Introduction to Machine Learning (UX Indonesia Meetup)

Transcript

1. Introduction to Machine Learning Galuh Sahid @galuhsahid | galuh.me UX

   Indonesia Meetup - June 23, 2020

2. • Data Scientist at Gojek • Google Developer Expert in

   Machine Learning • Co-host podcast Kartini Teknologi (kartiniteknologi.id) @galuhsahid Hi! I’m Galuh.

3. @galuhsahid Photo by Bram Van Oost from Unsplash

4. @galuhsahid Photo by Frank V. from Unsplash

5. @galuhsahid Photo by Bence Boros from Unsplash

6. @galuhsahid Photo by Nordwood from Unsplash

7. @galuhsahid Photo by Krsto Jevtic from Unsplash

8. It’s an exciting time to learn about machine learning! @galuhsahid

9. But… what is machine learning? @galuhsahid

10. A field of study that gives computers the ability to

    learn without being explicitly programmed. Arthur Samuel (1959) @galuhsahid

11. How is machine learning different from traditional programming? @galuhsahid

12. Traditional Programming Rules Data Answers @galuhsahid

13. if pixel[5][7] is black and pixel [5][6] is black and

    pixel [5][8] is black and …: if pixel[6][7] is black and pixel[6][7] is black and …: return “panda” … … … else: return “cat” Photo by Damian Patowski from Unsplash @galuhsahid

14. if pixel[5][7] is black and pixel [5][6] is black and

    pixel [5][7] is black and …: if pixel[6][7] is black and pixel[6][7] is black and …: return “panda” … … … else: return “not cat” Photo by Dušan Smetana from Unsplash @galuhsahid

15. Machine Learning Answers Data Rules

16. Answers Data Panda Cat Cat Photo by Max Baskalov and

    Zane Lee from Unsplash Panda @galuhsahid

17. ? Cat ? Photo by Cyrus Chew from Unsplash @galuhsahid

18. Machine learning? Artificial intelligence? Neural networks? Deep learning? @galuhsahid

19. Source @galuhsahid

20. Rule engine Knowledge Graphs Source @galuhsahid

21. Regression Decision Tree Random Forest Source @galuhsahid

22. Ingredients of machine learning @galuhsahid

23. Ingredient #1 Data @galuhsahid

24. Tabular @galuhsahid

25. Text @galuhsahid

26. Sound @galuhsahid

27. Image @galuhsahid

28. Ingredient #2 Features @galuhsahid

29. Examples of features for house price prediction Features @galuhsahid

30. Examples of features for house price prediction Features We want

    to predict this… @galuhsahid

31. Examples of features for house price prediction Features We want

    to predict this… …using these features @galuhsahid

32. What are the features for an image classification task? Features

    @galuhsahid

33. What are the features for an image classification task? Features

    @galuhsahid Source

34. Ingredient #3 Model @galuhsahid

35. What is a “model”? Model - A model maps examples

    to predicted labels - It is defined by weights that are learned during the training process - Once trained, you can use it to make predictions about data that it has never seen before @galuhsahid

36. The training process Model - Iteration 1: 2*number of floors

    + 3*area size = predicted house price Model Data Predictions House #1: predicted: 200 million actual: 500 million difference: 300 million @galuhsahid

37. The training process Model - Iteration 1: 2*number of floors

    + 3*area size = predicted house price Model Data Predictions House #1: predicted: 400 million actual: 500 million difference: 100 million - Iteration 2: 4*number of floors + 6*area size = predicted house price @galuhsahid

38. The training process Model - Iteration 1: 2*number of floors

    + 3*area size = predicted house price Model Data Predictions House #1: predicted: 400 million actual: 500 million difference: 100 million - Iteration 2: 4*number of floors + 6*area size = predicted house price Our model does not get smart right away - it needs to be “trained” @galuhsahid

39. Types of machine learning problems & applications @galuhsahid

40. Type #1 Binary classification Classifies input into one of two

    categories @galuhsahid

41. Spam or not spam Binary Classification @galuhsahid

42. Type #2 Multi-class classification Classifies input into one of more

    than two categories @galuhsahid

43. Language prediction Multi-class Classification @galuhsahid

44. Type #3 Regression Predicts a value on a continuous scale

    @galuhsahid

45. Visit duration & wait time estimates Regression @galuhsahid

46. Type #4 Catalog organization Produces a set of result to

    present to users @galuhsahid

47. Recommender System Catalog Organization @galuhsahid

48. Type #5 Generative model Focuses on generating data rather than

    classifying or organizing it @galuhsahid

49. Generating a new face Generative Model @galuhsahid

50. Generative Model Generating a new text @galuhsahid talktotransformer.com

51. Machine learning myths @galuhsahid

52. Myth #1 Machine learning is neutral @galuhsahid

53. Myth #1 Machine learning is neutral Machine learning systems are

    formulated and built by humans. Machine learning algorithms are trained by humans on data that are collected by humans and represent our (biased) current world. Since humans are biased, machine learning systems also inherit human’s biases. @galuhsahid

54. Gender-neutral translations Myth #1: Machine learning is neutral Source @galuhsahid

55. Gender-neutral translations Myth #1: Machine learning is neutral @galuhsahid

56. Gender-neutral translations Myth #1: Machine learning is neutral @galuhsahid

57. Text generation Myth #1: Machine learning is neutral Source @galuhsahid

58. Myth #2 Machine learning is (or can be) perfect @galuhsahid

59. Myth #2 Machine learning is (or can be) perfect Machine

    learning is never going to be perfect. Even humans can make errors. However, machine learning can improve. @galuhsahid

60. Feedback loop Myth #2: Machine learning is (or can be)

    perfect @galuhsahid

61. Feedback loop Myth #2: Machine learning is (or can be)

    perfect @galuhsahid

62. Feedback loop Myth #2: Machine learning is (or can be)

    perfect @galuhsahid

63. Feedback loop Myth #2: Machine learning is (or can be)

    perfect @galuhsahid

64. Myth #3 We can just “build/apply ML” and call it

    a day @galuhsahid

65. Myth #3 We can just “build/apply ML” and call it

    a day We still need to collaborate with others to ensure that we are solving the right problem. Machine learning is not going to figure out what the problem is. @galuhsahid

66. Example: recommendation system Myth #3: We can just “apply ML”

    and call it a day

67. Example: recommendation system Myth #3: We can just “apply ML”

    and call it a day @galuhsahid

68. Demo @galuhsahid

69. Rock Paper Scissors Demo @galuhsahid Code

70. Scroll with Your Voice Demo @galuhsahid Code

71. More machine learning • On building ML projects: First Steps

    Towards Your First Machine Learning Project • On ML with JavaScript: Machine Learning on the Web • On ML with TensorFlow: A Whirlwind Tour of Machine Learning with TensorFlow @galuhsahid

72. References • On UX and ML: Human-Centered Machine Learning (article)

    • On machine learning bias: Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy (book) • On end-to-end example of building ML-powered products: Building Machine Learning Powered Applications (book) @galuhsahid

73. Thank you! @galuhsahid