Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 431 · 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: “clear, sharp examples” is bad for training a model. (a) False (b) True
2. 2.True or false: the message “Send your password to claim a prize” should be labelled “spam”. (a) False (b) True
3. 3.🏷️ 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
4. 4.🐶 To teach a model to spot dogs in photos, what do you give it? (a) many labelled photos (b) a list of rules only (c) a song about dogs (d) one single photo
5. 5.🔍 Which is the odd one out? (a) examples of every type (b) correct labels (c) wrong labels (d) new data for testing
6. 6.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Earn ₹50,000 a day from home!!!” (a) spam (b) not spam
7. 7.Which of these is bad for training a model? (a) labels added at random (b) checking labels twice (c) correct labels (d) new data for testing
8. 8.🔍 Which is the odd one out? (a) copies of one photo (b) correct labels (c) blurry, unclear photos (d) labels added at random
9. 9.🔍 Which is the odd one out? (a) blurry, unclear photos (b) photos in many lights (c) checking labels twice (d) examples of every type
10. 10.True or false: “only one kind of example” is bad for training a model. (a) True (b) False
11. 11.🏷️ 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
12. 12.🥭 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 may get it wrong (d) it will turn yellow
13. 13.📚 Good or bad for training a model: copies of one photo? (a) good for training (b) bad for training
14. 14.True or false: “very few examples” is good for training a model. (a) True (b) False
15. 15.True or false: “many varied examples” is bad for training a model. (a) False (b) True
16. 16.🏷️ 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
17. 17.True or false: the message “Share your OTP to get cashback” should be labelled “not spam”. (a) False (b) True
18. 18.Which of these is good for training a model? (a) labels added at random (b) very few examples (c) wrong labels (d) examples of every type
19. 19.True or false: the message “Happy birthday! See you at lunch” should be labelled “not spam”. (a) True (b) False
20. 20.Which of these is good for training a model? (a) many varied examples (b) only one kind of example (c) blurry, unclear photos (d) very few examples
21. 21.📚 Good or bad for training a model: new data for testing? (a) bad for training (b) good for training
22. 22.📚 Usually, more good examples make a model… (a) forget everything (b) change colour (c) slower to switch on (d) better at its task
23. 23.📚 Good or bad for training a model: examples of every type? (a) good for training (b) bad for training
24. 24.True or false: the message “Happy birthday! See you at lunch” should be labelled “spam”. (a) True (b) False
25. 25.📚 Good or bad for training a model: blurry, unclear photos? (a) bad for training (b) good for training
26. 26.True or false: “checking labels twice” is good for training a model. (a) True (b) False
27. 27.🧠 Machine learning is a way for computers to… (a) clean screens (b) learn from data (c) print pages (d) charge faster
28. 28.🔍 Which is the odd one out? (a) new data for testing (b) very few examples (c) copies of one photo (d) blurry, unclear photos
29. 29.Which of these is bad for training a model? (a) many varied examples (b) new data for testing (c) copies of one photo (d) examples of every type
30. 30.📚 Good or bad for training a model: very few examples? (a) good for training (b) bad for training
31. 31.📚 Good or bad for training a model: only one kind of example? (a) bad for training (b) good for training
32. 32.True or false: the message “Please buy milk on the way home” should be labelled “not spam”. (a) True (b) False
33. 33.📚 Good or bad for training a model: photos in many lights? (a) bad for training (b) good for training
34. 34.Which of these is good for training a model? (a) very few examples (b) new data for testing (c) blurry, unclear photos (d) copies of one photo
35. 35.Which of these is good for training a model? (a) only one kind of example (b) correct labels (c) testing on training data (d) very few examples
36. 36.Which of these is bad for training a model? (a) photos in many lights (b) only one kind of example (c) many varied examples (d) new data for testing
37. 37.Which of these is bad for training a model? (a) correct labels (b) clear, sharp examples (c) photos in many lights (d) very few examples
38. 38.🔍 Which is the odd one out? (a) very few examples (b) examples of every type (c) copies of one photo (d) wrong labels
39. 39.True or false: “new data for testing” is good for training a model. (a) True (b) False
40. 40.True or false: “examples of every type” is bad for training a model. (a) False (b) True

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