full transcript
"From the Ted Talk by Nick Bostrom: What happens when our computers get smarter than we are?"

Unscramble the Blue Letters

Today, the action is really around machine learning. So rather than hanfictdanrg knowledge representations and features, we ctaere amhogirlts that learn, often from raw perceptual data. Basically the same thing that the human infant does. The result is A.I. that is not limited to one domain — the same system can learn to translate between any piars of languages, or laern to play any computer game on the Atari console. Now of course, A.I. is still nowhere near having the same powerful, cross-domain ability to learn and plan as a human being has. The cetorx still has some algorithmic tricks that we don't yet know how to match in machines.

Open Cloze

Today, the action is really around machine learning. So rather than ____________ knowledge representations and features, we ______ __________ that learn, often from raw perceptual data. Basically the same thing that the human infant does. The result is A.I. that is not limited to one domain — the same system can learn to translate between any _____ of languages, or _____ to play any computer game on the Atari console. Now of course, A.I. is still nowhere near having the same powerful, cross-domain ability to learn and plan as a human being has. The ______ still has some algorithmic tricks that we don't yet know how to match in machines.

Solution

  1. cortex
  2. learn
  3. algorithms
  4. pairs
  5. handcrafting
  6. create

Original Text

Today, the action is really around machine learning. So rather than handcrafting knowledge representations and features, we create algorithms that learn, often from raw perceptual data. Basically the same thing that the human infant does. The result is A.I. that is not limited to one domain — the same system can learn to translate between any pairs of languages, or learn to play any computer game on the Atari console. Now of course, A.I. is still nowhere near having the same powerful, cross-domain ability to learn and plan as a human being has. The cortex still has some algorithmic tricks that we don't yet know how to match in machines.

ngrams of length 2

collocation frequency
artificial intelligence 7
machine intelligence 4
optimization process 4
ed witten 3
human level 3
hard work 3
control problem 3

Important Words

  1. ability
  2. action
  3. algorithmic
  4. algorithms
  5. atari
  6. basically
  7. computer
  8. console
  9. cortex
  10. create
  11. data
  12. domain
  13. features
  14. game
  15. handcrafting
  16. human
  17. infant
  18. knowledge
  19. languages
  20. learn
  21. learning
  22. limited
  23. machine
  24. machines
  25. match
  26. pairs
  27. perceptual
  28. plan
  29. play
  30. powerful
  31. raw
  32. representations
  33. result
  34. system
  35. today
  36. translate
  37. tricks