Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Building AI-powered Apps on AWS

496 views

Published on

Slides from my talk at the Serverless Meetup in Helsinki (May 10th)

Published in: Technology
  • Be the first to comment

Building AI-powered Apps on AWS

  1. 1. Adrian Hornsby | Technical Evangelist | AWS May 2017 Building AI-powered apps on AWS <demo> Polly, Reko & more </demo> @adhorn
  2. 2. What’s coming 1. A little bit history never kills 2. AI in AWS 1. Polly 2. Reko 3. Building Mobile apps 1. Cognito 2. CodeStar 4. Putting it all together
  3. 3. Artificial Intelligence At Amazon
  4. 4. Artificial Intelligence At Amazon
  5. 5. The (60 years) rise of Artificial Intelligence
  6. 6. https://en.wikipedia.org/wiki/Artificial_neural_network
  7. 7. The Curse of Dimensionality
  8. 8. The Advent Of Deep Learning Algorithms
  9. 9. Data Algorithms The Advent Of Deep Learning
  10. 10. Data GPUs & Acceleration Algorithms The Advent Of Deep Learning
  11. 11. Data GPUs & Acceleration Cloud Computing Algorithms The Advent Of Deep Learning
  12. 12. Data GPUs & Acceleration Cloud Computing Algorithms AWS The Advent Of Deep Learning
  13. 13. Artificial Intelligence on AWS Polly Text-to-Speech Rekognition Lex Image Analysis ASR & NLU Deep Learning AMI Popular Frameworks
  14. 14. Artificial Intelligence on AWS Polly Text-to-Speech Rekognition Image Analysis
  15. 15. Artificial Intelligence on AWS Polly Text-to-Speech
  16. 16. 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
  17. 17. “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
  18. 18. 2. Intelligible and Easy to Understand 1. Automatic, Accurate Text Processing A Focus On Voice Quality & Pronunciation
  19. 19. 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
  20. 20. 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
  21. 21. 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>
  22. 22. 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
  23. 23. <demo> Amazon Polly API </demo>
  24. 24. PollyCast
  25. 25. <demo> Amazon PollyCast </demo> James Siri Piotr Lewalskihttps://github.com/adhorn/amazon-polly-sample
  26. 26. Artificial Intelligence on AWS Rekognition Image Analysis
  27. 27. 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
  28. 28. Object & Scene Detection
  29. 29. Object & Scene Detection
  30. 30. Facial Analysis
  31. 31. Facial Analysis
  32. 32. Facial Search
  33. 33. Facial Search
  34. 34. Collections
  35. 35. Bynder allows you to easily create, find and use content for branding automation and marketing solutions. With our new AI capabilities, Bynder’s software… now allows users to save hours of admin labor when uploading and organizing their files, adding exponentially more value. Chris Hall CEO, Bynder ” “ With Rekognition, Bynder revolutionizes marketing admin tasks with AI capabilities
  36. 36. <demo> Amazon Rekognition API </demo>
  37. 37. Cognito support for Identity
  38. 38. How it works Username Password Sign In SAML Identity Provider Amazon Cognito 2. Get AWS credentials API Gateway Your APIs DynamoDB S3 Lambda Cognito User Pools
  39. 39. AWS.config.region = 'us-east-1'; // Region AWS.config.credentials = new AWS.CognitoIdentityCredentials( { IdentityPoolId: 'us-east-1:873891a7-92b8-45c2-9c25-212bb7555bc1', }); Simple to use with the SDK
  40. 40. curl -X POST -H "Authorization: $(aws cognito-idp admin-initiate-auth --user-pool-id us-east-1_1ZkFb79PI --client-id 5q4eiv7mmb59lpg6jf9ei82r2j --cli-input-json file:///tmp/authflow.json --query AuthenticationResult.IdToken --output text --region us-east-1)" -H "search-key: building" -H "Cache-Control: no-cache" "https://xxx.amazonaws.com/prod/picture/search/" | native2ascii -encoding UTF-8 -reverse Simple to use with the CLI
  41. 41. AWS CodeStar New integrated AWS console UI for developers Start developing on AWS in minutes Manage software delivery in one place Work across your team, securely
  42. 42. Start projects quickly with templates
  43. 43. Set up secure team access
  44. 44. Configure projects with continuous delivery toolchain
  45. 45. Connect your IDE & Start Coding
  46. 46. Manage delivery pipeline and track issues
  47. 47. <demo> Poliko powered by Amazon Polly & Rekognition </demo>
  48. 48. C o o r d i n a t e t h e c o m p o n e n t s o f d i s t r i b u t e d a p p l i c a t i o n s u s i n g v i s u a l w o r k f l o w s A W S S t e p F u n c t i o n s
  49. 49. 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 A W S S t e p F u n c t i o n s
  50. 50. 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 A W S S t e p F u n c t i o n s
  51. 51. 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 ition L o a d i n Da t a b a se Branching Steps A W S S t e p F u n c t i o n s
  52. 52. https://github.com/awslabs/lambda-refarch-imagerecognition
  53. 53. <demo> Image Recognition and Processing Backend Step Functions </demo> https://github.com/awslabs/lambda-refarch-imagerecognition
  54. 54. Thank You!

×