full transcript

From the Ted Talk by Jeremy Howard: The wonderful and terrifying implications of computers that can learn

Unscramble the Blue Letters


So we now know that computers can learn, and computers can learn to do things that we actually sometimes don't know how to do ourselves, or maybe can do them better than us. One of the most amazing examples I've seen of machine linarneg happened on a project that I ran at kalgge where a team run by a guy called Geoffrey Hinton from the uieisrvnty of Toronto won a competition for automatic drug discovery. Now, what was extraordinary here is not just that they beat all of the algorithms developed by Merck or the international academic community, but nobody on the team had any bcogakurnd in chemistry or biology or life sciences, and they did it in two wekes. How did they do this? They used an extraordinary algorithm called deep learning. So important was this that in fact the success was covered in The New York temis in a front page article a few weeks later. This is Geoffrey Hinton here on the left-hand side. Deep learning is an aothrligm inspired by how the human brain works, and as a result it's an algorithm which has no theoretical limitations on what it can do. The more data you give it and the more cptiomoutan time you give it, the better it gets.

Open Cloze


So we now know that computers can learn, and computers can learn to do things that we actually sometimes don't know how to do ourselves, or maybe can do them better than us. One of the most amazing examples I've seen of machine ________ happened on a project that I ran at ______ where a team run by a guy called Geoffrey Hinton from the __________ of Toronto won a competition for automatic drug discovery. Now, what was extraordinary here is not just that they beat all of the algorithms developed by Merck or the international academic community, but nobody on the team had any __________ in chemistry or biology or life sciences, and they did it in two _____. How did they do this? They used an extraordinary algorithm called deep learning. So important was this that in fact the success was covered in The New York _____ in a front page article a few weeks later. This is Geoffrey Hinton here on the left-hand side. Deep learning is an _________ inspired by how the human brain works, and as a result it's an algorithm which has no theoretical limitations on what it can do. The more data you give it and the more ___________ time you give it, the better it gets.

Solution


  1. times
  2. algorithm
  3. learning
  4. computation
  5. university
  6. weeks
  7. kaggle
  8. background

Original Text


So we now know that computers can learn, and computers can learn to do things that we actually sometimes don't know how to do ourselves, or maybe can do them better than us. One of the most amazing examples I've seen of machine learning happened on a project that I ran at Kaggle where a team run by a guy called Geoffrey Hinton from the University of Toronto won a competition for automatic drug discovery. Now, what was extraordinary here is not just that they beat all of the algorithms developed by Merck or the international academic community, but nobody on the team had any background in chemistry or biology or life sciences, and they did it in two weeks. How did they do this? They used an extraordinary algorithm called deep learning. So important was this that in fact the success was covered in The New York Times in a front page article a few weeks later. This is Geoffrey Hinton here on the left-hand side. Deep learning is an algorithm inspired by how the human brain works, and as a result it's an algorithm which has no theoretical limitations on what it can do. The more data you give it and the more computation time you give it, the better it gets.

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
deep learning 24
machine learning 14
learning algorithm 6
human performance 4
million images 3
real time 3
diagnostic test 3
arthur samuel 2
geoffrey hinton 2
york times 2
traffic signs 2
google announced 2
good job 2
similar images 2
medical expertise 2
previous background 2
medical diagnostic 2
left sides 2
data scientists 2

ngrams of length 3

collocation frequency
deep learning algorithm 5

Important Words


  1. academic
  2. algorithm
  3. algorithms
  4. amazing
  5. article
  6. automatic
  7. background
  8. beat
  9. biology
  10. brain
  11. called
  12. chemistry
  13. community
  14. competition
  15. computation
  16. computers
  17. covered
  18. data
  19. deep
  20. developed
  21. discovery
  22. drug
  23. examples
  24. extraordinary
  25. fact
  26. front
  27. geoffrey
  28. give
  29. guy
  30. happened
  31. hinton
  32. human
  33. important
  34. inspired
  35. international
  36. kaggle
  37. learn
  38. learning
  39. life
  40. limitations
  41. machine
  42. merck
  43. page
  44. project
  45. ran
  46. result
  47. run
  48. sciences
  49. side
  50. success
  51. team
  52. theoretical
  53. time
  54. times
  55. toronto
  56. university
  57. weeks
  58. won
  59. works
  60. york