How to make deck to do trick's 1111.pptx

Easy methods

1. AI 101 By Brandon Leshchinskiy 1

2. Watch Mashable video about Google’s AI-based personal assistant: https://www.youtube.com/watch?v=JvbHu_bVa_g 2

3. With the right data and the right model, machine learning can solve many problems. B ut finding the right data and training the right model can be difficult . 3

4. AI ML Deep Learning 4

5. Car photo © Google; kitten photo © source unknown. All rights reserved . This content is excluded from our Creative Commons license . For more information, see https://ocw.mit.edu/help/faq-fair-use / . 5

6. AI can be general or narrow. Terminator image © Skydance Media; car photo © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information , see https://ocw.mit.edu/help/faq-fair-use/ . 6

7. AI can be general or narrow. Terminator image © Skydance Media. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 7

8. AI can be general or narrow. Terminator image © Skydance Media; car photo © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 8

9. AI can be general or narrow . © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 9

10. AI can be general or narrow. Terminator image © Skydance Media; car photo © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 10

11. Typical “narrow” tasks include vision, language processing, and planning. Photo of eye © source unknown; smart speaker and map detail © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 11

12. Typical “narrow” tasks include vision , language processing, and planning. Photo of eye © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 12

13. Typical “narrow” tasks include vision, language processing , and planning. Photo © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 13

14. Typical “narrow” tasks include vision, language processing, and planning . © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 14

15. Typical “narrow” tasks include vision, language processing, and planning. Photo of eye © source unknown; smart speaker and map detail © Google. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 15

16. There are many ways to build AI, including expert systems and tree search. 16

17. There are many ways to build AI, including expert systems and tree search. 17

18. There are many ways to build AI, including expert systems and tree search . 18

19. There are many ways to build AI, including expert systems and tree search. 19

20. AI ML 20

21. Machine learning can perform many tasks, i.e. classification, clustering, and regression. Cat photo © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 21

22. Machine learning can perform many tasks, i.e. classification , clustering, and regression. © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 22

23. Machine learning can perform many tasks, i.e. classification, clustering , and regression. 23

24. Machine learning can perform many tasks, i.e. classification, clustering, and regression . 24

25. Machine learning can perform many tasks, i.e. classification, clustering, and regression. Cat photo © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 25

26. There are three types of learning: supervised, unsupervised, and reinforcement learning. Images © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 26

27. There are three types of learning: supervised , unsupervised, and reinforcement learning. Images © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 27

28. There are three types of learning: supervised, unsupervised , and reinforcement learning. Photo © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 28

29. There are three types of learning: supervised, unsupervised, and reinforcement learning . Images © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 29

30. There are three types of learning: supervised, unsupervised, and reinforcement learning. Images © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 30

31. AI ML Deep Learning 31

32. With the right data and the right model, machine learning can solve many problems. B ut finding the right data and training the right model can be difficult . 32

33. 1. Define a problem. Cat photo © source unknown; dog photo © Getty images. All rights reserved. This content is excluded from our Creative Commons license . For more information , see https://ocw.mit.edu/help/faq-fair-use/ . 33

34. 2 . Find data. Dog Dog Dog Cat Cat Cat Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 34

35. 3. Clean data. Dog Dog Dog Cat Cat Cat Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 35

36. 3. Clean data. Cat Cat Cat Dog Dog Dog Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 36

37. 4. Choose a model. Always Sometimes Always Sometimes Dogs Cats 37

38. 5. Train the model. 38

39. 5. Train the model. Cat © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 39

40. 5. Train the model. Cat © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 40

41. 5. Train the model. Dog © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 41

42. 5. Train the model. Dog © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 42

43. 6. Test the model. Cat © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 43

44. 7. Deploy the model.  44

45. Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/ . 45

46. AI ML Deep Learning 46

47. Goal? 47

48. Goal? Training data? 48

49. Goal? Training data? Model? 49

50. Goal? Training data? Model? Accuracy? 50

51. Goal? Training data? Model? Accuracy? 51

52. AI 101 By Brandon Leshchinskiy 52

53. Goal? Training data? Model? Accuracy? 53

54. MIT OpenCourseWare https ://ocw.mit.edu/ RES.6-013 AI 101 Fall 2021 For information about citing these materials or our Terms of Use, visit: https://ocw.mit.edu/terms . 54