full transcript

From the Ted Talk by Rana el Kaliouby: This app knows how you feel -- from the look on your face

Unscramble the Blue Letters


Teaching a computer to read these facial emotions is hard, because these action units, they can be fast, they're subtle, and they combine in many different ways. So take, for example, the smile and the smirk. They look somewhat similar, but they mean very different things. (Laughter) So the smile is positive, a srmik is often negative. Sometimes a smirk can make you become famous. But seriously, it's important for a computer to be able to tell the difference between the two eesipnrxsos.

So how do we do that? We give our algorithms tens of thousands of examples of people we know to be smiling, from different ethnicities, ages, gednres, and we do the same for smirks. And then, using deep learning, the algorithm looks for all these textures and wrinkles and spahe changes on our face, and basically lnraes that all slemis have common characteristics, all smirks have sbluty different ciarhctaetrsics. And the next time it sees a new face, it essentially learns that this face has the same characteristics of a smile, and it says, "Aha, I recognize this. This is a smile expression."

Open Cloze


Teaching a computer to read these facial emotions is hard, because these action units, they can be fast, they're subtle, and they combine in many different ways. So take, for example, the smile and the smirk. They look somewhat similar, but they mean very different things. (Laughter) So the smile is positive, a _____ is often negative. Sometimes a smirk can make you become famous. But seriously, it's important for a computer to be able to tell the difference between the two ___________.

So how do we do that? We give our algorithms tens of thousands of examples of people we know to be smiling, from different ethnicities, ages, _______, and we do the same for smirks. And then, using deep learning, the algorithm looks for all these textures and wrinkles and _____ changes on our face, and basically ______ that all ______ have common characteristics, all smirks have ______ different _______________. And the next time it sees a new face, it essentially learns that this face has the same characteristics of a smile, and it says, "Aha, I recognize this. This is a smile expression."

Solution


  1. learns
  2. smiles
  3. characteristics
  4. smirk
  5. genders
  6. expressions
  7. subtly
  8. shape

Original Text


Teaching a computer to read these facial emotions is hard, because these action units, they can be fast, they're subtle, and they combine in many different ways. So take, for example, the smile and the smirk. They look somewhat similar, but they mean very different things. (Laughter) So the smile is positive, a smirk is often negative. Sometimes a smirk can make you become famous. But seriously, it's important for a computer to be able to tell the difference between the two expressions.

So how do we do that? We give our algorithms tens of thousands of examples of people we know to be smiling, from different ethnicities, ages, genders, and we do the same for smirks. And then, using deep learning, the algorithm looks for all these textures and wrinkles and shape changes on our face, and basically learns that all smiles have common characteristics, all smirks have subtly different characteristics. And the next time it sees a new face, it essentially learns that this face has the same characteristics of a smile, and it says, "Aha, I recognize this. This is a smile expression."

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
action unit 3
bring emotions 2
emotionally intelligent 2
human face 2
emotion data 2


Important Words


  1. action
  2. ages
  3. algorithm
  4. algorithms
  5. basically
  6. characteristics
  7. combine
  8. common
  9. computer
  10. deep
  11. difference
  12. emotions
  13. essentially
  14. ethnicities
  15. examples
  16. expression
  17. expressions
  18. face
  19. facial
  20. famous
  21. fast
  22. genders
  23. give
  24. hard
  25. important
  26. laughter
  27. learning
  28. learns
  29. negative
  30. people
  31. positive
  32. read
  33. recognize
  34. sees
  35. shape
  36. similar
  37. smile
  38. smiles
  39. smiling
  40. smirk
  41. smirks
  42. subtle
  43. subtly
  44. teaching
  45. tens
  46. textures
  47. thousands
  48. time
  49. units
  50. ways
  51. wrinkles