Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 220 · 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) checking labels twice (b) correct labels (c) photos in many lights (d) testing on training data
2. 2.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Please buy milk on the way home” (a) not spam (b) spam
3. 3.True or false: “wrong labels” is bad for training a model. (a) False (b) True
4. 4.Which of these is good for training a model? (a) new data for testing (b) only one kind of example (c) copies of one photo (d) labels added at random
5. 5.📚 Good or bad for training a model: clear, sharp examples? (a) bad for training (b) good for training
6. 6.True or false: the message “Last chance! Free gift card inside” should be labelled “not spam”. (a) False (b) True
7. 7.📚 Good or bad for training a model: correct labels? (a) good for training (b) bad for training
8. 8.Which of these is bad for training a model? (a) wrong labels (b) new data for testing (c) clear, sharp examples (d) examples of every type
9. 9.🐶 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
10. 10.Which of these is good for training a model? (a) testing on training data (b) wrong labels (c) only one kind of example (d) photos in many lights
11. 11.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
12. 12.Which of these is bad for training a model? (a) blurry, unclear photos (b) checking labels twice (c) clear, sharp examples (d) photos in many lights
13. 13.🔍 Which is the odd one out? (a) new data for testing (b) wrong labels (c) copies of one photo (d) very few examples
14. 14.📚 Good or bad for training a model: only one kind of example? (a) bad for training (b) good for training
15. 15.Which of these is good for training a model? (a) labels added at random (b) wrong labels (c) blurry, unclear photos (d) checking labels twice
16. 16.🔍 Which is the odd one out? (a) testing on training data (b) correct labels (c) clear, sharp examples (d) photos in many lights
17. 17.True or false: “labels added at random” is bad for training a model. (a) True (b) False
18. 18.📚 Good or bad for training a model: labels added at random? (a) good for training (b) bad for training
19. 19.Which of these is bad for training a model? (a) correct labels (b) clear, sharp examples (c) very few examples (d) checking labels twice
20. 20.📚 Good or bad for training a model: new data for testing? (a) bad for training (b) good for training
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) spam (b) not spam
22. 22.🏷️ 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
23. 23.Which of these is good for training a model? (a) testing on training data (b) labels added at random (c) many varied examples (d) blurry, unclear photos
24. 24.True or false: the message “The class picnic is on Friday at 8 am” should be labelled “not spam”. (a) False (b) True
25. 25.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Happy birthday! See you at lunch” (a) not spam (b) spam
26. 26.🔍 Which is the odd one out? (a) very few examples (b) clear, sharp examples (c) examples of every type (d) new data for testing
27. 27.📚 Good or bad for training a model: blurry, unclear photos? (a) good for training (b) bad for training
28. 28.True or false: “many varied examples” is bad for training a model. (a) True (b) False
29. 29.True or false: the message “Please buy milk on the way home” should be labelled “spam”. (a) True (b) False
30. 30.🧠 Machine learning is a way for computers to… (a) clean screens (b) learn from data (c) print pages (d) charge faster
31. 31.📚 Good or bad for training a model: photos in many lights? (a) good for training (b) bad for training
32. 32.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it may get it wrong (b) it will turn yellow (c) it will shut down (d) it will be perfect
33. 33.📚 Usually, more good examples make a model… (a) slower to switch on (b) forget everything (c) better at its task (d) change colour
34. 34.🔍 Which is the odd one out? (a) examples of every type (b) very few examples (c) testing on training data (d) wrong labels
35. 35.True or false: “correct labels” is bad for training a model. (a) True (b) False
36. 36.🔍 Which is the odd one out? (a) photos in many lights (b) labels added at random (c) new data for testing (d) many varied examples
37. 37.📚 Good or bad for training a model: very few examples? (a) bad for training (b) good for training
38. 38.📚 Good or bad for training a model: testing on training data? (a) good for training (b) bad for training
39. 39.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Send your password to claim a prize” (a) not spam (b) spam
40. 40.True or false: “examples of every type” is good for training a model. (a) False (b) True

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