← Design a tiny AI project lesson New set →

Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 435 · 40 questions
TalentJR

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.

NameDateTime takenScore ___ / 40
  1. 1.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 50 right and Model B got 49 right. How many percentage points more accurate is Model A?
  2. 2.🎯 Kabir’s bird-song app is 70% accurate. If it is tested on 40 new bird songs, how many should it get right?
  3. 3.📋 Planning an AI project: which comes first — try unseen examples or choose what to sort? (a) try unseen examples (b) choose what to sort
  4. 4.📋 Planning an AI project: which comes first — improve data, retest or gather many examples? (a) improve data, retest (b) gather many examples
  5. 5.🧪 You can plan a simple AI project with… (a) a secret password (b) only a big robot (c) paper and examples (d) nothing at all
  6. 6.🎯 Ananya’s handwriting reader was tested on 10 new handwritten letters and got 10 right. What is its accuracy in percent?
  7. 7.📋 Planning an AI project: which comes first — work out the accuracy or fix it and test again? (a) work out the accuracy (b) fix it and test again
  8. 8.📦 Vihaan collected 110 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  9. 9.🎯 Nisha’s handwriting reader is 90% accurate. If it is tested on 100 new handwritten letters, how many should it get right?
  10. 10.📋 Planning an AI project: which comes first — choose what to sort or fix it and test again? (a) choose what to sort (b) fix it and test again
  11. 11.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to make it bigger (c) to see if it learned (d) to save paper
  12. 12.📦 Saanvi collected 110 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  13. 13.🎯 Meera’s recycling sorter is 90% accurate. If it is tested on 60 new waste photos, how many should it get right?
  14. 14.🎯 Meera’s handwriting reader is 80% accurate. If it is tested on 40 new handwritten letters, how many should it get right?
  15. 15.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) fewer examples (c) a louder speaker (d) a new colour screen
  16. 16.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 15 right and Model B got 14 right. How many percentage points more accurate is Model A?
  17. 17.📋 Planning an AI project: which comes first — collect fruit photos or label each example? (a) collect fruit photos (b) label each example
  18. 18.📋 Planning an AI project: which comes first — correct bad labels or collect fruit photos? (a) correct bad labels (b) collect fruit photos
  19. 19.🎯 Diya’s handwriting reader is 60% accurate. If it is tested on 40 new handwritten letters, how many should it get right?
  20. 20.📦 Diya collected 130 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  21. 21.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
  22. 22.🎯 Arjun’s fruit sorter is 50% accurate. If it is tested on 60 new fruit photos, how many should it get right?
  23. 23.❌ Arjun’s spam spotter was tested on 40 new messages and got 33 right. How many did it get wrong?
  24. 24.📋 Planning an AI project: which comes first — fix it and test again or collect fruit photos? (a) fix it and test again (b) collect fruit photos
  25. 25.🎯 Meera’s spam spotter is 70% accurate. If it is tested on 60 new messages, how many should it get right?
  26. 26.📋 Planning an AI project: which comes first — work out the accuracy or try unseen examples? (a) work out the accuracy (b) try unseen examples
  27. 27.📋 Planning an AI project: which comes first — test on new photos or label each example? (a) test on new photos (b) label each example
  28. 28.❌ Vihaan’s leaf identifier was tested on 30 new leaf photos and got 21 right. How many did it get wrong?
  29. 29.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 46 right and Model B got 44 right. How many percentage points more accurate is Model A?
  30. 30.🎯 Meera’s spam spotter is 80% accurate. If it is tested on 80 new messages, how many should it get right?
  31. 31.📋 Planning an AI project: which comes first — recheck every label or improve data, retest? (a) recheck every label (b) improve data, retest
  32. 32.📋 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
  33. 33.❌ Ananya’s spam spotter was tested on 20 new messages and got 17 right. How many did it get wrong?
  34. 34.📋 Planning an AI project: which comes first — split train and test or correct bad labels? (a) split train and test (b) correct bad labels
  35. 35.📋 Planning an AI project: which comes first — calculate percent right or let it learn patterns? (a) calculate percent right (b) let it learn patterns
  36. 36.📋 Planning an AI project: which comes first — let it learn patterns or split train and test? (a) let it learn patterns (b) split train and test
  37. 37.❌ Saanvi’s fruit sorter was tested on 37 new fruit photos and got 35 right. How many did it get wrong?
  38. 38.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 17 right and Model B got 13 right. How many percentage points more accurate is Model A?
  39. 39.📦 Diya collected 110 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  40. 40.🎯 Ishaan’s handwriting reader is 50% accurate. If it is tested on 30 new handwritten letters, how many should it get right?

Answer key

  1. 2
  2. 28
  3. choose what to sort
  4. gather many examples
  5. paper and examples
  6. 100
  7. work out the accuracy
  8. 88
  9. 90
  10. choose what to sort
  11. to see if it learned
  12. 88
  13. 54
  14. 32
  15. more labelled examples
  16. 5
  17. collect fruit photos
  18. collect fruit photos
  19. 24
  20. 104
  21. correct ÷ total × 100
  22. 30
  23. 7
  24. collect fruit photos
  25. 42
  26. try unseen examples
  27. label each example
  28. 9
  29. 4
  30. 64
  31. recheck every label
  32. calculate percent right
  33. 3
  34. correct bad labels
  35. let it learn patterns
  36. split train and test
  37. 2
  38. 20
  39. 88
  40. 15

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