Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 950 · 40 questions

AI tip (Accuracy = correct ÷ total × 100): Steps: 1 choose a problem → 2 collect examples → 3 label them → 4 check and correct bad labels (clean the data) → 5 split into training and test sets → 6 train → 7 test with new examples → 8 measure accuracy → 9 improve the data and retest. Accuracy = correct ÷ total × 100. Wrong = total − correct. Expected right = accuracy ÷ 100 × total. Keep some examples apart for testing (for example one fifth); the rest are for training.

1. 1.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 7 right and Model B got 6 right. How many percentage points more accurate is Model A?
2. 2.🎯 Aarav’s recycling sorter is 60% accurate. If it is tested on 60 new waste photos, how many should it get right?
3. 3.🎯 Vihaan’s bird-song app is 50% accurate. If it is tested on 10 new bird songs, how many should it get right?
4. 4.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to make it faster (c) to save paper (d) to see if it learned
5. 5.❌ Nisha’s leaf identifier was tested on 45 new leaf photos and got 37 right. How many did it get wrong?
6. 6.📋 Planning an AI project: which comes first — set aside test photos or test on new photos? (a) set aside test photos (b) test on new photos
7. 7.📋 Planning an AI project: which comes first — test on new photos or split train and test? (a) test on new photos (b) split train and test
8. 8.📋 Planning an AI project: which comes first — correct bad labels or improve data, retest? (a) correct bad labels (b) improve data, retest
9. 9.📋 Planning an AI project: which comes first — test on new photos or collect fruit photos? (a) test on new photos (b) collect fruit photos
10. 10.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) fewer examples (b) more labelled examples (c) a louder speaker (d) a new colour screen
11. 11.📋 Planning an AI project: which comes first — correct bad labels or work out the accuracy? (a) correct bad labels (b) work out the accuracy
12. 12.📋 Planning an AI project: which comes first — calculate percent right or train the model? (a) calculate percent right (b) train the model
13. 13.📋 Planning an AI project: which comes first — fix it and test again or test on new photos? (a) fix it and test again (b) test on new photos
14. 14.🎯 Rohan’s handwriting reader is 50% accurate. If it is tested on 40 new handwritten letters, how many should it get right?
15. 15.🧪 What is accuracy? (a) correct + total (b) total × 2 (c) correct ÷ total × 100 (d) total − correct
16. 16.📋 Planning an AI project: which comes first — train the model or gather many examples? (a) train the model (b) gather many examples
17. 17.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
18. 18.🧪 You can plan a simple AI project with… (a) paper and examples (b) only a big robot (c) nothing at all (d) a secret password
19. 19.❌ Tara’s spam spotter was tested on 16 new messages and got 14 right. How many did it get wrong?
20. 20.❌ Diya’s leaf identifier was tested on 19 new leaf photos and got 11 right. How many did it get wrong?
21. 21.📋 Planning an AI project: which comes first — try unseen examples or improve data, retest? (a) try unseen examples (b) improve data, retest
22. 22.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 22 right and Model B got 20 right. How many percentage points more accurate is Model A?
23. 23.📋 Planning an AI project: which comes first — work out the accuracy or label each example? (a) work out the accuracy (b) label each example
24. 24.📋 Planning an AI project: which comes first — calculate percent right or set aside test photos? (a) calculate percent right (b) set aside test photos
25. 25.📦 Tara collected 50 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
26. 26.📋 Planning an AI project: which comes first — calculate percent right or fix it and test again? (a) calculate percent right (b) fix it and test again
27. 27.📋 Planning an AI project: which comes first — train the model or fix it and test again? (a) train the model (b) fix it and test again
28. 28.📦 Vihaan collected 50 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
29. 29.🎯 Kabir’s recycling sorter is 80% accurate. If it is tested on 20 new waste photos, how many should it get right?
30. 30.🎯 Arjun’s handwriting reader is 80% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
31. 31.🎯 Tara’s spam spotter is 50% accurate. If it is tested on 40 new messages, how many should it get right?
32. 32.❌ Diya’s handwriting reader was tested on 26 new handwritten letters and got 23 right. How many did it get wrong?
33. 33.🎯 Kabir’s fruit sorter was tested on 25 new fruit photos and got 17 right. What is its accuracy in percent?
34. 34.❌ Meera’s fruit sorter was tested on 31 new fruit photos and got 27 right. How many did it get wrong?
35. 35.🎯 Saanvi’s leaf identifier was tested on 4 new leaf photos and got 2 right. What is its accuracy in percent?
36. 36.🎯 Diya’s bird-song app is 80% accurate. If it is tested on 10 new bird songs, how many should it get right?
37. 37.❌ Vihaan’s spam spotter was tested on 33 new messages and got 24 right. How many did it get wrong?
38. 38.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
39. 39.🎯 Meera’s handwriting reader was tested on 5 new handwritten letters and got 4 right. What is its accuracy in percent?
40. 40.❌ Nisha’s bird-song app was tested on 27 new bird songs and got 21 right. How many did it get wrong?

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