Machine Learning for Kids Worksheet

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

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