Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 490 · 40 questions

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.

1. 1.True or false: the message “Science project groups are on the board” should be labelled “spam”. (a) True (b) False
2. 2.True or false: the message “Match practice moved to 5 pm” should be labelled “spam”. (a) True (b) False
3. 3.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Send your password to claim a prize” (a) spam (b) not spam
4. 4.🔍 Which is the odd one out? (a) labels added at random (b) copies of one photo (c) correct labels (d) only one kind of example
5. 5.True or false: “wrong labels” is good for training a model. (a) False (b) True
6. 6.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it will shut down (b) it may get it wrong (c) it will turn yellow (d) it will be perfect
7. 7.📚 Good or bad for training a model: photos in many lights? (a) good for training (b) bad for training
8. 8.📚 Good or bad for training a model: new data for testing? (a) good for training (b) bad for training
9. 9.Which of these is bad for training a model? (a) photos in many lights (b) new data for testing (c) very few examples (d) many varied examples
10. 10.📚 Good or bad for training a model: checking labels twice? (a) bad for training (b) good for training
11. 11.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Earn ₹50,000 a day from home!!!” (a) not spam (b) spam
12. 12.True or false: “copies of one photo” is bad for training a model. (a) True (b) False
13. 13.Which of these is good for training a model? (a) only one kind of example (b) testing on training data (c) examples of every type (d) copies of one photo
14. 14.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Science project groups are on the board” (a) spam (b) not spam
15. 15.Which of these is bad for training a model? (a) photos in many lights (b) clear, sharp examples (c) only one kind of example (d) correct labels
16. 16.True or false: “only one kind of example” is bad for training a model. (a) False (b) True
17. 17.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
18. 18.True or false: “examples of every type” is bad for training a model. (a) True (b) False
19. 19.🔍 Which is the odd one out? (a) checking labels twice (b) examples of every type (c) clear, sharp examples (d) testing on training data
20. 20.True or false: the message “Share your OTP to get cashback” should be labelled “spam”. (a) False (b) True
21. 21.True or false: the message “Last chance! Free gift card inside” should be labelled “not spam”. (a) True (b) False
22. 22.True or false: the message “Send your password to claim a prize” should be labelled “not spam”. (a) False (b) True
23. 23.📚 Good or bad for training a model: examples of every type? (a) bad for training (b) good for training
24. 24.True or false: “very few examples” is bad for training a model. (a) False (b) True
25. 25.🔍 Which is the odd one out? (a) new data for testing (b) only one kind of example (c) checking labels twice (d) examples of every type
26. 26.🐶 To teach a model to spot dogs in photos, what do you give it? (a) a song about dogs (b) many labelled photos (c) one single photo (d) a list of rules only
27. 27.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Your library book is due on Monday” (a) spam (b) not spam
28. 28.🔍 Which is the odd one out? (a) examples of every type (b) copies of one photo (c) wrong labels (d) very few examples
29. 29.True or false: the message “Happy birthday! See you at lunch” should be labelled “not spam”. (a) True (b) False
30. 30.📚 Good or bad for training a model: copies of one photo? (a) bad for training (b) good for training
31. 31.📚 Usually, more good examples make a model… (a) forget everything (b) change colour (c) better at its task (d) slower to switch on
32. 32.📚 Good or bad for training a model: labels added at random? (a) good for training (b) bad for training
33. 33.True or false: “photos in many lights” is bad for training a model. (a) False (b) True
34. 34.🔍 Which is the odd one out? (a) only one kind of example (b) very few examples (c) labels added at random (d) clear, sharp examples
35. 35.True or false: “clear, sharp examples” is bad for training a model. (a) True (b) False
36. 36.Which of these is bad for training a model? (a) new data for testing (b) testing on training data (c) examples of every type (d) correct labels
37. 37.Which of these is good for training a model? (a) wrong labels (b) blurry, unclear photos (c) clear, sharp examples (d) labels added at random
38. 38.True or false: “only one kind of example” is good for training a model. (a) True (b) False
39. 39.Which of these is bad for training a model? (a) copies of one photo (b) photos in many lights (c) correct labels (d) new data for testing
40. 40.🔍 Which is the odd one out? (a) many varied examples (b) very few examples (c) examples of every type (d) correct labels

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