Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 55 · 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 is the odd one out? (a) photos in many lights (b) checking labels twice (c) blurry, unclear photos (d) examples of every type
2. 2.Which of these is bad for training a model? (a) blurry, unclear photos (b) many varied examples (c) photos in many lights (d) checking labels twice
3. 3.Which of these is good for training a model? (a) wrong labels (b) correct labels (c) labels added at random (d) only one kind of example
4. 4.🏷️ 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
5. 5.🔍 Which is the odd one out? (a) testing on training data (b) very few examples (c) examples of every type (d) labels added at random
6. 6.🔍 Which is the odd one out? (a) blurry, unclear photos (b) labels added at random (c) only one kind of example (d) many varied examples
7. 7.🏷️ What is a “label” in machine learning? (a) a sticker on a laptop (b) the font size (c) the right answer tag (d) the price
8. 8.📚 Good or bad for training a model: testing on training data? (a) bad for training (b) good for training
9. 9.📚 Usually, more good examples make a model… (a) change colour (b) slower to switch on (c) better at its task (d) forget everything
10. 10.📚 Good or bad for training a model: photos in many lights? (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? “Happy birthday! See you at lunch” (a) spam (b) not spam
12. 12.Which of these is bad for training a model? (a) correct labels (b) photos in many lights (c) only one kind of example (d) new data for testing
13. 13.True or false: “photos in many lights” is good for training a model. (a) False (b) True
14. 14.🔍 Which is the odd one out? (a) correct labels (b) photos in many lights (c) examples of every type (d) very few examples
15. 15.🏷️ 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
16. 16.📚 Good or bad for training a model: copies of one photo? (a) bad for training (b) good for training
17. 17.Which of these is bad for training a model? (a) many varied examples (b) very few examples (c) clear, sharp examples (d) new data for testing
18. 18.🏷️ 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
19. 19.Which of these is bad for training a model? (a) correct labels (b) checking labels twice (c) many varied examples (d) testing on training data
20. 20.🐶 To teach a model to spot dogs in photos, what do you give it? (a) a list of rules only (b) one single photo (c) a song about dogs (d) many labelled photos
21. 21.True or false: “correct labels” is bad for training a model. (a) False (b) True
22. 22.Which of these is good for training a model? (a) only one kind of example (b) very few examples (c) photos in many lights (d) copies of one photo
23. 23.True or false: the message “Share your OTP to get cashback” should be labelled “not spam”. (a) False (b) True
24. 24.Which of these is good for training a model? (a) labels added at random (b) only one kind of example (c) copies of one photo (d) new data for testing
25. 25.🔍 Which is the odd one out? (a) correct labels (b) copies of one photo (c) blurry, unclear photos (d) testing on training data
26. 26.📚 Good or bad for training a model: very few examples? (a) good for training (b) bad for training
27. 27.🔍 Which is the odd one out? (a) checking labels twice (b) copies of one photo (c) photos in many lights (d) correct labels
28. 28.🥭 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
29. 29.🏷️ 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
30. 30.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
31. 31.🔍 Which is the odd one out? (a) very few examples (b) wrong labels (c) new data for testing (d) labels added at random
32. 32.🔍 Which is the odd one out? (a) checking labels twice (b) only one kind of example (c) new data for testing (d) clear, sharp examples
33. 33.True or false: the message “The class picnic is on Friday at 8 am” should be labelled “spam”. (a) False (b) True
34. 34.🏷️ 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
35. 35.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Your account is locked, pay ₹99 now” (a) spam (b) not spam
36. 36.📚 Good or bad for training a model: only one kind of example? (a) bad for training (b) good for training
37. 37.True or false: “testing on training data” is good for training a model. (a) False (b) True
38. 38.True or false: the message “Your account is locked, pay ₹99 now” should be labelled “spam”. (a) True (b) False
39. 39.🧠 Machine learning is a way for computers to… (a) learn from data (b) clean screens (c) print pages (d) charge faster
40. 40.True or false: the message “Your library book is due on Monday” should be labelled “not spam”. (a) True (b) False

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