Machine Learning for Kids Worksheet

AI for students lesson 2: How machines learn from examples · Set 553 · 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 good for training a model? (a) only one kind of example (b) copies of one photo (c) wrong labels (d) checking labels twice
2. 2.True or false: “testing on training data” is good for training a model. (a) True (b) False
3. 3.🔍 Which is the odd one out? (a) blurry, unclear photos (b) wrong labels (c) photos in many lights (d) very few examples
4. 4.True or false: “new data for testing” is good for training a model. (a) False (b) True
5. 5.🏷️ 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
6. 6.True or false: the message “Your account is locked, pay ₹99 now” should be labelled “not spam”. (a) False (b) True
7. 7.🔍 Which is the odd one out? (a) many varied examples (b) photos in many lights (c) wrong labels (d) correct labels
8. 8.📚 Good or bad for training a model: examples of every type? (a) good for training (b) bad for training
9. 9.True or false: “many varied examples” is bad for training a model. (a) True (b) False
10. 10.True or false: “checking labels twice” is bad for training a model. (a) True (b) False
11. 11.🔍 Which is the odd one out? (a) checking labels twice (b) clear, sharp examples (c) photos in many lights (d) very few examples
12. 12.📚 Good or bad for training a model: very few examples? (a) bad for training (b) good for training
13. 13.🐶 To teach a model to spot dogs in photos, what do you give it? (a) a song about dogs (b) one single photo (c) a list of rules only (d) many labelled photos
14. 14.True or false: the message “Share your OTP to get cashback” should be labelled “spam”. (a) True (b) False
15. 15.Which of these is bad for training a model? (a) photos in many lights (b) new data for testing (c) examples of every type (d) only one kind of example
16. 16.📚 Usually, more good examples make a model… (a) slower to switch on (b) forget everything (c) change colour (d) better at its task
17. 17.📚 Good or bad for training a model: testing on training data? (a) good for training (b) bad for training
18. 18.📚 Good or bad for training a model: checking labels twice? (a) good for training (b) bad for training
19. 19.🔍 Which is the odd one out? (a) only one kind of example (b) copies of one photo (c) many varied examples (d) blurry, unclear photos
20. 20.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
21. 21.Which of these is good for training a model? (a) new data for testing (b) very few examples (c) blurry, unclear photos (d) testing on training data
22. 22.True or false: “wrong labels” is good for training a model. (a) True (b) False
23. 23.🔍 Which is the odd one out? (a) only one kind of example (b) clear, sharp examples (c) photos in many lights (d) new data for testing
24. 24.🔍 Which is the odd one out? (a) checking labels twice (b) clear, sharp examples (c) photos in many lights (d) blurry, unclear photos
25. 25.🔍 Which is the odd one out? (a) wrong labels (b) correct labels (c) very few examples (d) blurry, unclear photos
26. 26.🏷️ 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
27. 27.True or false: “blurry, unclear photos” is good for training a model. (a) True (b) False
28. 28.🔍 Which is the odd one out? (a) blurry, unclear photos (b) only one kind of example (c) new data for testing (d) copies of one photo
29. 29.True or false: the message “Earn ₹50,000 a day from home!!!” should be labelled “not spam”. (a) False (b) True
30. 30.Which of these is bad for training a model? (a) new data for testing (b) many varied examples (c) very few examples (d) checking labels twice
31. 31.True or false: “new data for testing” is bad for training a model. (a) False (b) True
32. 32.True or false: the message “Your account is locked, pay ₹99 now” should be labelled “spam”. (a) False (b) True
33. 33.True or false: “blurry, unclear photos” is bad for training a model. (a) False (b) True
34. 34.🧠 Machine learning is a way for computers to… (a) print pages (b) charge faster (c) learn from data (d) clean screens
35. 35.True or false: the message “You won a free phone! Click now!” should be labelled “spam”. (a) True (b) False
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: “copies of one photo” is good for training a model. (a) False (b) True
38. 38.Which of these is good for training a model? (a) blurry, unclear photos (b) testing on training data (c) labels added at random (d) photos in many lights
39. 39.📚 Good or bad for training a model: blurry, unclear photos? (a) bad for training (b) good for training
40. 40.🔍 Which is the odd one out? (a) examples of every type (b) testing on training data (c) labels added at random (d) very few examples

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