1. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Building interactive websites while automating
for efficiency with Amazon AI services
Clifford Duke
Solutions Architect, AWS

2. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Put machine learning in the
hands of every developer
Our mission at

3. Our approach for machine learning
Customer-focused
90%+ of our ML roadmap is
defined by customers
Multi-framework
Support for the most
popular frameworks
Pace of innovation
200+ new ML launches and major feature
updates in the
last year
Breadth and depth
A wide range of AI and ML services in-
production
Security and analytics
Deep set of security and
encryption features, with robust analytics
capabilities
Embedded R&D
Customer-centric approach to
advancing the state of the art

4. The AWS ML Stack
Broadest and most complete set of Machine Learning capabilities
VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD DEVELOPMENT CONTACT CENTERS
Ground
Truth
AWS
Marketplace
for ML
Neo Augmented
AIBuilt-in
algorithms
Notebooks Experiments Processing
Model
training &
tuning
Debugger Autopilot
Model
hosting
Model Monitor
Deep Learning
AMIs & Containers
GPUs &
CPUs
Elastic
Inference
Inferentia FPGA
Amazon
Rekognition
Amazon
Polly
Amazon
Transcribe
+Medical
Amazon
Comprehend
+Medical
Amazon
Translate
Amazon
Lex
Amazon
Personalize
Amazon
Forecast
Amazon
Fraud Detector
Amazon
CodeGuru
AI SERVICES
ML SERVICES
ML FRAMEWORKS & INFRASTRUCTURE
Amazon
Textract
Amazon
Kendra
Contact Lens
For Amazon Connect
SageMaker Studio IDE
Amazon SageMaker
DeepGraphLibrary
RL Coach

5. Fully managed data
processing jobs and
data labeling
workflows
One-click collaborative
notebooks and built-in,
high performance
algorithms and models
One-click
training Debugging and optimization
One-click
deployment and
autoscaling
Amazon SageMaker helps you build, train, and deploy models
Visually track and
compare experiments
Automatically
spot
concept drift
Fully
managed with
auto-scaling
for 75% less
Prepare Build Train & Tune Deploy & Manage
101011010
010101010
000011110
Collect and
prepare
training data
Choose or bring
your own
ML algorithm
Set up and manage
environments
for training
Train, debug, and
tune models
Deploy
model in
production
Manage training runs Monitor
models
Validate
predictions
Scale and manage
the production
environment
Add human
review of
predictions
Web-based IDE for machine learning
Automatically build and train models

6. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
How do I let my applications leverage
machine learning?

7. AI Services
Pre-trained AI services that require
no ML skills or training
Easily add intelligence to your
existing apps and workflows
Quality and accuracy from
continuously-learning APIs
VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD DEVELOPMENT CONTACT CENTERS
Amazon
Rekognition
Amazon
Polly
Amazon
Transcribe
+Medical
Amazon
Comprehend
+Medical
Amazon
Translate
Amazon
Lex
Amazon
Personalize
Amazon
Forecast
Amazon
Fraud Detector
Amazon
CodeGuru
Amazon
Textract
Amazon
Kendra
Contact Lens
For Amazon Connect

8. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Machine learning APIs for vision

9. Amazon Rekognition – Image and Video Analysis

10. Object & scene detection

11. Facial analysis

12. Face search/comparison

13. Use case?
Moderating user-generated content

14. Policing user-generated content
Age range – 26–43 years
Wearing glasses – 99.9%
Eyes closed – 94%
Mouth open – 96%
Eyes closed – 94%
Barrack Obama – 100%
Not smiling – 60.3%
Female – 100%

15. Challenges of non-AI approach
• Manual process for checking images – Labor intensive
• Non-uniformity – Results vary from resource to resource
• Scalability – Difficult to keep up with the rate of image
generation

16. Example: user-generated content moderation
2. Submit picture
4. DetectFaces
8. SearchFaces
- Blacklist
- Whitelist
- Duplicate check
- Persons of interest
1. Live pic
3. Store live pic
Amazon
Rekognition
Lambda Step functions
5. Recognize Celebrities
Amazon
Rekognition
7. Detect Moderation
Labels
9. Store metadata and
analysis Amazon DynamoDB
Elasticsearch
Blacklist images
Amazon
Rekognition
Amazon
Rekognition

17. Amazon Textract – OCR++

18. Amazon Textract – How it works

19. Use case?
Automate traditional document processing

20. Example: automated document processing
2. Extract form
data
1. Capture
document image
Amazon
Textract
Application
Backend
3. Send data to
backend 4. User
submitted data
loaded into
database
Amazon
DynamoDB

21. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Machine learning APIs for chatbots

22. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex:
A service for building conversational interfaces
into your applications using voice and text

23. Amazon Lex – Features
Text and speech language understanding: powered by
the same technology as Amazon Alexa
Deployment to chat services
(Web/Mobile Apps, Facebook, Kik, Slack, Twilio SMS)
Designed for builders: efficient and intuitive tools to
build conversations; scales automatically
Versioning and alias support@

24. Amazon Lex Bots – key concepts
Utterances
Spoken or typed phrases that invoke
your intent
BookHotel
Intents
An intent performs an action in response
to natural language user input
Slots
Slots are input data required to fulfill
the intent
Fulfillment
Fulfillment mechanism for your intent

25. “Book a hotel”
Book hotel
NYC
“Book a hotel in
NYC”
Automatic speech recognition
Hotel booking
New York City
Natural language
understanding
Intent/slot
Model
UtterancesHotel Booking
City New York City
Check in Nov 30th
Check out Dec 2nd
“Your hotel is booked for Nov
30th”
Amazon Polly
Confirmation: “Your hotel is
booked for Nov 30th”
“Can I go ahead
with the booking?
a
in

26. Utterances
I’d like to book a hotel
Can you help me book my hotel?
I want to book a hotel in New York City
I want to make my hotel reservations

27. Slots
Destination City New York City, Seattle, London …
Slot Type Values
Check in Date Valid dates
Check out Date Valid dates

28. Slot elicitation
I’d like to book a hotel
What date do you check in?
New York City
Sure, what city do you want to book?
Nov 30th Check in
11/30/2017
City
New York City

29. Amazon Connect
Self-service, cloud-based contact center service
Real time and
historical analytics
High-quality
voice capability
Call
recording
Skills-based routing
[Automatic Call Distribution (ACD)]

30. Intelligent call center chatbot
Amazon
Connect
Customer
Amazon Lex Lambda:
Fulfillment
DynamoDB:
Customer Data
SNS:
SMS Messaging
Customer calls
Connect to
reschedule an
appointment
Connect calls
Lex chatbot
Lex chatbot calls
Lambda function
to get customer
preferences and
fulfil Intents
Lambda function
sends text message
confirmation via SNS
Customer receives
appointment
confirmation text
message
Lambda
function writes
updates to
DynamoDB

31. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Machine learning APIs for language

32. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
How do you extract insights from
unstructured text?

33. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend:
A fully managed and continuously trained service that
helps you extract insights from unstructured text

34. Amazon Comprehend
Sentiment Entities LanguagesKeyphrases
Topic
modeling
Syntax

35. Amazon Comprehend – Natural Language Processing
Amazon.com, Inc. is located in Seattle, WA
and was founded July 5, 1994 by Jeff
Bezos. Our customers love buying
everything from books to blenders at
great prices
Named Entities
• Amazon.com: Organization
• Seattle, WA : Location
• July 5th,1994: Date
• Jeff Bezos : Person
Keyphrases
• Our customers
• books
• blenders
• great prices
Sentiment
• Positive
Language
• English

36. Amazon Comprehend – Syntax API
Our customers love buying everything
from books to blenders at great prices
Token
(word)
Part of
Speech
customers Noun
love Verb
books Noun
great Adjective
prices Noun

37. Supported parts of speech
ADJ – Adjective
ADP – Adposition
ADV – Adverb
AUX – Auxiliary
CCONJ – Coordinating Conjunction
DET – Determiner
INTJ - Interjection
NOUN - Noun
NUM – Numeral
O – Other
PART – Particle
PRON – Pronoun
PROPN – Proper Noun
PUNCT – Punctuation
SCONJ – Subordinating
Conjunction
SYM – Symbol
VERB – Verb

38. Syntax detection
$ aws comprehend detect-syntax
--language-code 'en' --text 'I love cloud!’
{
"SyntaxTokens": [
{
"TokenId": 1,
"Text": "I",
"BeginOffset": 0,
"EndOffset": 1,
"PartOfSpeech": {
"Tag": "PRON",
"Score": 0.9999802112579346
}
},
...

39. Sentiment analysis
$ aws comprehend detect-sentiment
--language-code 'en' --text 'I love cloud!’
{
"Sentiment": "POSITIVE”,
"SentimentScore": {
"Mixed": 0.012617903761565685,
"Positive": 0.9599817991256714,
"Neutral": 0.021758323535323143,
"Negative": 0.005641999188810587
}
}

40. Popular text analytics use cases
Content Personalization
• Understand related documents based on entities, phrases or even topic similarities for trends
analysis, to drive content personalization and recommendations
Semantic Search
• Index entities for boosting and ranking search results
Intelligent data warehouse
• Query unstructured data in relational databases, processing data within the data lake (Amazon S3)
and then inserting it back into the data warehouse
Social Analytics
• Ingest, process and analyze trends from entities and sentiment from social media posts across
Twitter and Facebook

41. Support for large data sets and topic modeling
STORM
WORLD SERIES
STOCK MARKET
WASHINGTON
LIBRARY OF
NEWS ARTICLES *
Amazon
Comprehend

42. Audio Input
Example: End-to-end audio analysis
store
Amazon S3
trigger
AWS
Lambda
call
Amazon
Transcribe
in cascade
Amazon
Comprehend
aggregate
Amazon
Athena
analyze
Amazon
QuickSight

43. Thank you!
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.