Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 551 · 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.🎯 Ishaan’s recycling sorter was tested on 25 new waste photos and got 21 right. What is its accuracy in percent?
2. 2.🧪 What is accuracy? (a) total − correct (b) total × 2 (c) correct + total (d) correct ÷ total × 100
3. 3.📋 Planning an AI project: which comes first — work out the accuracy or train the model? (a) work out the accuracy (b) train the model
4. 4.📦 Nisha collected 90 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
5. 5.🎯 Arjun’s recycling sorter was tested on 20 new waste photos and got 20 right. What is its accuracy in percent?
6. 6.🎯 Kabir’s handwriting reader was tested on 25 new handwritten letters and got 18 right. What is its accuracy in percent?
7. 7.🧪 Why must you test a model on examples it has NOT seen? (a) to see if it learned (b) to save paper (c) to make it faster (d) to make it bigger
8. 8.🎯 Meera’s leaf identifier is 70% accurate. If it is tested on 70 new leaf photos, how many should it get right?
9. 9.🎯 Vihaan’s recycling sorter is 80% accurate. If it is tested on 70 new waste photos, how many should it get right?
10. 10.🎯 Meera’s fruit sorter was tested on 5 new fruit photos and got 3 right. What is its accuracy in percent?
11. 11.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
12. 12.❌ Ananya’s spam spotter was tested on 39 new messages and got 32 right. How many did it get wrong?
13. 13.🎯 Arjun’s leaf identifier was tested on 10 new leaf photos and got 6 right. What is its accuracy in percent?
14. 14.🧪 You can plan a simple AI project with… (a) a secret password (b) only a big robot (c) nothing at all (d) paper and examples
15. 15.🎯 Ishaan’s fruit sorter is 90% accurate. If it is tested on 30 new fruit photos, how many should it get right?
16. 16.❌ Vihaan’s recycling sorter was tested on 45 new waste photos and got 36 right. How many did it get wrong?
17. 17.📋 Planning an AI project: which comes first — try unseen examples or correct bad labels? (a) try unseen examples (b) correct bad labels
18. 18.❌ Ishaan’s bird-song app was tested on 11 new bird songs and got 10 right. How many did it get wrong?
19. 19.❌ Rohan’s recycling sorter was tested on 13 new waste photos and got 11 right. How many did it get wrong?
20. 20.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
21. 21.❌ Aarav’s spam spotter was tested on 46 new messages and got 37 right. How many did it get wrong?
22. 22.📋 Planning an AI project: which comes first — label each example or choose what to sort? (a) label each example (b) choose what to sort
23. 23.📋 Planning an AI project: which comes first — pick a question to solve or tag each photo by type? (a) pick a question to solve (b) tag each photo by type
24. 24.📋 Planning an AI project: which comes first — split train and test or tag each photo by type? (a) split train and test (b) tag each photo by type
25. 25.⚖️ Two leaf identifier models were tested on the same 50 leaf photos. Model A got 40 right and Model B got 31 right. How many percentage points more accurate is Model A?
26. 26.📋 Planning an AI project: which comes first — try unseen examples or split train and test? (a) try unseen examples (b) split train and test
27. 27.❌ Rohan’s spam spotter was tested on 16 new messages and got 15 right. How many did it get wrong?
28. 28.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
29. 29.❌ Rohan’s fruit sorter was tested on 15 new fruit photos and got 12 right. How many did it get wrong?
30. 30.🎯 Tara’s bird-song app was tested on 20 new bird songs and got 11 right. What is its accuracy in percent?
31. 31.📋 Planning an AI project: which comes first — improve data, retest or label each example? (a) improve data, retest (b) label each example
32. 32.🎯 Ishaan’s handwriting reader is 90% accurate. If it is tested on 60 new handwritten letters, how many should it get right?
33. 33.📦 Diya collected 100 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
34. 34.📋 Planning an AI project: which comes first — calculate percent right or correct bad labels? (a) calculate percent right (b) correct bad labels
35. 35.📦 Rohan collected 80 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
36. 36.📋 Planning an AI project: which comes first — correct bad labels or collect fruit photos? (a) correct bad labels (b) collect fruit photos
37. 37.📦 Saanvi collected 180 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
38. 38.📦 Ishaan collected 90 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
39. 39.❌ Saanvi’s leaf identifier was tested on 49 new leaf photos and got 46 right. How many did it get wrong?
40. 40.❌ Rohan’s recycling sorter was tested on 36 new waste photos and got 33 right. How many did it get wrong?

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