Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 192 · 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.Which of these is bad for training a model? (a) new data for testing (b) clear, sharp examples (c) photos in many lights (d) labels added at random
2. 2.🏷️ 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
3. 3.📚 Usually, more good examples make a model… (a) slower to switch on (b) forget everything (c) better at its task (d) change colour
4. 4.True or false: “clear, sharp examples” is good for training a model. (a) False (b) True
5. 5.🔍 Which is the odd one out? (a) photos in many lights (b) testing on training data (c) blurry, unclear photos (d) labels added at random
6. 6.🔍 Which is the odd one out? (a) labels added at random (b) wrong labels (c) examples of every type (d) copies of one photo
7. 7.🏷️ 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
8. 8.True or false: the message “Earn ₹50,000 a day from home!!!” should be labelled “not spam”. (a) True (b) False
9. 9.True or false: “testing on training data” is bad for training a model. (a) False (b) True
10. 10.True or false: the message “Last chance! Free gift card inside” should be labelled “not spam”. (a) True (b) False
11. 11.True or false: the message “Send your password to claim a prize” should be labelled “not spam”. (a) True (b) False
12. 12.📚 Good or bad for training a model: photos in many lights? (a) bad for training (b) good for training
13. 13.📚 Good or bad for training a model: only one kind of example? (a) good for training (b) bad for training
14. 14.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Last chance! Free gift card inside” (a) spam (b) not spam
15. 15.📚 Good or bad for training a model: copies of one photo? (a) bad for training (b) good for training
16. 16.📚 Good or bad for training a model: new data for testing? (a) good for training (b) bad for training
17. 17.🐶 To teach a model to spot dogs in photos, what do you give it? (a) a list of rules only (b) a song about dogs (c) many labelled photos (d) one single photo
18. 18.Which of these is good for training a model? (a) blurry, unclear photos (b) new data for testing (c) labels added at random (d) wrong labels
19. 19.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Match practice moved to 5 pm” (a) not spam (b) spam
20. 20.True or false: the message “Please buy milk on the way home” should be labelled “spam”. (a) True (b) False
21. 21.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “You won a free phone! Click now!” (a) not spam (b) spam
22. 22.🏷️ 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
23. 23.Which of these is good for training a model? (a) wrong labels (b) photos in many lights (c) testing on training data (d) labels added at random
24. 24.Which of these is good for training a model? (a) testing on training data (b) wrong labels (c) only one kind of example (d) many varied examples
25. 25.True or false: “examples of every type” is bad for training a model. (a) True (b) False
26. 26.🔍 Which is the odd one out? (a) clear, sharp examples (b) photos in many lights (c) testing on training data (d) many varied examples
27. 27.True or false: the message “Science project groups are on the board” should be labelled “not spam”. (a) False (b) True
28. 28.Which of these is good for training a model? (a) testing on training data (b) wrong labels (c) clear, sharp examples (d) labels added at random
29. 29.True or false: “photos in many lights” is good for training a model. (a) False (b) True
30. 30.True or false: the message “Happy birthday! See you at lunch” should be labelled “not spam”. (a) True (b) False
31. 31.Which of these is bad for training a model? (a) many varied examples (b) examples of every type (c) testing on training data (d) clear, sharp examples
32. 32.Which of these is bad for training a model? (a) new data for testing (b) only one kind of example (c) checking labels twice (d) photos in many lights
33. 33.🔍 Which is the odd one out? (a) photos in many lights (b) labels added at random (c) examples of every type (d) correct labels
34. 34.True or false: “examples of every type” is good for training a model. (a) True (b) False
35. 35.📚 Good or bad for training a model: testing on training data? (a) good for training (b) bad for training
36. 36.True or false: the message “Share your OTP to get cashback” should be labelled “not spam”. (a) False (b) True
37. 37.🏷️ 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
38. 38.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it will turn yellow (b) it will shut down (c) it may get it wrong (d) it will be perfect
39. 39.🔍 Which is the odd one out? (a) new data for testing (b) clear, sharp examples (c) examples of every type (d) only one kind of example
40. 40.📚 Good or bad for training a model: checking labels twice? (a) bad for training (b) good for training

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