Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 764 · 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.🎯 Rohan’s leaf identifier is 80% accurate. If it is tested on 80 new leaf photos, how many should it get right?
2. 2.🎯 Ishaan’s bird-song app is 50% accurate. If it is tested on 20 new bird songs, how many should it get right?
3. 3.📋 Planning an AI project: which comes first — recheck every label or tag each photo by type? (a) recheck every label (b) tag each photo by type
4. 4.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 37 right and Model B got 28 right. How many percentage points more accurate is Model A?
5. 5.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 9 right and Model B got 6 right. How many percentage points more accurate is Model A?
6. 6.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) a new colour screen (c) fewer examples (d) more labelled examples
7. 7.📦 Ishaan collected 60 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
8. 8.📋 Planning an AI project: which comes first — gather many examples or calculate percent right? (a) gather many examples (b) calculate percent right
9. 9.📦 Kabir collected 110 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
10. 10.📦 Saanvi collected 200 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
11. 11.🧪 Why must you test a model on examples it has NOT seen? (a) to save paper (b) to make it bigger (c) to make it faster (d) to see if it learned
12. 12.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
13. 13.📋 Planning an AI project: which comes first — calculate percent right or improve data, retest? (a) calculate percent right (b) improve data, retest
14. 14.❌ Kabir’s leaf identifier was tested on 22 new leaf photos and got 17 right. How many did it get wrong?
15. 15.🧪 You can plan a simple AI project with… (a) only a big robot (b) paper and examples (c) nothing at all (d) a secret password
16. 16.🎯 Ishaan’s recycling sorter is 60% accurate. If it is tested on 70 new waste photos, how many should it get right?
17. 17.📋 Planning an AI project: which comes first — calculate percent right or train the model? (a) calculate percent right (b) train the model
18. 18.📋 Planning an AI project: which comes first — try unseen examples or work out the accuracy? (a) try unseen examples (b) work out the accuracy
19. 19.🧪 What is accuracy? (a) correct ÷ total × 100 (b) total − correct (c) correct + total (d) total × 2
20. 20.🎯 Vihaan’s leaf identifier was tested on 4 new leaf photos and got 4 right. What is its accuracy in percent?
21. 21.📋 Planning an AI project: which comes first — pick a question to solve or collect fruit photos? (a) pick a question to solve (b) collect fruit photos
22. 22.📋 Planning an AI project: which comes first — set aside test photos or train the model? (a) set aside test photos (b) train the model
23. 23.📦 Tara collected 150 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
24. 24.📦 Ishaan collected 150 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
25. 25.📦 Arjun collected 50 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
26. 26.📋 Planning an AI project: which comes first — set aside test photos or gather many examples? (a) set aside test photos (b) gather many examples
27. 27.🎯 Arjun’s handwriting reader is 80% accurate. If it is tested on 50 new handwritten letters, how many should it get right?
28. 28.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
29. 29.📦 Vihaan collected 140 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
30. 30.❌ Vihaan’s fruit sorter was tested on 35 new fruit photos and got 32 right. How many did it get wrong?
31. 31.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 31 right and Model B got 26 right. How many percentage points more accurate is Model A?
32. 32.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
33. 33.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 24 right and Model B got 22 right. How many percentage points more accurate is Model A?
34. 34.📋 Planning an AI project: which comes first — work out the accuracy or pick a question to solve? (a) work out the accuracy (b) pick a question to solve
35. 35.🎯 Nisha’s bird-song app is 70% accurate. If it is tested on 20 new bird songs, how many should it get right?
36. 36.📦 Diya collected 100 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
37. 37.📋 Planning an AI project: which comes first — test on new photos or recheck every label? (a) test on new photos (b) recheck every label
38. 38.📋 Planning an AI project: which comes first — set aside test photos or let it learn patterns? (a) set aside test photos (b) let it learn patterns
39. 39.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
40. 40.🎯 Saanvi’s leaf identifier is 50% accurate. If it is tested on 10 new leaf photos, how many should it get right?

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