learning Inference Pipelines

Technical requirements

Understanding the architecture of the inference pipeline in SageMaker

Creating features using Amazon Glue and SparkML

Walking through the prerequisites

Preprocessing data using PySpark

Creating an AWS Glue job

Identifying topics by training NTM in SageMaker

Running online versus batch inferences in SageMaker

Creating real-time predictions through an inference pipeline

Creating batch predictions through an inference pipeline

Summary

Further reading

Discovering Topics in Text Collection

Technical requirements

Reviewing topic modeling techniques

Understanding how the Neural Topic Model works

Training NTM in SageMaker

Deploying the trained NTM model and running the inference

Summary

Further reading

Classifying Images Using Amazon SageMaker

Technical requirements

Walking through convolutional neural and residual networks

Classifying images through transfer learning in Amazon SageMaker

Creating input for image classification

Defining hyperparameters for image classification

Performing inference through Batch Transform

Summary

Further reading

Sales Forecasting with Deep Learning and Auto Regression

Technical requirements

Understanding traditional time series forecasting

Auto-Regressive Integrated Moving Average (ARIMA )

Exponential smoothing

How the DeepAR model works

Model architecture

Arriving at optimal network weights

Understanding model sales through DeepAR

Brief description of the dataset

Exploratory data analysis

Data pre-processing

Training DeepAR

Predicting and evaluating sales

Summary

Further reading

Section 4: Machine Learning Model Monitoring and Governance

Model Accuracy Degradation and Feedback Loops

Technical requirements

Monitoring models for degraded performance

Developing a use case for evolving training data – ad-click conversion

Creating a machine learning feedback loop

Exploring data

Creating features

Using Amazon's SageMaker XGBoost algorithm to classify ad-click data

Evaluating model performance

Summary

Further reading

What Is Next?

Summarizing the concepts we learned in Part I

Summarizing the concepts we learned in Part II

Summarizing the concepts we learned in Part III

Summarizing the concepts we learned in Part IV

What's next?

Artificial intelligence in the physical world

AWS DeepLens

AWS DeepRacer

Internet of Things and AWS IoT Greengrass

Artificial intelligence in your own field

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think