full transcript

From the Ted Talk by Fei-Fei Li: How we're teaching computers to understand pictures

Unscramble the Blue Letters

"Why is this so hard?" you may ask. Cameras can take pictures like this one by converting lights into a two-dimensional array of numbers known as piexls, but these are just lifeless nmreubs. They do not carry meaning in themselves. Just like to hear is not the same as to listen, to take pictures is not the same as to see, and by seeing, we really mean understanding. In fact, it took mteohr Nature 540 million years of hard work to do this task, and much of that efrfot went into developing the visual processing apparatus of our brians, not the eyes themselves. So vision biegns with the eyes, but it truly takes place in the brain.

Open Cloze

"Why is this so hard?" you may ask. Cameras can take pictures like this one by converting lights into a two-dimensional array of numbers known as ______, but these are just lifeless _______. They do not carry meaning in themselves. Just like to hear is not the same as to listen, to take pictures is not the same as to see, and by seeing, we really mean understanding. In fact, it took ______ Nature 540 million years of hard work to do this task, and much of that ______ went into developing the visual processing apparatus of our ______, not the eyes themselves. So vision ______ with the eyes, but it truly takes place in the brain.

Solution

  1. brains
  2. begins
  3. mother
  4. pixels
  5. effort
  6. numbers

Original Text

"Why is this so hard?" you may ask. Cameras can take pictures like this one by converting lights into a two-dimensional array of numbers known as pixels, but these are just lifeless numbers. They do not carry meaning in themselves. Just like to hear is not the same as to listen, to take pictures is not the same as to see, and by seeing, we really mean understanding. In fact, it took Mother Nature 540 million years of hard work to do this task, and much of that effort went into developing the visual processing apparatus of our brains, not the eyes themselves. So vision begins with the eyes, but it truly takes place in the brain.

Frequently Occurring Word Combinations

ngrams of length 2

collocation frequency
machine learning 3
computer algorithm 3
neural network 3
computer vision 2
training images 2
data set 2
imagenet project 2
amazon mechanical 2
mechanical turk 2
big data 2
convolutional neural 2
object recognition 2
car prices 2
cat lying 2
baseball bat 2

ngrams of length 3

collocation frequency
amazon mechanical turk 2

Important Words

  1. apparatus
  2. array
  3. begins
  4. brain
  5. brains
  6. cameras
  7. carry
  8. converting
  9. developing
  10. effort
  11. eyes
  12. fact
  13. hard
  14. hear
  15. lifeless
  16. lights
  17. listen
  18. meaning
  19. million
  20. mother
  21. nature
  22. numbers
  23. pictures
  24. pixels
  25. place
  26. processing
  27. takes
  28. task
  29. understanding
  30. vision
  31. visual
  32. work
  33. years