Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Adrian Hornsby, Technical Evangelist @ AWS
Build...
• Technical Evangelist, Developer Advocate,
… Software Engineer
• Own bed in Finland
• Previously:
• Solutions Architect @...
What to Expect from the Session
1. A little bit history & theory never kills
2. AI in AWS
3. Building AI-powered apps x3
No servers to provision
or manage
Scales with usage
Never pay for idle Availability and fault
tolerance built in
Serverles...
EVENT DRIVEN CONTINUOUS SCALING PAY BY USAGE
Serverless means…
Exposing functionality rather than the whole
server(s).
Serverless means…
The rise of AI
Artificial Intelligence
At Amazon
Artificial Intelligence
At Amazon
Data
GPUs
& Acceleration
Cloud
Computing
Algorithms
AWS
The Advent Of Deep
Learning
Machine Learning In The Hands Of Every Developer
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Machine Learning On AWS Today
Machine Learning In The Hands Of Every Developer
Text In, Life-like Speech Out
Amazon Polly
“Today in Seattle, WA
it’s 11°F”
“Today in Seattle Washington
it’s 11 degrees F...
“Today in Seattle, WA, it’s 11°F”
‘"We live for the music" live from the Madison Square Garden.’
1. Automatic, Accurate Te...
2. Intelligible and Easy to Understand
1. Automatic, Accurate Text Processing
A Focus On Voice Quality & Pronunciation
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
“Richard’s number is 2122341237“
“Richard’s number ...
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
4. Customized Pronunciation
“My daughter’s name is ...
A Focus On Voice Quality & Pronunciation
https://www.w3.org/TR/speech-synthesis/<speak>
The spelling of my last name is
<p...
Duolingo voices its language learning service Using Polly
Duolingo is a free language learning service where
users help tr...
<API>
Amazon Polly
</API>
aws polly synthesize-speech
--text "It was nice to live such a wonderful live show"
--output-for...
Pollycast
<demo>
Amazon PollyCast
</demo>
* Initial project by James Siri, Piotr Lewalski
https://github.com/adhorn/pollycast
Amazon Rekognition
Deep learning-based image recognition service
Search, verify, and organize millions of images
Object an...
Object & Scene Detection
Object & Scene Detection
Facial Analysis
Facial Analysis
Facial Search
Facial Search
Collections
Amazon Rekognition
Customers
• Digital Asset Management
• Media and Entertainment
• Travel and Hospitality
• Influencer Ma...
<API>
Amazon Rekognition
</API>
aws rekognition detect-faces
--image '{"S3Object":{"Bucket":"adhorn-reko","Name":"horse.jp...
Poliko
http://poliko.adhorn.me
Poliko
Take Pic
Amazon Cognito
2. Detect Labels
4. Synthesize-speech
Amazon Rekognition
Amazon Pol...
Cognito support for Identity
Username
Password
Sign In
SAML
Identity Provider
Amazon Cognito2. Get AWS credentials
API Gat...
Policies
CognitoAmazon S3
<demo>
Poliko
powered by Amazon Polly & Rekognition
</demo>
https://github.com/adhorn/poliko
http://poliko.adhorn.me
* Ini...
Backend powered by Step
Functions
Start
Sequential Steps
U p l o a d R AW f i l e
D e l e t e R AW f i l e
End
AWS Step Functions
S e l e c t i m a g e
c o n v e rt e r
RA W t o J P E G RA W t o P NGRA W t o TI FF
L o a d i n Da t a b a se
Start
End
Un...
P r o c e s s p h o t o
Re s i ze i m a g e
Start
End
E xt r a c t m e t a d a ta Fa c i a l r e c o g n it i on
L o a d i...
AWS Step Functions
<demo>
Image Recognition and Processing Backend
Step Functions
</demo>
https://github.com/awslabs/lambda-refarch-imagereco...
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Questions?
Adrian Hornsby, Technical Evangelist
...
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWS
Próxima SlideShare
Cargando en…5
×

Building AI-powered Serverless Applications on AWS

411 visualizaciones

Publicado el

Slides from my talk at the AWSLoft in London
https://awsloft.london/session/2017/a5da881d-67f8-4af5-8ace-4f8adcf579db

"In this talk, we will show the audience how to build and deploy serverless AI-powered applications on AWS. In particular, two demos will be analysed in depths. The first demo is a simple mobile web app that allows a user to upload or take a picture with their mobile phone. The result is then spoken out loud using Amazon Polly. This demo is deployed using the AWS CLI (command line interface) with scripting techniques. The second demo is a podcast generator which connects to any RSS feed and converts that feed into a podcast. The result can then be played on iTunes or any podcast player. This demo uses AWS Lambda and Amazon Polly and is deployed using the Serverless framework. We will go through the architecture, the APIs, the code itself and the deployment of those two applications using Amazon Rekognition, Amazon Polly, AWS Lambda, Amazon S3, Amazon Route53, Elasticsearch, and more."

Publicado en: Tecnología
  • Sé el primero en comentar

Building AI-powered Serverless Applications on AWS

  1. 1. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Adrian Hornsby, Technical Evangelist @ AWS Building Serverless AI-powered Applications on AWS @adhorn
  2. 2. • Technical Evangelist, Developer Advocate, … Software Engineer • Own bed in Finland • Previously: • Solutions Architect @AWS • Lead Cloud Architect @Dreambroker • Director of Engineering, Software Engineer, DevOps, Manager, ... @Hdm • Researcher @Nokia Research Center • and a bunch of other stuff. • Climber, like Ginger shots.
  3. 3. What to Expect from the Session 1. A little bit history & theory never kills 2. AI in AWS 3. Building AI-powered apps x3
  4. 4. No servers to provision or manage Scales with usage Never pay for idle Availability and fault tolerance built in Serverless means…
  5. 5. EVENT DRIVEN CONTINUOUS SCALING PAY BY USAGE Serverless means…
  6. 6. Exposing functionality rather than the whole server(s). Serverless means…
  7. 7. The rise of AI
  8. 8. Artificial Intelligence At Amazon
  9. 9. Artificial Intelligence At Amazon
  10. 10. Data GPUs & Acceleration Cloud Computing Algorithms AWS The Advent Of Deep Learning
  11. 11. Machine Learning In The Hands Of Every Developer
  12. 12. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Machine Learning On AWS Today
  13. 13. Machine Learning In The Hands Of Every Developer
  14. 14. Text In, Life-like Speech Out Amazon Polly “Today in Seattle, WA it’s 11°F” “Today in Seattle Washington it’s 11 degrees Fahrenheit” 47 lifelike voices spread across 24 languages
  15. 15. “Today in Seattle, WA, it’s 11°F” ‘"We live for the music" live from the Madison Square Garden.’ 1. Automatic, Accurate Text Processing A Focus On Voice Quality & Pronunciation
  16. 16. 2. Intelligible and Easy to Understand 1. Automatic, Accurate Text Processing A Focus On Voice Quality & Pronunciation
  17. 17. 2. Intelligible and Easy to Understand 3. Add Semantic Meaning to Text “Richard’s number is 2122341237“ “Richard’s number is 2122341237“ Telephone Number A Focus On Voice Quality & Pronunciation 1. Automatic, Accurate Text Processing
  18. 18. 2. Intelligible and Easy to Understand 3. Add Semantic Meaning to Text 4. Customized Pronunciation “My daughter’s name is Kaja.” “My daughter’s name is Kaja.” A Focus On Voice Quality & Pronunciation 1. Automatic, Accurate Text Processing
  19. 19. A Focus On Voice Quality & Pronunciation https://www.w3.org/TR/speech-synthesis/<speak> The spelling of my last name is <prosody rate='x-slow'> <say-as interpret-as="characters">Adrian</say-as> </prosody></speak>
  20. 20. Duolingo voices its language learning service Using Polly Duolingo is a free language learning service where users help translate the web and rate translations. With Amazon Polly our users benefit from the most lifelike Text-to-Speech voices available on the market. Severin Hacker CTO, Duolingo ” “ • Spoken language crucial for language learning • Accurate pronunciation matters • Faster iteration thanks to TTS • As good as natural human speech
  21. 21. <API> Amazon Polly </API> 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
  22. 22. Pollycast
  23. 23. <demo> Amazon PollyCast </demo> * Initial project by James Siri, Piotr Lewalski https://github.com/adhorn/pollycast
  24. 24. Amazon Rekognition Deep learning-based image recognition service Search, verify, and organize millions of images Object and Scene Detection Facial Analysis Face Comparison Facial Recognition
  25. 25. Object & Scene Detection
  26. 26. Object & Scene Detection
  27. 27. Facial Analysis
  28. 28. Facial Analysis
  29. 29. Facial Search
  30. 30. Facial Search
  31. 31. Collections
  32. 32. Amazon Rekognition Customers • Digital Asset Management • Media and Entertainment • Travel and Hospitality • Influencer Marketing • Systems Integration • Digital Advertising • Consumer Storage • Law Enforcement • Public Safety • eCommerce • Education
  33. 33. <API> Amazon Rekognition </API> aws rekognition detect-faces --image '{"S3Object":{"Bucket":"adhorn-reko","Name":"horse.jpg"}}' --attributes "ALL" aws rekognition detect-labels --image '{"S3Object":{"Bucket":"adhorn-reko","Name":"horse.jpg"}}'
  34. 34. Poliko
  35. 35. http://poliko.adhorn.me Poliko Take Pic Amazon Cognito 2. Detect Labels 4. Synthesize-speech Amazon Rekognition Amazon Polly 3. Detect Faces Amazon S3 “Static website hosting” enabled
  36. 36. Cognito support for Identity Username Password Sign In SAML Identity Provider Amazon Cognito2. Get AWS credentials API Gateway DynamoDB S3 Lambda Cognito User Pools Rekognition Polly
  37. 37. Policies CognitoAmazon S3
  38. 38. <demo> Poliko powered by Amazon Polly & Rekognition </demo> https://github.com/adhorn/poliko http://poliko.adhorn.me * Initial project by Martin Elwin
  39. 39. Backend powered by Step Functions
  40. 40. Start Sequential Steps U p l o a d R AW f i l e D e l e t e R AW f i l e End AWS Step Functions
  41. 41. S e l e c t i m a g e c o n v e rt e r RA W t o J P E G RA W t o P NGRA W t o TI FF L o a d i n Da t a b a se Start End Un s u p p or te d i m a g e t yp eParallel Steps AWS Step Functions
  42. 42. P r o c e s s p h o t o Re s i ze i m a g e Start End E xt r a c t m e t a d a ta Fa c i a l r e c o g n it i on L o a d i n Da t a b a se Branching Steps AWS Step Functions
  43. 43. AWS Step Functions
  44. 44. <demo> Image Recognition and Processing Backend Step Functions </demo> https://github.com/awslabs/lambda-refarch-imagerecognition
  45. 45. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Questions? Adrian Hornsby, Technical Evangelist @adhorn adhorn@amazon.com

×