Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 225 · 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: “labels added at random” is good for training a model. (a) False (b) True
2. 2.🏷️ 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
3. 3.Which of these is bad for training a model? (a) new data for testing (b) correct labels (c) very few examples (d) photos in many lights
4. 4.📚 Good or bad for training a model: photos in many lights? (a) bad for training (b) good for training
5. 5.True or false: the message “Last chance! Free gift card inside” should be labelled “spam”. (a) True (b) False
6. 6.🏷️ What is a “label” in machine learning? (a) the price (b) a sticker on a laptop (c) the right answer tag (d) the font size
7. 7.True or false: “many varied examples” is bad for training a model. (a) False (b) True
8. 8.📚 Good or bad for training a model: checking labels twice? (a) good for training (b) bad for training
9. 9.Which of these is bad for training a model? (a) checking labels twice (b) photos in many lights (c) wrong labels (d) correct labels
10. 10.🏷️ 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
11. 11.🔍 Which is the odd one out? (a) testing on training data (b) labels added at random (c) very few examples (d) new data for testing
12. 12.🐶 To teach a model to spot dogs in photos, what do you give it? (a) one single photo (b) many labelled photos (c) a list of rules only (d) a song about dogs
13. 13.True or false: the message “Your account is locked, pay ₹99 now” should be labelled “not spam”. (a) True (b) False
14. 14.📚 Usually, more good examples make a model… (a) slower to switch on (b) change colour (c) forget everything (d) better at its task
15. 15.🧠 Machine learning is a way for computers to… (a) learn from data (b) charge faster (c) print pages (d) clean screens
16. 16.🏷️ 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
17. 17.Which of these is bad for training a model? (a) correct labels (b) many varied examples (c) labels added at random (d) new data for testing
18. 18.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
19. 19.🔍 Which is the odd one out? (a) testing on training data (b) only one kind of example (c) labels added at random (d) photos in many lights
20. 20.📚 Good or bad for training a model: new data for testing? (a) bad for training (b) good for training
21. 21.True or false: “copies of one photo” is good for training a model. (a) False (b) True
22. 22.📚 Good or bad for training a model: correct labels? (a) bad for training (b) good for training
23. 23.True or false: “labels added at random” is bad for training a model. (a) True (b) False
24. 24.📚 Good or bad for training a model: examples of every type? (a) good for training (b) bad for training
25. 25.🔍 Which is the odd one out? (a) only one kind of example (b) examples of every type (c) testing on training data (d) labels added at random
26. 26.True or false: “checking labels twice” is bad for training a model. (a) True (b) False
27. 27.Which of these is good for training a model? (a) very few examples (b) wrong labels (c) correct labels (d) testing on training data
28. 28.True or false: the message “Send your password to claim a prize” should be labelled “not spam”. (a) False (b) True
29. 29.True or false: “blurry, unclear photos” is good for training a model. (a) True (b) False
30. 30.🏷️ 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
31. 31.🏷️ 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
32. 32.📚 Good or bad for training a model: copies of one photo? (a) good for training (b) bad for training
33. 33.🔍 Which is the odd one out? (a) labels added at random (b) blurry, unclear photos (c) only one kind of example (d) many varied examples
34. 34.True or false: “very few examples” is bad for training a model. (a) False (b) True
35. 35.🏷️ 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
36. 36.True or false: “only one kind of example” is bad for training a model. (a) True (b) False
37. 37.🏷️ 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
38. 38.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it will be perfect (b) it may get it wrong (c) it will turn yellow (d) it will shut down
39. 39.True or false: the message “Earn ₹50,000 a day from home!!!” should be labelled “spam”. (a) False (b) True
40. 40.🔍 Which is the odd one out? (a) many varied examples (b) examples of every type (c) checking labels twice (d) very few examples

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