← How machines learn from examples lesson New set →

Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 23 · 40 questions
TalentJR

AI tip (Show, label, learn): Machine learning learns patterns from many labelled examples — a label is the right answer tag on each example. Good for training: many varied examples, correct labels, every type the model will meet, and separate new data for testing. Bad for training: very few examples, wrong or random labels, only one kind of example, blurry examples, testing on the training data.

NameDateTime takenScore ___ / 40
  1. 1.Which of these is good for training a model? (a) very few examples (b) wrong labels (c) copies of one photo (d) clear, sharp examples
  2. 2.🔍 Which is the odd one out? (a) examples of every type (b) new data for testing (c) testing on training data (d) photos in many lights
  3. 3.🧠 Machine learning is a way for computers to… (a) charge faster (b) clean screens (c) print pages (d) learn from data
  4. 4.📚 Good or bad for training a model: only one kind of example? (a) bad for training (b) good for training
  5. 5.Which of these is bad for training a model? (a) photos in many lights (b) correct labels (c) wrong labels (d) new data for testing
  6. 6.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “The class picnic is on Friday at 8 am” (a) not spam (b) spam
  7. 7.True or false: “very few examples” is bad for training a model. (a) False (b) True
  8. 8.Which of these is bad for training a model? (a) clear, sharp examples (b) labels added at random (c) many varied examples (d) checking labels twice
  9. 9.🔍 Which is the odd one out? (a) checking labels twice (b) clear, sharp examples (c) very few examples (d) correct labels
  10. 10.True or false: “correct labels” is good for training a model. (a) True (b) False
  11. 11.📚 Usually, more good examples make a model… (a) forget everything (b) better at its task (c) slower to switch on (d) change colour
  12. 12.True or false: “many varied examples” is good for training a model. (a) False (b) True
  13. 13.Which of these is bad for training a model? (a) photos in many lights (b) many varied examples (c) copies of one photo (d) examples of every type
  14. 14.True or false: “correct labels” is bad for training a model. (a) True (b) False
  15. 15.🔍 Which is the odd one out? (a) only one kind of example (b) new data for testing (c) very few examples (d) blurry, unclear photos
  16. 16.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Share your OTP to get cashback” (a) spam (b) not spam
  17. 17.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Earn ₹50,000 a day from home!!!” (a) spam (b) not spam
  18. 18.📚 Good or bad for training a model: wrong labels? (a) good for training (b) bad for training
  19. 19.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it will be perfect (b) it will turn yellow (c) it will shut down (d) it may get it wrong
  20. 20.📚 Good or bad for training a model: very few examples? (a) good for training (b) bad for training
  21. 21.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Match practice moved to 5 pm” (a) spam (b) not spam
  22. 22.🔍 Which is the odd one out? (a) checking labels twice (b) very few examples (c) copies of one photo (d) blurry, unclear photos
  23. 23.True or false: the message “Earn ₹50,000 a day from home!!!” should be labelled “not spam”. (a) True (b) False
  24. 24.🐶 To teach a model to spot dogs in photos, what do you give it? (a) many labelled photos (b) a list of rules only (c) one single photo (d) a song about dogs
  25. 25.True or false: the message “Earn ₹50,000 a day from home!!!” should be labelled “spam”. (a) False (b) True
  26. 26.Which of these is good for training a model? (a) labels added at random (b) blurry, unclear photos (c) testing on training data (d) correct labels
  27. 27.🔍 Which is the odd one out? (a) very few examples (b) photos in many lights (c) blurry, unclear photos (d) wrong labels
  28. 28.Which of these is good for training a model? (a) wrong labels (b) checking labels twice (c) blurry, unclear photos (d) very few examples
  29. 29.📚 Good or bad for training a model: copies of one photo? (a) bad for training (b) good for training
  30. 30.Which of these is good for training a model? (a) photos in many lights (b) very few examples (c) blurry, unclear photos (d) only one kind of example
  31. 31.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Happy birthday! See you at lunch” (a) spam (b) not spam
  32. 32.🔍 Which is the odd one out? (a) photos in many lights (b) copies of one photo (c) clear, sharp examples (d) correct labels
  33. 33.True or false: “many varied examples” is bad for training a model. (a) True (b) False
  34. 34.📚 Good or bad for training a model: examples of every type? (a) good for training (b) bad for training
  35. 35.🔍 Which is the odd one out? (a) labels added at random (b) new data for testing (c) many varied examples (d) photos in many lights
  36. 36.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Your account is locked, pay ₹99 now” (a) not spam (b) spam
  37. 37.Which of these is bad for training a model? (a) examples of every type (b) correct labels (c) very few examples (d) many varied examples
  38. 38.🏷️ What is a “label” in machine learning? (a) the price (b) the font size (c) the right answer tag (d) a sticker on a laptop
  39. 39.True or false: the message “The class picnic is on Friday at 8 am” should be labelled “spam”. (a) False (b) True
  40. 40.🔍 Which is the odd one out? (a) very few examples (b) correct labels (c) blurry, unclear photos (d) wrong labels

Answer key

  1. clear, sharp examples
  2. testing on training data
  3. learn from data
  4. bad for training
  5. wrong labels
  6. not spam
  7. True
  8. labels added at random
  9. very few examples
  10. True
  11. better at its task
  12. True
  13. copies of one photo
  14. False
  15. new data for testing
  16. spam
  17. spam
  18. bad for training
  19. it may get it wrong
  20. bad for training
  21. not spam
  22. checking labels twice
  23. False
  24. many labelled photos
  25. True
  26. correct labels
  27. photos in many lights
  28. checking labels twice
  29. bad for training
  30. photos in many lights
  31. not spam
  32. copies of one photo
  33. False
  34. good for training
  35. labels added at random
  36. spam
  37. very few examples
  38. the right answer tag
  39. False
  40. correct labels

Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students