© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Artificial Intelligence for Developers
Boaz Ziniman, Technical Evangelist – Amazon Web Service
@ziniman
boaz.ziniman.aws
ziniman
OOP 2019
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon.com,1995
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Our deep experience with AI/ML differentiates our approach
Product
recommendation
engine
Robot-enabled
fulfillment
centers
New
product
categories
Amazon has invested in AI/ML since our inception, and we
share our knowledge and capabilities with our customers
20181995
Natural language
processing-supported
contact centers
ML-driven supply
chain and
capacity planning
Checkout-free
shopping
using deep learning
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Machine Learning On AWS Today
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Our mission
Put Machine Learning in the hands of
every developer and data scientist
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Application Services
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Rekognition
Deep Learning-based image analysis service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon
Rekognition
Object and scene detection
Facial analysis
Face comparison
Celebrity recognition
Image moderation
Text in image
Image analysis service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Object & Scene Detection
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Facial Analysis
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Smiling?
Facial Analysis
(Deep) Learning from a Masterpiece
http://bit.ly/MonaLisaAI
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Crowd Detection – up to 100 faces
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Facial Search
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Celebrity Recognition
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Text in Image
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
DEMO
https://github.com/ziniman/aws-rekognition-demo
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Rekognition API example
boaz: ~/ 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"
}……
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Rekognition API example
boaz: ~/ 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
},
....
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Face search - media and entertainment
A u t o m a t i n g f o o t a g e
t a g g i n g w i t h A m a z o n
R e k o g n i t i o n
Indexed 99,000 people
Saves ~9,000 hours a year in labor
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Rekognition Video
Deep Learning-based video analysis service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Video Analysis
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Polly
Deep Learning-based text-to-speech service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
“Today in Seattle, WA
it’s 11°F”
Amazon Polly: Text In, Life-like Speech Out
58 voices across 28 languages
“Today in Seattle Washington
it’s 11 degrees Fahrenheit”
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Polly: Text In, Life-like Speech Out
“Today in Mumbai,
India it’s 32°C”
“Today in Mumbai, India it’s 32
degrees Celcius”
58 voices across 28 languages
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
A Focus On Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
• “Today in Seattle, WA, it’s 11°F”
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
A Focus On Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
2. Intelligible and Easy to Understand
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
A Focus On Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
A Focus On Voice Quality & Pronunciation
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>
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
A Focus On Voice Quality & Pronunciation
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">
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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>
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
“This is a new technology that can give users
more choice and better accessibility to our
content, so we wanted to create an
experiment to dive deeper into the user
experience. After a month, we’ll take what
we’ve learned about how users engage with
this feature to develop our first iteration of a
product with Amazon Polly.“
Joseph Price, Product Manager
The Washington Post
https://www.washingtonpost.com/pr/wp/201
7/06/09/the-washington-post-to-start-
experimenting-with-audio-articles-using-
amazon-polly
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Transcribe
Automatic speech recognition service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
“Hello, this is Allan
speaking”
Automatic speech recognition service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Support for
telephony
audio
Timestamp
generation
Intelligent punctuation
and formatting
Recognize multiple
speakers
Custom
vocabulary
Multiple
languages
Automatic speech recognition service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Translate
Neural Machine Translation Service
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
“Hello, what’s up? Do
you want to go see a
movie tonight?”
Amazon Translate
Natural and fluent language translation
“Hallo, was gibt's?
Möchten Sie heute Abend
einen Film sehen?"
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Automatic translation
Real-time
translation
Powered by Deep
Learning
21 Language pairs
(417 translation combinations)
Language detection
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Translate API example
boazz: ~$ aws translate translate-text 
--text "Hello, what’s up? Do you want to go see a movie tonight?" 
--source-language-code auto --target-language-code de
{
"TargetLanguageCode": "de",
"TranslatedText": "Hallo, was gibt's? Möchten Sie heute Abend einen Film
sehen?",
"SourceLanguageCode": "en"
}
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Translate API example
import boto3
translate = boto3.client("translate")
lang_flag_pairs = [("fr", "!"), ("de", """),
("es", "#"), ("pt", "$"),
("zh", "%"), ("ar", "&"),
("ja", "'"), ("ru", "("),
("it", ")"), ("zh-TW", "*"),
(”he", "+"), ("cs", ",")]
for lang, flag in lang_flag_pairs:
print(flag)
print(translate.translate_text(
Text="Hello, World",
SourceLanguageCode="en",
TargetLanguageCode=lang
)['TranslatedText'])
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Translate API example
!
Bonjour, Monde
"
Hallo, Welt
#
Hola, Mundo
$
Olá, Mundo
%
&
‫ﻣ‬‫ﺮ‬‫ﺣ‬‫ﺒ‬‫ﺎ‬،‫ا‬‫ﻟ‬‫ﻌ‬‫ﺎ‬‫ﻟ‬‫ﻢ‬
'
(
Привет, Мир
)
Ciao, Mondo
*
,
+
‫ש‬‫ל‬‫ו‬‫ם‬‫ע‬‫ו‬‫ל‬‫ם‬
,
Ahoj, světe.
https://github.com/ziniman/aws-translate-demo
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Demo – https://translate.boaz.cloud
https://github.com/ziniman/aws-translate-demo
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
DEMO
https://github.com/ziniman/aws-rekognition-demo
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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)
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Comprehend
Natural Language Processing
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Fully managed natural language processing
Discover valuable insights from text
Entities
Key Phrases
Language
Sentiment
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Topic modeling
STORM
WORLD SERIES
AUSTRALIASTOCK MARKET
WASHINGTON
HEALTH
CRISIS
MACHINE
LEARNING
LIBRARY OF
NEWS ARTICLES *
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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))
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Demo
https://github.com/ziniman/aws-comprehend-demo
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Comprehend Medical
Protect patient
information
Lower medical document
processing costs
K E Y F E AT U R E S
Extract medical data
quickly and accurately
Medical
Conditions
Anatomy
Entities
PHI
Identification
Medication and
Dosage
Extraction
No ML experience
required
NEW
Extract text and data from virtually any document
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Lex
Conversational Interfaces
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
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
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
New Services
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Personalize
K E Y F E AT U R E S
Context-aware
Recommendations
Automated
machine learning
Bring existing algorithms
from Amazon SageMaker
Continuous
learning
Data is kept
private and
encrypted
NEW
Improve customer experiences with personalization and recommendations
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Forecast
K E Y F E AT U R E S
Consider
multiple
time-series
at once
Automatic
machine
learning
Visualize
forecasts &
import results into
business apps
Evaluate model
accuracy
Privacy &
encryption
Bring existing
algorithms from
Amazon
SageMaker
NEW
Improve forecasting accuracy by up to 50% at 1/10th the cost
Schedule
forecasts
and training
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Textract
K E Y F E AT U R E S
Optical Character
Recognition
(OCR)
Key-value pair
detection
Adjustable
confidence
thresholds
Table
detection
Bounding box
coordinates
No ML experience
required
NEW
Extract text and data from virtually any document
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
FRAMEWORKS AND INTERFACES
PLATFORM SERVICES
APPLICATION SERVICES
Amazon
Rekognition
Democratization of AI
Amazon
Rekognition Video
Amazon SageMaker AWS DeepLens Amazon DeepRacer
Deep Learning AMI
Amazon EMR
Amazon Polly
Amazon Transcribe
Amazon Lex
Amazon Translate
Amazon Comprehend
Amazon Personalize
Amazon Forecast
Amazon Textract
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Thank You!
Give me feedback
http://bit.ly/2QZddrm
Boaz Ziniman - Technical Evangelist
Amazon Web Service
@ziniman
boaz.ziniman.aws
ziniman

Artificial Intelligence for Developers - OOP Munich

  • 1.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Artificial Intelligence for Developers Boaz Ziniman, Technical Evangelist – Amazon Web Service @ziniman boaz.ziniman.aws ziniman OOP 2019
  • 2.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon.com,1995
  • 3.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.
  • 4.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Our deep experience with AI/ML differentiates our approach Product recommendation engine Robot-enabled fulfillment centers New product categories Amazon has invested in AI/ML since our inception, and we share our knowledge and capabilities with our customers 20181995 Natural language processing-supported contact centers ML-driven supply chain and capacity planning Checkout-free shopping using deep learning
  • 5.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Machine Learning On AWS Today
  • 6.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Our mission Put Machine Learning in the hands of every developer and data scientist
  • 7.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 8.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 9.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Application Services
  • 10.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Rekognition Deep Learning-based image analysis service
  • 11.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Rekognition Object and scene detection Facial analysis Face comparison Celebrity recognition Image moderation Text in image Image analysis service
  • 12.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Object & Scene Detection
  • 13.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Facial Analysis
  • 14.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Smiling? Facial Analysis (Deep) Learning from a Masterpiece http://bit.ly/MonaLisaAI
  • 15.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Crowd Detection – up to 100 faces
  • 16.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Facial Search
  • 17.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 18.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Celebrity Recognition
  • 19.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Text in Image
  • 20.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. DEMO https://github.com/ziniman/aws-rekognition-demo
  • 21.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Rekognition API example boaz: ~/ 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" }……
  • 22.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Rekognition API example boaz: ~/ 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 }, ....
  • 23.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Face search - media and entertainment A u t o m a t i n g f o o t a g e t a g g i n g w i t h A m a z o n R e k o g n i t i o n Indexed 99,000 people Saves ~9,000 hours a year in labor
  • 24.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. 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
  • 25.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Rekognition Video Deep Learning-based video analysis service
  • 26.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Video Analysis
  • 27.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.
  • 28.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Polly Deep Learning-based text-to-speech service
  • 29.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. “Today in Seattle, WA it’s 11°F” Amazon Polly: Text In, Life-like Speech Out 58 voices across 28 languages “Today in Seattle Washington it’s 11 degrees Fahrenheit”
  • 30.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Polly: Text In, Life-like Speech Out “Today in Mumbai, India it’s 32°C” “Today in Mumbai, India it’s 32 degrees Celcius” 58 voices across 28 languages
  • 31.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. A Focus On Voice Quality & Pronunciation 1. Automatic, Accurate Text Processing • “Today in Seattle, WA, it’s 11°F”
  • 32.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. A Focus On Voice Quality & Pronunciation 1. Automatic, Accurate Text Processing 2. Intelligible and Easy to Understand
  • 33.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. A Focus On Voice Quality & Pronunciation 1. Automatic, Accurate Text Processing 2. Intelligible and Easy to Understand 3. Add Semantic Meaning to Text
  • 34.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. A Focus On Voice Quality & Pronunciation 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>
  • 35.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. A Focus On Voice Quality & Pronunciation 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">
  • 36.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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>
  • 37.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.
  • 38.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 39.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. “This is a new technology that can give users more choice and better accessibility to our content, so we wanted to create an experiment to dive deeper into the user experience. After a month, we’ll take what we’ve learned about how users engage with this feature to develop our first iteration of a product with Amazon Polly.“ Joseph Price, Product Manager The Washington Post https://www.washingtonpost.com/pr/wp/201 7/06/09/the-washington-post-to-start- experimenting-with-audio-articles-using- amazon-polly
  • 40.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Transcribe Automatic speech recognition service
  • 41.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. “Hello, this is Allan speaking” Automatic speech recognition service
  • 42.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Support for telephony audio Timestamp generation Intelligent punctuation and formatting Recognize multiple speakers Custom vocabulary Multiple languages Automatic speech recognition service
  • 43.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 44.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Translate Neural Machine Translation Service
  • 45.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. “Hello, what’s up? Do you want to go see a movie tonight?” Amazon Translate Natural and fluent language translation “Hallo, was gibt's? Möchten Sie heute Abend einen Film sehen?"
  • 46.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Automatic translation Real-time translation Powered by Deep Learning 21 Language pairs (417 translation combinations) Language detection
  • 47.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Translate API example boazz: ~$ aws translate translate-text --text "Hello, what’s up? Do you want to go see a movie tonight?" --source-language-code auto --target-language-code de { "TargetLanguageCode": "de", "TranslatedText": "Hallo, was gibt's? Möchten Sie heute Abend einen Film sehen?", "SourceLanguageCode": "en" }
  • 48.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Translate API example import boto3 translate = boto3.client("translate") lang_flag_pairs = [("fr", "!"), ("de", """), ("es", "#"), ("pt", "$"), ("zh", "%"), ("ar", "&"), ("ja", "'"), ("ru", "("), ("it", ")"), ("zh-TW", "*"), (”he", "+"), ("cs", ",")] for lang, flag in lang_flag_pairs: print(flag) print(translate.translate_text( Text="Hello, World", SourceLanguageCode="en", TargetLanguageCode=lang )['TranslatedText'])
  • 49.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Translate API example ! Bonjour, Monde " Hallo, Welt # Hola, Mundo $ Olá, Mundo % & ‫ﻣ‬‫ﺮ‬‫ﺣ‬‫ﺒ‬‫ﺎ‬،‫ا‬‫ﻟ‬‫ﻌ‬‫ﺎ‬‫ﻟ‬‫ﻢ‬ ' ( Привет, Мир ) Ciao, Mondo * , + ‫ש‬‫ל‬‫ו‬‫ם‬‫ע‬‫ו‬‫ל‬‫ם‬ , Ahoj, světe. https://github.com/ziniman/aws-translate-demo
  • 50.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Demo – https://translate.boaz.cloud https://github.com/ziniman/aws-translate-demo
  • 51.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 52.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. DEMO https://github.com/ziniman/aws-rekognition-demo
  • 53.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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)
  • 54.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 55.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Comprehend Natural Language Processing
  • 56.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Fully managed natural language processing Discover valuable insights from text Entities Key Phrases Language Sentiment
  • 57.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Topic modeling STORM WORLD SERIES AUSTRALIASTOCK MARKET WASHINGTON HEALTH CRISIS MACHINE LEARNING LIBRARY OF NEWS ARTICLES *
  • 58.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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))
  • 59.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Demo https://github.com/ziniman/aws-comprehend-demo
  • 60.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Comprehend Medical Protect patient information Lower medical document processing costs K E Y F E AT U R E S Extract medical data quickly and accurately Medical Conditions Anatomy Entities PHI Identification Medication and Dosage Extraction No ML experience required NEW Extract text and data from virtually any document
  • 61.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Lex Conversational Interfaces
  • 62.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. 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
  • 63.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved.© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. New Services
  • 64.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Personalize K E Y F E AT U R E S Context-aware Recommendations Automated machine learning Bring existing algorithms from Amazon SageMaker Continuous learning Data is kept private and encrypted NEW Improve customer experiences with personalization and recommendations
  • 65.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Forecast K E Y F E AT U R E S Consider multiple time-series at once Automatic machine learning Visualize forecasts & import results into business apps Evaluate model accuracy Privacy & encryption Bring existing algorithms from Amazon SageMaker NEW Improve forecasting accuracy by up to 50% at 1/10th the cost Schedule forecasts and training
  • 66.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Amazon Textract K E Y F E AT U R E S Optical Character Recognition (OCR) Key-value pair detection Adjustable confidence thresholds Table detection Bounding box coordinates No ML experience required NEW Extract text and data from virtually any document
  • 67.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. FRAMEWORKS AND INTERFACES PLATFORM SERVICES APPLICATION SERVICES Amazon Rekognition Democratization of AI Amazon Rekognition Video Amazon SageMaker AWS DeepLens Amazon DeepRacer Deep Learning AMI Amazon EMR Amazon Polly Amazon Transcribe Amazon Lex Amazon Translate Amazon Comprehend Amazon Personalize Amazon Forecast Amazon Textract
  • 68.
    © 2019, AmazonWeb Services, Inc. or its Affiliates. All rights reserved. Thank You! Give me feedback http://bit.ly/2QZddrm Boaz Ziniman - Technical Evangelist Amazon Web Service @ziniman boaz.ziniman.aws ziniman