Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Machine Learning & CoreML by Anita Agrawal Swift Hyderabad

Machine Learning & CoreML by Anita Agrawal Swift Hyderabad


Swift India

July 08, 2017


  1. Machine Learning & Core ML By Anita Agrawal

  2. Today’s Agenda • Introduction to Machine learning. • Different Types

    of Machine Learning. • Machine Learning in our day to day lives. • Machine Learning In iOS. • Introduction to Core ML Framework. • Sample Demo Application Using Core ML.
  3. What Companies have to say About Machine Learning

  4. “A breakthrough in machine learning would be worth ten Microsofts”

    “Machine learning is enabling us to say yes to some things that in past years we would have said no to” “Web rankings today are mostly a matter of machine learning” “ Technologies like artificial intelligence and machine learning can make huge difference to everyday”
  5. Introduction to Machine Learning

  6. Machine learning is a type of Artificial intelligence (AI) that

    provides computers with the ability to learn without being explicitly programmed.
  7. Traditional Programming Computer Data Program Output Computer Data Output Program

    Machine Learning
  8. Machine Learning Process Training Data model/ predictor Training the Model

    with Data Prediction model/ predictor Test the Model with unseen data Testing Data Machine learning is about predicting future based upon the past.
  9. Types Of machine Learning Reinforcement Learning Supervised learning. Unsupervised Learning.

  10. Data??

  11. examples Data examples examples examples

  12. Machine learning in apple’s products and services • Siri •

    Photos • Music • Camera • Fitness related apps • QuickType keyboard • iWatch
  13. Real Time Image Recognition Text Prediction Entity Recognition Sentiment Analysis

    Handwriting Recognition Style Transfer Search Ranking Machine Translation Image Captioning Personalization Face Detection Emotion Detection Speaker Identification Music Tagging Text Summarization
  14. When and Why

  15. Training Offline +Labels Learning Algorithm Model

  16. Inference Model Label : 96% Confidence : Rose

  17. ML Frameworks Your App Vision Natural Language Processing Core ML

    Domain Specific Framework Accelerate Metal Performance Shaders ML Framework ML Performance Primitives
  18. Core ML macOS iOS watchOS tvOS

  19. CoreML Framework Simple Performant Compatible

  20. Model Types Text Prediction Sentiment Analysis Handwriting Recognition Translation Music

    Tagging Scene Classification Feed Forward Neural Networks Convolutional Neural Networks Recurrent Neural Networks Tree Ensembles Support Vector Machines Generalized Linear Models
  21. Model Types Text Prediction Sentiment Analysis Handwriting Recognition Translation Music

    Tagging Scene Classification
  22. Core ML Model Single Document Public Format

  23. Where do the Models come from??

  24. Sample Models https://developer.apple.com/machine-learning/ Core ML Model Ready to use Task

  25. Convert to Core ML Model Core ML Tools python Model

    Providers Open Source
  26. Model as Code Xcode Your App

  27. Development Flow

  28. References https://developer.apple.com/videos/play/wwdc2017/703/ https://developer.apple.com/documentation/coreml/ integrating_a_core_ml_model_into_your_app https://medium.com/towards-data-science/introduction-to-core-ml-conversion- tool-d1466bf10018 https://medium.com/compileswift/swift-world-whats-new-in-ios-11- vision-456ba4156bad https://www.raywenderlich.com/164213/coreml-and-vision-machine-learning- in-ios-11-tutorial

  29. Resources Images : www.google.com Flow and Content : WWDC 2017,

    session 703 Demo App : https://medium.com/towards-data-science/introduction-to-core-ml- conversion-tool-d1466bf10018
  30. Questions??

  31. Thank You!