full transcript

From the Ted Talk by Briana Brownell: How does artificial intelligence learn?

Unscramble the Blue Letters


Today, aicftirail intelligence helps doctors diagnose patients, pilots fly commercial aircraft, and city paelnrns priecdt traffic. But no metatr what these AIs are doing, the computer scientists who deiesgnd them likely don’t know exactly how they’re doing it. This is because artificial intelligence is often self-taught, working off a simple set of instructions to carete a unique array of rules and strategies. So how exactly does a mahncie learn?

There are many different ways to biuld self-teaching programs. But they all rely on the three basic types of machine learning: unepuviesrsd learning, supervised learning, and reinforcement learning. To see these in action, let’s imagine researchers are trying to pull information from a set of medical data containing thousands of patient profiles.

Open Cloze


Today, __________ intelligence helps doctors diagnose patients, pilots fly commercial aircraft, and city ________ _______ traffic. But no ______ what these AIs are doing, the computer scientists who ________ them likely don’t know exactly how they’re doing it. This is because artificial intelligence is often self-taught, working off a simple set of instructions to ______ a unique array of rules and strategies. So how exactly does a _______ learn?

There are many different ways to _____ self-teaching programs. But they all rely on the three basic types of machine learning: ____________ learning, supervised learning, and reinforcement learning. To see these in action, let’s imagine researchers are trying to pull information from a set of medical data containing thousands of patient profiles.

Solution


  1. build
  2. create
  3. artificial
  4. machine
  5. unsupervised
  6. matter
  7. planners
  8. designed
  9. predict

Original Text


Today, artificial intelligence helps doctors diagnose patients, pilots fly commercial aircraft, and city planners predict traffic. But no matter what these AIs are doing, the computer scientists who designed them likely don’t know exactly how they’re doing it. This is because artificial intelligence is often self-taught, working off a simple set of instructions to create a unique array of rules and strategies. So how exactly does a machine learn?

There are many different ways to build self-teaching programs. But they all rely on the three basic types of machine learning: unsupervised learning, supervised learning, and reinforcement learning. To see these in action, let’s imagine researchers are trying to pull information from a set of medical data containing thousands of patient profiles.

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
computer scientists 4
reinforcement learning 3
artificial intelligence 2
patient profiles 2
unsupervised learning 2
healthy patients 2
supervised learning 2
treatment plans 2
learning program 2


Important Words


  1. action
  2. aircraft
  3. ais
  4. array
  5. artificial
  6. basic
  7. build
  8. city
  9. commercial
  10. computer
  11. create
  12. data
  13. designed
  14. diagnose
  15. doctors
  16. fly
  17. helps
  18. imagine
  19. information
  20. instructions
  21. intelligence
  22. learn
  23. learning
  24. machine
  25. matter
  26. medical
  27. patient
  28. patients
  29. pilots
  30. planners
  31. predict
  32. profiles
  33. programs
  34. pull
  35. reinforcement
  36. rely
  37. researchers
  38. rules
  39. scientists
  40. set
  41. simple
  42. strategies
  43. supervised
  44. thousands
  45. today
  46. traffic
  47. types
  48. unique
  49. unsupervised
  50. ways
  51. working