AI Services for Developers - Floor28

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
SSID: Guest
Password: Cube@11999
Introduction to AI services for
Developers
Boaz Ziniman
Technical Evangelist, Amazon Web Service
@ziniman
boaz.ziniman.aws

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Floor28 Agenda
GameDay
24 Oct
Enterprise IT Day
23 Oct
Builders Day
AppSync, Alexa & IoT
22 Oct
Big Data Day
14 Oct
ML & DL Day
15 Oct
DevOps Day
16 Oct
DevOps Day
17 Oct
Technical Sessions
Serverless Data Workshop
Big Data UG Meetup
Technical Sessions
SageMaker Workshop
ML&DL Meetup
Technical Sessions
K8s Workshop
DevOps Meetup
Technical Sessions
Spot Workshop
Databases Day
18 Oct
Technical Sessions
Serverless Workshop
Virtual assistants UG Meetup
Technical Sessions
PyTorch Meetup
Technical Sessions
CDK Workshop
AWS IL UG Meetup
Builders Day
Serverless backend
21 Oct
Technical Sessions

Amazon.com,1995

Two Decades of Recommender Systems at Amazon.com (2017)
https://www.computer.org/csdl/mags/ic/2017/03/mic2017030012.html
G.D. Linden, J.A. Jacobi, and E.A. Benson,
Collaborative Recommendations Using Item-to-Item
Similarity Mappings, US Patent 6,266,649, to
Amazon.com, Patent and Trademark Office, 2001
(filed 1998).

Machine Learning On AWS Today

Our mission
Put Machine Learning in the hands of every
developer and data scientist

Application
Services
Platform
Services
Frameworks
&
Infrastructure
API-driven services: Vision & Language Services, Conversational Chatbots
Deploy machine learning models with high-performance machine learning
algorithms, broad framework support, and one-click training, tuning, and
inference.
Develop sophisticated models with any framework, create managed, auto-
scaling clusters of GPUs for large scale training, or run inference on trained
models.
AWS ML Stack

Frameworks & Infrastructure

Amazon EC2 P3 Instances
• T h e f a s t e s t , m o s t p o w e r f u l G P U i n s t a n c e s i n t h e
c l o u d
• U p t o e i g h t N V I D I A T e s l a V 1 0 0 G P U s
• 1 P e t a F L O P s o f c o m p u t a t i o n a l p e r f o r m a n c e – 1 4 x
b e t t e r t h a n P 2
• 3 0 0 G B / s G P U - t o - G P U c o m m u n i c a t i o n
( N V L i n k ) – 9 x b e t t e r t h a n P 2
• 1 6 G B G P U m e m o r y w i t h 9 0 0 G B / s e c p e a k G P U
m e m o r y b a n d w i d t h

AWS Deep Learning AMI
• Easy-to-launch tutorials
• Hassle-free setup and configuration
• Pay only for what you use
• Accelerate your model training and deployment
• Support for popular deep learning frameworks

Platform Services

End-to-End
Machine Learning
Platform
Zero setup Flexible Model
Training
Pay by the second
$
Amazon SageMaker
• Build, train, and deploy machine learning models at scale

Highly-optimized
machine learning
algorithms
BuildPre-built
notebook
instances
Amazon SageMaker

Highly-optimized
machine learning
algorithms
BuildPre-built
notebook
instances
Train
One-click training
for ML, DL, and
custom algorithms
Easier training with
hyperparameter
optimization
Amazon SageMaker

Highly-optimized
machine learning
algorithms
Deployment
without
engineering effort
Fully-managed
hosting at scale
BuildPre-built
notebook
instances
Deploy
Train
One-click training
for ML, DL, and
custom algorithms
Easier training with
hyperparameter
optimization
Amazon SageMaker

Application Services

Amazon Rekognition
Deep Learning-based image analysis service

Amazon
Rekognition
Object and scene detection
Facial analysis
Face comparison
Celebrity recognition
Image moderation
Text in image
Image analysis service

Object & Scene Detection

Facial Analysis

Smiling?
Facial Analysis
(Deep) Learning from a Masterpiece
http://bit.ly/MonaLisaAI

NEWCrowd Detection – up to 100 faces

Facial Search

Explicit Nudity
Nudity
Graphic Male Nudity
Graphic Female Nudity
Sexual Activity
Partial Nudity
Suggestive
Female Swimwear or Underwear
Male Swimwear or Underwear
Revealing Clothes
Image Moderation

Celebrity Recognition

NEWText in Image

Rekognition API example
boazz: ~/ aws rekognition detect-labels
--image '{"S3Object":{"Bucket":"demos.ziniman.com","Name":"photos/reko.jpg"}}’
{
"Labels": [
{
"Confidence": 99.14048767089844,
"Name": "Human"
},
{
"Confidence": 99.1404800415039,
"Name": "People"
},
{
"Confidence": 99.14048767089844,
"Name": "Person"
}……

Rekognition API example
boazz: ~/ aws rekognition detect-faces
--image '{"S3Object":{"Bucket":"demos.ziniman.com","Name":"photos/reko.jpg"}}'
--attributes "ALL”
{
"FaceDetails": [
{
....
"Gender": {
"Confidence": 99.9211654663086,
"Value": "Male"
},
"AgeRange": {
"High": 52,
"Low": 35
},
....

Marinus Analytics
Marinus Analytics provides law enforcement
with tools founded in artificial intelligence.
Traffic Jam, is a suite of tools for use by law
enforcement agencies on sex trafficking
investigations.
Before using Amazon Rekognition, their only
recourse was manual processing; this was time-
intensive or not possible.
Now, investigators are able to take effective
action by searching through millions of records
in seconds to find victims.
http://www.marinusanalytics.com/articles/2017/10/
17/amazon-rekognition-helps-marinus-analytics-
fight-human-trafficking

Demo
https://github.com/ziniman/aws-rekognition-demo

Amazon Rekognition Video
Deep Learning-based video analysis service

Video Analysis

Amazon Polly
Deep Learning-based text-to-speech service

Amazon Polly
“Today in Seattle, WA
it’s 11°F”
Amazon Polly: Text In, Life-like Speech Out
52 voices across 25 languages
“Today in Seattle Washington
it’s 11 degrees Fahrenheit”

Amazon Polly
Amazon Polly: Text In, Life-like Speech Out
52 voices across 25 languages
“Today in Mumbai,
India it’s 32°C”
“Today in Mumbai, India it’s 32
degrees Celcius”

A Focus On Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
• “Today in Seattle, WA, it’s 11°F”

• Automatic, Accurate Text Processing
• Intelligible and Easy to Understand

• Automatic, Accurate Text Processing
• Intelligible and Easy to Understand
• Add Semantic Meaning to Text

https://www.w3.org/TR/speech-synthesis/
<speak>
The spelling of my name is
<prosody rate='x-slow'>
<say-as interpret-as="characters">Boaz</say-as>
</prosody>
</speak>

1. Automatic, Accurate Text Processing
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
• “Richard’s number is 2122341237“
<say-as interpret-as="telephone">

Voice Modification: Vocal Tract Length
<speak>
This is Brian without any voice modifications.
<amazon:effect vocal-tract-length="+15%"> Imagine now that I got bigger… </amazon:effect>
<amazon:effect vocal-tract-length="+25%"> Suppose that I got even bigger still… </amazon:effect>
Now let's go back and hear the effect when I go in the opposite direction.
<amazon:effect vocal-tract-length="-15%"> Can you tell that I'm getting smaller? </amazon:effect>
<amazon:effect vocal-tract-length="-25%"> Now I'm even smaller than before. </amazon:effect>
</speak>

Polly API example
aws polly synthesize-speech
--text "It was nice to live such a wonderful live show"
--output-format mp3
--voice-id Joanna
--text-type text
johanna.mp3

Polly API example
aws polly synthesize-speech
--output-format mp3 --voice-id Matthew --text-type ssml
--text '<speak>
<amazon:auto-breaths>
<prosody rate="x-slow" pitch="low">Here is my little secret.</prosody>
<amazon:breath duration="long" volume="x-loud"/>
<amazon:effect name="whispered">
<prosody rate="x-slow">
<prosody pitch="x-low">I</prosody>
killed Mufasa!
</prosody>
</amazon:effect>
</amazon:auto-breaths>
</speak>'
mufasa.mp3

Duolingo
• Duolingo is the most popular
language-learning platform and the
most downloaded education app in
the world, with more than 170 million
users.
• They have run six A/B tests, testing an
Amazon Polly voice against a voice
from other TTS providers.
• For all of these experiments, the
winning condition was the Amazon
Polly voice https://aws.amazon.com/blogs/machine-
learning/powering-language-learning-on-
duolingo-with-amazon-polly/

Amazon Translate
Neural Machine Translation Service

“Hello, what’s up? Do
you want to go see a
movie tonight?”
Amazon Translate
• Natural and fluent language translation
" Hallo, was ist los? Willst
du heute Abend einen
Film sehen? "
Amazon
Translate

Automatic translation
Real-time translation Powered by Deep
Learning
12 Language pairs
(more to come)
Language detection

Hotels.com
Machine Translation
At Hotels.com, we are committed to offering all of our customers the
most relevant and up to date information about their destination. To
achieve that, we operate 90 localized websites in 41 languages. We have
more than 25M customer reviews and more are coming in every day,
making a great candidate for machine translation. Having evaluated
Amazon Translate and several other solutions, we believe that Amazon
Translate presents a quick, efficient and most importantly, accurate
solution.
Matt Fryer, VP and Chief Data Science Officer, Hotels.com

Polly
def speak(text_string, voice="Joanna"):
try:
# Request speech synthesis
response = polly.synthesize_speech(Text=text_string,
TextType="text", OutputFormat="pcm", VoiceId=voice)
except (BotoCoreError, ClientError) as error:
# The service returned an error, exit gracefully
print(error)
exit(-1)
# Access the audio stream from the response
if "AudioStream" in response:
stream = pya.open(format=pya.get_format_from_width(width=2), channels=1, rate=16000, output=True)
stream.write(response['AudioStream'].read())
sleep(1)
stream.stop_stream()
stream.close()
else:
# The response didn't contain audio data, return False
print("Could not stream audio")
return(False)

Rekognition
def reko_detect_labels(image_bytes):
response = reko.detect_labels(
Image={
'Bytes': image_bytes
},
MaxLabels=8,
MinConfidence=60
)
return response
def reko_detect_faces(image_bytes):
response = reko.detect_faces(
Image={
'Bytes': image_bytes
},
Attributes=['ALL']
)
return response

Amazon Transcribe
Automatic speech recognition service

“Hello, this is Allan
speaking”
Amazon
Transcribe

Support for
telephony
audio
Timestamp
generation
Intelligent
punctuation
and formatting
Recognize
multiple
speakers
Custom
vocabulary
Multiple
languages

ringDNA
RingDNA is an end-to-end communications
platform for sales teams.
Hundreds of enterprise organizations use
RingDNA to increase productivity, engage in
smarter sales conversations, gain predictive
sales insights and improve their win rate.
Speech to Text
"A critical component of RingDNA’s
Conversation AI requires best of breed speech-
to-text to deliver transcriptions of every
phone call. RingDNA is excited about Amazon
Transcribe since it provides high-quality
speech recognition at scale, helping us to
better transcribe every call to text"
Howard Brown, CEO & Founder, RingDNA
https://www.youtube.com/watch?v=1ZJ_f1bDdog

Amazon Comprehend
Natural Language Processing

Fully managed natural language processing
• Discover valuable insights from text
Entities
Key Phrases
Language
Sentiment
Amazon
Comprehend

Run Amazon Comprehend on S3 Bucket
import boto3
import json
s3 = boto3.resource('s3’)
bucket_name = ‘my_bucket’
region_name = ‘us-east-1’
bucket = s3.Bucket(bucket_name)
comprehend = boto3.client(service_name='comprehend', region_name=region)
for obj in bucket.objects.all():
body = obj.get()['Body'].read()
text = body
sentiment_response = comprehend.detect_sentiment(Text=text, LanguageCode='en’)
print(json.dumps(sentiment_response, sort_keys=True, indent=4))

Demo
https://github.com/ziniman/aws-comprehend-demo

Topic modeling
STORM
WORLD SERIES
AUSTRALIASTOCK
MARKET
WASHINGTON
HEALTH
CRISIS
MACHINE
LEARNING
LIBRARY OF
NEWS ARTICLES *
Amazon
Comprehend

Amazon Lex
Conversational Interfaces

Intents
A particular goal that the
user wants to achieve
Utterances
Spoken or typed phrases
that invoke your intent
Slots
Data the user must provide to fulfill the
intent
Prompts
Questions that ask the user to input
data
Fulfillment
The business logic required to fulfill the
user’s intent
BookHotel

Lex Bots
Salesforce
Microsoft Dynamics
Marketo
Zendesk
Web
Devices
Apps
Facebook Messenger,
Slack
Amazon
Connect
Mobile
Mobile Hub
integration
Quickbooks
Amazon Lex: Conversational Chatbots

Democratization of AI
FRAMEWORKS AND INTERFACES
PLATFORM SERVICES
APPLICATION SERVICES
Amazon
Rekognition
Amazon Polly Amazon Lex
Amazon
Rekognition Video
Amazon Transcribe
Amazon Comprehend
Amazon SageMaker AWS DeepLens Amazon EMR
Deep Learning AMI
Amazon Translate

Thank You!
Boaz Ziniman
Technical Evangelist, Amazon Web Service
Give me feedback – Talk to my Bot
m.me/boaz.ziniman.aws
@ziniman
boaz.ziniman.aws

SSID: Guest
Password: Cube@11999
GAME DAY
PUT YOUR SKILLS TO THE TEST
OCT 24
Register now: bit.ly/Floor28GameDay

AI Services for Developers - Floor28

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to AI Services for Developers - Floor28

Similar to AI Services for Developers - Floor28 (20)

More from Boaz Ziniman

More from Boaz Ziniman (20)

Recently uploaded

Recently uploaded (20)

AI Services for Developers - Floor28